AVX512FP16: Adjust builtin name for FP16 builtins to match AVX512F style
Commit Message
Hi,
For AVX512FP16 builtins, they all contain format like vaddph_v8hf,
while AVX512F builtins use addps128 which succeeded SSE/AVX style.
Adjust AVX512FP16 builtins to match such format.
Bootstraped/regtested on x86-64-*-linux, ok for master?
gcc/ChangeLog:
* config/i386/avx512fp16intrin.h: Adjust all builtin calls.
* config/i386/avx512fp16vlintrin.h: Likewise.
* config/i386/i386-builtin.def: Adjust builtin name to match
AVX512F style.
gcc/testsuite/ChangeLog:
* gcc.target/i386/avx-1.c: Adjust builtin macros.
* gcc.target/i386/sse-13.c: Likewise.
* gcc.target/i386/sse-23.c: Likewise.
---
gcc/config/i386/avx512fp16intrin.h | 1236 ++++++++++++------------
gcc/config/i386/avx512fp16vlintrin.h | 454 ++++-----
gcc/config/i386/i386-builtin.def | 130 +--
gcc/testsuite/gcc.target/i386/avx-1.c | 58 +-
gcc/testsuite/gcc.target/i386/sse-13.c | 58 +-
gcc/testsuite/gcc.target/i386/sse-23.c | 58 +-
6 files changed, 997 insertions(+), 997 deletions(-)
Comments
On Wed, Sep 15, 2021 at 5:08 PM Hongyu Wang via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> Hi,
>
> For AVX512FP16 builtins, they all contain format like vaddph_v8hf,
> while AVX512F builtins use addps128 which succeeded SSE/AVX style.
> Adjust AVX512FP16 builtins to match such format.
>
> Bootstraped/regtested on x86-64-*-linux, ok for master?
>
> gcc/ChangeLog:
>
> * config/i386/avx512fp16intrin.h: Adjust all builtin calls.
> * config/i386/avx512fp16vlintrin.h: Likewise.
> * config/i386/i386-builtin.def: Adjust builtin name to match
> AVX512F style.
>
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_vmsmaxv8hf3_mask, "__builtin_ia32_maxsh_mask",
IX86_BUILTIN_VMAXSH_V8HF_MASK, UNKNOWN, (int)
V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_vmsminv8hf3_mask, "__builtin_ia32_minsh_mask",
IX86_BUILTIN_VMINSH_V8HF_MASK, UNKNOWN, (int)
V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_cmpv8hf3_mask, "__builtin_ia32_cmpph128_mask",
IX86_BUILTIN_VCMPPH_V8HF_MASK, UNKNOWN, (int)
UQI_FTYPE_V8HF_V8HF_INT_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512vl_cmpv16hf3_mask, "__builtin_ia32_cmpph256_mask",
IX86_BUILTIN_VCMPPH_V16HF_MASK, UNKNOWN, (int)
UHI_FTYPE_V16HF_V16HF_INT_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512bw_cmpv32hf3_mask, "__builtin_ia32_cmpph512_mask",
IX86_BUILTIN_VCMPPH_V32HF_MASK, UNKNOWN, (int)
USI_FTYPE_V32HF_V32HF_INT_USI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_sqrtv8hf2_mask, "__builtin_ia32_sqrtph128_mask",
IX86_BUILTIN_VSQRTPH_V8HF_MASK, UNKNOWN, (int)
V8HF_FTYPE_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_sqrtv16hf2_mask, "__builtin_ia32_sqrtph256_mask",
IX86_BUILTIN_VSQRTPH_V16HF_MASK, UNKNOWN, (int)
V16HF_FTYPE_V16HF_V16HF_UHI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_rsqrtv8hf2_mask, "__builtin_ia32_rsqrtph128_mask",
IX86_BUILTIN_VRSQRTPH_V8HF_MASK, UNKNOWN, (int)
V8HF_FTYPE_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_rsqrtv16hf2_mask,
"__builtin_ia32_rsqrtph256_mask", IX86_BUILTIN_VRSQRTPH_V16HF_MASK,
UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_rsqrtv32hf2_mask,
"__builtin_ia32_rsqrtph512_mask", IX86_BUILTIN_VRSQRTPH_V32HF_MASK,
UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_vmrsqrtv8hf2_mask, "__builtin_ia32_rsqrtsh_mask",
IX86_BUILTIN_VRSQRTSH_V8HF_MASK, UNKNOWN, (int)
V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_rcpv8hf2_mask, "__builtin_ia32_rcpph128_mask",
IX86_BUILTIN_VRCPPH_V8HF_MASK, UNKNOWN, (int)
V8HF_FTYPE_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_rcpv16hf2_mask, "__builtin_ia32_rcpph256_mask",
IX86_BUILTIN_VRCPPH_V16HF_MASK, UNKNOWN, (int)
V16HF_FTYPE_V16HF_V16HF_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_rcpv32hf2_mask, "__builtin_ia32_rcpph512_mask",
IX86_BUILTIN_VRCPPH_V32HF_MASK, UNKNOWN, (int)
V32HF_FTYPE_V32HF_V32HF_USI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_vmrcpv8hf2_mask, "__builtin_ia32_rcpsh_mask",
IX86_BUILTIN_VRCPSH_V8HF_MASK, UNKNOWN, (int)
V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512fp16_scalefv8hf_mask,
"__builtin_ia32_scalefph128_mask", IX86_BUILTIN_VSCALEFPH_V8HF_MASK,
UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
CODE_FOR_avx512vl_scalefv16hf_mask, "__builtin_ia32_scalefph256_mask",
IX86_BUILTIN_VSCALEFPH_V16HF_MASK, UNKNOWN, (int)
V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
Could you also change IX86_BUILTIN_VSCALEFPH_V16HF_MASK
IX86_BUILTIN_VSCALEFPH256_MASK, similar for others.
> gcc/testsuite/ChangeLog:
>
> * gcc.target/i386/avx-1.c: Adjust builtin macros.
> * gcc.target/i386/sse-13.c: Likewise.
> * gcc.target/i386/sse-23.c: Likewise.
> ---
> gcc/config/i386/avx512fp16intrin.h | 1236 ++++++++++++------------
> gcc/config/i386/avx512fp16vlintrin.h | 454 ++++-----
> gcc/config/i386/i386-builtin.def | 130 +--
> gcc/testsuite/gcc.target/i386/avx-1.c | 58 +-
> gcc/testsuite/gcc.target/i386/sse-13.c | 58 +-
> gcc/testsuite/gcc.target/i386/sse-23.c | 58 +-
> 6 files changed, 997 insertions(+), 997 deletions(-)
>
> diff --git a/gcc/config/i386/avx512fp16intrin.h b/gcc/config/i386/avx512fp16intrin.h
> index 2fbfc140c44..5d66ca5c820 100644
> --- a/gcc/config/i386/avx512fp16intrin.h
> +++ b/gcc/config/i386/avx512fp16intrin.h
> @@ -229,15 +229,15 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_add_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> {
> - return __builtin_ia32_vaddph_v32hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_addph512_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_add_ph (__mmask32 __A, __m512h __B, __m512h __C)
> {
> - return __builtin_ia32_vaddph_v32hf_mask (__B, __C,
> - _mm512_setzero_ph (), __A);
> + return __builtin_ia32_addph512_mask (__B, __C,
> + _mm512_setzero_ph (), __A);
> }
>
> extern __inline __m512h
> @@ -251,15 +251,15 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_sub_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> {
> - return __builtin_ia32_vsubph_v32hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_subph512_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_sub_ph (__mmask32 __A, __m512h __B, __m512h __C)
> {
> - return __builtin_ia32_vsubph_v32hf_mask (__B, __C,
> - _mm512_setzero_ph (), __A);
> + return __builtin_ia32_subph512_mask (__B, __C,
> + _mm512_setzero_ph (), __A);
> }
>
> extern __inline __m512h
> @@ -273,15 +273,15 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_mul_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> {
> - return __builtin_ia32_vmulph_v32hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_mulph512_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_mul_ph (__mmask32 __A, __m512h __B, __m512h __C)
> {
> - return __builtin_ia32_vmulph_v32hf_mask (__B, __C,
> - _mm512_setzero_ph (), __A);
> + return __builtin_ia32_mulph512_mask (__B, __C,
> + _mm512_setzero_ph (), __A);
> }
>
> extern __inline __m512h
> @@ -295,15 +295,15 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_div_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> {
> - return __builtin_ia32_vdivph_v32hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_divph512_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_div_ph (__mmask32 __A, __m512h __B, __m512h __C)
> {
> - return __builtin_ia32_vdivph_v32hf_mask (__B, __C,
> - _mm512_setzero_ph (), __A);
> + return __builtin_ia32_divph512_mask (__B, __C,
> + _mm512_setzero_ph (), __A);
> }
>
> #ifdef __OPTIMIZE__
> @@ -311,9 +311,9 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_add_round_ph (__m512h __A, __m512h __B, const int __C)
> {
> - return __builtin_ia32_vaddph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1, __C);
> + return __builtin_ia32_addph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1, __C);
> }
>
> extern __inline __m512h
> @@ -321,7 +321,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_add_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> __m512h __D, const int __E)
> {
> - return __builtin_ia32_vaddph_v32hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_addph512_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m512h
> @@ -329,18 +329,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_add_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> const int __D)
> {
> - return __builtin_ia32_vaddph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_addph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A, __D);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_sub_round_ph (__m512h __A, __m512h __B, const int __C)
> {
> - return __builtin_ia32_vsubph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1, __C);
> + return __builtin_ia32_subph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1, __C);
> }
>
> extern __inline __m512h
> @@ -348,7 +348,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_sub_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> __m512h __D, const int __E)
> {
> - return __builtin_ia32_vsubph_v32hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_subph512_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m512h
> @@ -356,18 +356,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_sub_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> const int __D)
> {
> - return __builtin_ia32_vsubph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_subph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A, __D);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mul_round_ph (__m512h __A, __m512h __B, const int __C)
> {
> - return __builtin_ia32_vmulph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1, __C);
> + return __builtin_ia32_mulph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1, __C);
> }
>
> extern __inline __m512h
> @@ -375,7 +375,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_mul_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> __m512h __D, const int __E)
> {
> - return __builtin_ia32_vmulph_v32hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_mulph512_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m512h
> @@ -383,18 +383,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_mul_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> const int __D)
> {
> - return __builtin_ia32_vmulph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_mulph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A, __D);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_div_round_ph (__m512h __A, __m512h __B, const int __C)
> {
> - return __builtin_ia32_vdivph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1, __C);
> + return __builtin_ia32_divph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1, __C);
> }
>
> extern __inline __m512h
> @@ -402,7 +402,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_div_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> __m512h __D, const int __E)
> {
> - return __builtin_ia32_vdivph_v32hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_divph512_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m512h
> @@ -410,67 +410,67 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_div_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> const int __D)
> {
> - return __builtin_ia32_vdivph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_divph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A, __D);
> }
> #else
> #define _mm512_add_round_ph(A, B, C) \
> - ((__m512h)__builtin_ia32_vaddph_v32hf_mask_round((A), (B), \
> - _mm512_setzero_ph (),\
> - (__mmask32)-1, (C)))
> + ((__m512h)__builtin_ia32_addph512_mask_round((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, (C)))
>
> -#define _mm512_mask_add_round_ph(A, B, C, D, E) \
> - ((__m512h)__builtin_ia32_vaddph_v32hf_mask_round((C), (D), (A), (B), (E)))
> +#define _mm512_mask_add_round_ph(A, B, C, D, E) \
> + ((__m512h)__builtin_ia32_addph512_mask_round((C), (D), (A), (B), (E)))
>
> #define _mm512_maskz_add_round_ph(A, B, C, D) \
> - ((__m512h)__builtin_ia32_vaddph_v32hf_mask_round((B), (C), \
> - _mm512_setzero_ph (),\
> - (A), (D)))
> + ((__m512h)__builtin_ia32_addph512_mask_round((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), (D)))
>
> #define _mm512_sub_round_ph(A, B, C) \
> - ((__m512h)__builtin_ia32_vsubph_v32hf_mask_round((A), (B), \
> - _mm512_setzero_ph (),\
> - (__mmask32)-1, (C)))
> + ((__m512h)__builtin_ia32_subph512_mask_round((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, (C)))
>
> -#define _mm512_mask_sub_round_ph(A, B, C, D, E) \
> - ((__m512h)__builtin_ia32_vsubph_v32hf_mask_round((C), (D), (A), (B), (E)))
> +#define _mm512_mask_sub_round_ph(A, B, C, D, E) \
> + ((__m512h)__builtin_ia32_subph512_mask_round((C), (D), (A), (B), (E)))
>
> #define _mm512_maskz_sub_round_ph(A, B, C, D) \
> - ((__m512h)__builtin_ia32_vsubph_v32hf_mask_round((B), (C), \
> - _mm512_setzero_ph (),\
> - (A), (D)))
> + ((__m512h)__builtin_ia32_subph512_mask_round((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), (D)))
>
> #define _mm512_mul_round_ph(A, B, C) \
> - ((__m512h)__builtin_ia32_vmulph_v32hf_mask_round((A), (B), \
> - _mm512_setzero_ph (),\
> - (__mmask32)-1, (C)))
> + ((__m512h)__builtin_ia32_mulph512_mask_round((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, (C)))
>
> -#define _mm512_mask_mul_round_ph(A, B, C, D, E) \
> - ((__m512h)__builtin_ia32_vmulph_v32hf_mask_round((C), (D), (A), (B), (E)))
> +#define _mm512_mask_mul_round_ph(A, B, C, D, E) \
> + ((__m512h)__builtin_ia32_mulph512_mask_round((C), (D), (A), (B), (E)))
>
> #define _mm512_maskz_mul_round_ph(A, B, C, D) \
> - ((__m512h)__builtin_ia32_vmulph_v32hf_mask_round((B), (C), \
> - _mm512_setzero_ph (),\
> - (A), (D)))
> + ((__m512h)__builtin_ia32_mulph512_mask_round((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), (D)))
>
> #define _mm512_div_round_ph(A, B, C) \
> - ((__m512h)__builtin_ia32_vdivph_v32hf_mask_round((A), (B), \
> - _mm512_setzero_ph (),\
> - (__mmask32)-1, (C)))
> + ((__m512h)__builtin_ia32_divph512_mask_round((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, (C)))
>
> -#define _mm512_mask_div_round_ph(A, B, C, D, E) \
> - ((__m512h)__builtin_ia32_vdivph_v32hf_mask_round((C), (D), (A), (B), (E)))
> +#define _mm512_mask_div_round_ph(A, B, C, D, E) \
> + ((__m512h)__builtin_ia32_divph512_mask_round((C), (D), (A), (B), (E)))
>
> #define _mm512_maskz_div_round_ph(A, B, C, D) \
> - ((__m512h)__builtin_ia32_vdivph_v32hf_mask_round((B), (C), \
> - _mm512_setzero_ph (),\
> - (A), (D)))
> + ((__m512h)__builtin_ia32_divph512_mask_round((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), (D)))
> #endif /* __OPTIMIZE__ */
>
> /* Intrinsics of v[add,sub,mul,div]sh. */
> extern __inline __m128h
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> + __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_add_sh (__m128h __A, __m128h __B)
> {
> __A[0] += __B[0];
> @@ -481,15 +481,15 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_add_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vaddsh_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_addsh_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_add_sh (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vaddsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_addsh_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> extern __inline __m128h
> @@ -504,15 +504,15 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_sub_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vsubsh_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_subsh_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_sub_sh (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vsubsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_subsh_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> extern __inline __m128h
> @@ -527,14 +527,14 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_mul_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vmulsh_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_mulsh_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_mul_sh (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vmulsh_v8hf_mask (__B, __C, _mm_setzero_ph (), __A);
> + return __builtin_ia32_mulsh_mask (__B, __C, _mm_setzero_ph (), __A);
> }
>
> extern __inline __m128h
> @@ -549,15 +549,15 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_div_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vdivsh_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_divsh_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_div_sh (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vdivsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_divsh_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> #ifdef __OPTIMIZE__
> @@ -565,9 +565,9 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_add_round_sh (__m128h __A, __m128h __B, const int __C)
> {
> - return __builtin_ia32_vaddsh_v8hf_mask_round (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1, __C);
> + return __builtin_ia32_addsh_mask_round (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1, __C);
> }
>
> extern __inline __m128h
> @@ -575,7 +575,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_add_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, const int __E)
> {
> - return __builtin_ia32_vaddsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_addsh_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m128h
> @@ -583,18 +583,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_add_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D)
> {
> - return __builtin_ia32_vaddsh_v8hf_mask_round (__B, __C,
> - _mm_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_addsh_mask_round (__B, __C,
> + _mm_setzero_ph (),
> + __A, __D);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_sub_round_sh (__m128h __A, __m128h __B, const int __C)
> {
> - return __builtin_ia32_vsubsh_v8hf_mask_round (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1, __C);
> + return __builtin_ia32_subsh_mask_round (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1, __C);
> }
>
> extern __inline __m128h
> @@ -602,7 +602,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_sub_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, const int __E)
> {
> - return __builtin_ia32_vsubsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_subsh_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m128h
> @@ -610,18 +610,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_sub_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D)
> {
> - return __builtin_ia32_vsubsh_v8hf_mask_round (__B, __C,
> - _mm_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_subsh_mask_round (__B, __C,
> + _mm_setzero_ph (),
> + __A, __D);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mul_round_sh (__m128h __A, __m128h __B, const int __C)
> {
> - return __builtin_ia32_vmulsh_v8hf_mask_round (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1, __C);
> + return __builtin_ia32_mulsh_mask_round (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1, __C);
> }
>
> extern __inline __m128h
> @@ -629,7 +629,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_mul_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, const int __E)
> {
> - return __builtin_ia32_vmulsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_mulsh_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m128h
> @@ -637,18 +637,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_mul_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D)
> {
> - return __builtin_ia32_vmulsh_v8hf_mask_round (__B, __C,
> - _mm_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_mulsh_mask_round (__B, __C,
> + _mm_setzero_ph (),
> + __A, __D);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_div_round_sh (__m128h __A, __m128h __B, const int __C)
> {
> - return __builtin_ia32_vdivsh_v8hf_mask_round (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1, __C);
> + return __builtin_ia32_divsh_mask_round (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1, __C);
> }
>
> extern __inline __m128h
> @@ -656,7 +656,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_div_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, const int __E)
> {
> - return __builtin_ia32_vdivsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_divsh_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m128h
> @@ -664,62 +664,62 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_div_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D)
> {
> - return __builtin_ia32_vdivsh_v8hf_mask_round (__B, __C,
> - _mm_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_divsh_mask_round (__B, __C,
> + _mm_setzero_ph (),
> + __A, __D);
> }
> #else
> #define _mm_add_round_sh(A, B, C) \
> - ((__m128h)__builtin_ia32_vaddsh_v8hf_mask_round ((A), (B), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, (C)))
> + ((__m128h)__builtin_ia32_addsh_mask_round ((A), (B), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, (C)))
>
> #define _mm_mask_add_round_sh(A, B, C, D, E) \
> - ((__m128h)__builtin_ia32_vaddsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> + ((__m128h)__builtin_ia32_addsh_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm_maskz_add_round_sh(A, B, C, D) \
> - ((__m128h)__builtin_ia32_vaddsh_v8hf_mask_round ((B), (C), \
> - _mm_setzero_ph (), \
> - (A), (D)))
> +#define _mm_maskz_add_round_sh(A, B, C, D) \
> + ((__m128h)__builtin_ia32_addsh_mask_round ((B), (C), \
> + _mm_setzero_ph (), \
> + (A), (D)))
>
> #define _mm_sub_round_sh(A, B, C) \
> - ((__m128h)__builtin_ia32_vsubsh_v8hf_mask_round ((A), (B), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, (C)))
> + ((__m128h)__builtin_ia32_subsh_mask_round ((A), (B), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, (C)))
>
> #define _mm_mask_sub_round_sh(A, B, C, D, E) \
> - ((__m128h)__builtin_ia32_vsubsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> + ((__m128h)__builtin_ia32_subsh_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm_maskz_sub_round_sh(A, B, C, D) \
> - ((__m128h)__builtin_ia32_vsubsh_v8hf_mask_round ((B), (C), \
> - _mm_setzero_ph (), \
> - (A), (D)))
> +#define _mm_maskz_sub_round_sh(A, B, C, D) \
> + ((__m128h)__builtin_ia32_subsh_mask_round ((B), (C), \
> + _mm_setzero_ph (), \
> + (A), (D)))
>
> #define _mm_mul_round_sh(A, B, C) \
> - ((__m128h)__builtin_ia32_vmulsh_v8hf_mask_round ((A), (B), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, (C)))
> + ((__m128h)__builtin_ia32_mulsh_mask_round ((A), (B), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, (C)))
>
> #define _mm_mask_mul_round_sh(A, B, C, D, E) \
> - ((__m128h)__builtin_ia32_vmulsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> + ((__m128h)__builtin_ia32_mulsh_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm_maskz_mul_round_sh(A, B, C, D) \
> - ((__m128h)__builtin_ia32_vmulsh_v8hf_mask_round ((B), (C), \
> - _mm_setzero_ph (), \
> - (A), (D)))
> +#define _mm_maskz_mul_round_sh(A, B, C, D) \
> + ((__m128h)__builtin_ia32_mulsh_mask_round ((B), (C), \
> + _mm_setzero_ph (), \
> + (A), (D)))
>
> #define _mm_div_round_sh(A, B, C) \
> - ((__m128h)__builtin_ia32_vdivsh_v8hf_mask_round ((A), (B), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, (C)))
> + ((__m128h)__builtin_ia32_divsh_mask_round ((A), (B), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, (C)))
>
> #define _mm_mask_div_round_sh(A, B, C, D, E) \
> - ((__m128h)__builtin_ia32_vdivsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> + ((__m128h)__builtin_ia32_divsh_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm_maskz_div_round_sh(A, B, C, D) \
> - ((__m128h)__builtin_ia32_vdivsh_v8hf_mask_round ((B), (C), \
> - _mm_setzero_ph (), \
> - (A), (D)))
> +#define _mm_maskz_div_round_sh(A, B, C, D) \
> + ((__m128h)__builtin_ia32_divsh_mask_round ((B), (C), \
> + _mm_setzero_ph (), \
> + (A), (D)))
> #endif /* __OPTIMIZE__ */
>
> /* Intrinsic vmaxph vminph. */
> @@ -727,48 +727,48 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_max_ph (__m512h __A, __m512h __B)
> {
> - return __builtin_ia32_vmaxph_v32hf_mask (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1);
> + return __builtin_ia32_maxph512_mask (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_max_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> {
> - return __builtin_ia32_vmaxph_v32hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_maxph512_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_max_ph (__mmask32 __A, __m512h __B, __m512h __C)
> {
> - return __builtin_ia32_vmaxph_v32hf_mask (__B, __C,
> - _mm512_setzero_ph (), __A);
> + return __builtin_ia32_maxph512_mask (__B, __C,
> + _mm512_setzero_ph (), __A);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_min_ph (__m512h __A, __m512h __B)
> {
> - return __builtin_ia32_vminph_v32hf_mask (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1);
> + return __builtin_ia32_minph512_mask (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_min_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> {
> - return __builtin_ia32_vminph_v32hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_minph512_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_min_ph (__mmask32 __A, __m512h __B, __m512h __C)
> {
> - return __builtin_ia32_vminph_v32hf_mask (__B, __C,
> - _mm512_setzero_ph (), __A);
> + return __builtin_ia32_minph512_mask (__B, __C,
> + _mm512_setzero_ph (), __A);
> }
>
> #ifdef __OPTIMIZE__
> @@ -776,9 +776,9 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_max_round_ph (__m512h __A, __m512h __B, const int __C)
> {
> - return __builtin_ia32_vmaxph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1, __C);
> + return __builtin_ia32_maxph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1, __C);
> }
>
> extern __inline __m512h
> @@ -786,7 +786,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_max_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> __m512h __D, const int __E)
> {
> - return __builtin_ia32_vmaxph_v32hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_maxph512_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m512h
> @@ -794,18 +794,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_max_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> const int __D)
> {
> - return __builtin_ia32_vmaxph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_maxph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A, __D);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_min_round_ph (__m512h __A, __m512h __B, const int __C)
> {
> - return __builtin_ia32_vminph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1, __C);
> + return __builtin_ia32_minph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1, __C);
> }
>
> extern __inline __m512h
> @@ -813,7 +813,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_min_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> __m512h __D, const int __E)
> {
> - return __builtin_ia32_vminph_v32hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_minph512_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m512h
> @@ -821,37 +821,37 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_min_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> const int __D)
> {
> - return __builtin_ia32_vminph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_minph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A, __D);
> }
>
> #else
> -#define _mm512_max_round_ph(A, B, C) \
> - (__builtin_ia32_vmaxph_v32hf_mask_round ((A), (B), \
> - _mm512_setzero_ph (), \
> - (__mmask32)-1, (C)))
> +#define _mm512_max_round_ph(A, B, C) \
> + (__builtin_ia32_maxph512_mask_round ((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, (C)))
>
> #define _mm512_mask_max_round_ph(A, B, C, D, E) \
> - (__builtin_ia32_vmaxph_v32hf_mask_round ((C), (D), (A), (B), (E)))
> + (__builtin_ia32_maxph512_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm512_maskz_max_round_ph(A, B, C, D) \
> - (__builtin_ia32_vmaxph_v32hf_mask_round ((B), (C), \
> - _mm512_setzero_ph (), \
> - (A), (D)))
> +#define _mm512_maskz_max_round_ph(A, B, C, D) \
> + (__builtin_ia32_maxph512_mask_round ((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), (D)))
>
> -#define _mm512_min_round_ph(A, B, C) \
> - (__builtin_ia32_vminph_v32hf_mask_round ((A), (B), \
> - _mm512_setzero_ph (), \
> - (__mmask32)-1, (C)))
> +#define _mm512_min_round_ph(A, B, C) \
> + (__builtin_ia32_minph512_mask_round ((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, (C)))
>
> #define _mm512_mask_min_round_ph(A, B, C, D, E) \
> - (__builtin_ia32_vminph_v32hf_mask_round ((C), (D), (A), (B), (E)))
> + (__builtin_ia32_minph512_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm512_maskz_min_round_ph(A, B, C, D) \
> - (__builtin_ia32_vminph_v32hf_mask_round ((B), (C), \
> - _mm512_setzero_ph (), \
> - (A), (D)))
> +#define _mm512_maskz_min_round_ph(A, B, C, D) \
> + (__builtin_ia32_minph512_mask_round ((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), (D)))
> #endif /* __OPTIMIZE__ */
>
> /* Intrinsic vmaxsh vminsh. */
> @@ -867,15 +867,15 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_max_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vmaxsh_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_maxsh_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_max_sh (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vmaxsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_maxsh_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> extern __inline __m128h
> @@ -890,15 +890,15 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_min_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vminsh_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_minsh_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_min_sh (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vminsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_minsh_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> #ifdef __OPTIMIZE__
> @@ -906,9 +906,9 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_max_round_sh (__m128h __A, __m128h __B, const int __C)
> {
> - return __builtin_ia32_vmaxsh_v8hf_mask_round (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1, __C);
> + return __builtin_ia32_maxsh_mask_round (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1, __C);
> }
>
> extern __inline __m128h
> @@ -916,7 +916,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_max_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, const int __E)
> {
> - return __builtin_ia32_vmaxsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_maxsh_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m128h
> @@ -924,18 +924,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_max_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D)
> {
> - return __builtin_ia32_vmaxsh_v8hf_mask_round (__B, __C,
> - _mm_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_maxsh_mask_round (__B, __C,
> + _mm_setzero_ph (),
> + __A, __D);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_min_round_sh (__m128h __A, __m128h __B, const int __C)
> {
> - return __builtin_ia32_vminsh_v8hf_mask_round (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1, __C);
> + return __builtin_ia32_minsh_mask_round (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1, __C);
> }
>
> extern __inline __m128h
> @@ -943,7 +943,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_min_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, const int __E)
> {
> - return __builtin_ia32_vminsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> + return __builtin_ia32_minsh_mask_round (__C, __D, __A, __B, __E);
> }
>
> extern __inline __m128h
> @@ -951,37 +951,37 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_min_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D)
> {
> - return __builtin_ia32_vminsh_v8hf_mask_round (__B, __C,
> - _mm_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_minsh_mask_round (__B, __C,
> + _mm_setzero_ph (),
> + __A, __D);
> }
>
> #else
> -#define _mm_max_round_sh(A, B, C) \
> - (__builtin_ia32_vmaxsh_v8hf_mask_round ((A), (B), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, (C)))
> +#define _mm_max_round_sh(A, B, C) \
> + (__builtin_ia32_maxsh_mask_round ((A), (B), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, (C)))
>
> -#define _mm_mask_max_round_sh(A, B, C, D, E) \
> - (__builtin_ia32_vmaxsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> +#define _mm_mask_max_round_sh(A, B, C, D, E) \
> + (__builtin_ia32_maxsh_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm_maskz_max_round_sh(A, B, C, D) \
> - (__builtin_ia32_vmaxsh_v8hf_mask_round ((B), (C), \
> - _mm_setzero_ph (), \
> - (A), (D)))
> +#define _mm_maskz_max_round_sh(A, B, C, D) \
> + (__builtin_ia32_maxsh_mask_round ((B), (C), \
> + _mm_setzero_ph (), \
> + (A), (D)))
>
> -#define _mm_min_round_sh(A, B, C) \
> - (__builtin_ia32_vminsh_v8hf_mask_round ((A), (B), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, (C)))
> +#define _mm_min_round_sh(A, B, C) \
> + (__builtin_ia32_minsh_mask_round ((A), (B), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, (C)))
>
> -#define _mm_mask_min_round_sh(A, B, C, D, E) \
> - (__builtin_ia32_vminsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> +#define _mm_mask_min_round_sh(A, B, C, D, E) \
> + (__builtin_ia32_minsh_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm_maskz_min_round_sh(A, B, C, D) \
> - (__builtin_ia32_vminsh_v8hf_mask_round ((B), (C), \
> - _mm_setzero_ph (), \
> - (A), (D)))
> +#define _mm_maskz_min_round_sh(A, B, C, D) \
> + (__builtin_ia32_minsh_mask_round ((B), (C), \
> + _mm_setzero_ph (), \
> + (A), (D)))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -991,8 +991,8 @@ extern __inline __mmask32
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_cmp_ph_mask (__m512h __A, __m512h __B, const int __C)
> {
> - return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask (__A, __B, __C,
> - (__mmask32) -1);
> + return (__mmask32) __builtin_ia32_cmpph512_mask (__A, __B, __C,
> + (__mmask32) -1);
> }
>
> extern __inline __mmask32
> @@ -1000,8 +1000,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_cmp_ph_mask (__mmask32 __A, __m512h __B, __m512h __C,
> const int __D)
> {
> - return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask (__B, __C, __D,
> - __A);
> + return (__mmask32) __builtin_ia32_cmpph512_mask (__B, __C, __D,
> + __A);
> }
>
> extern __inline __mmask32
> @@ -1009,9 +1009,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_cmp_round_ph_mask (__m512h __A, __m512h __B, const int __C,
> const int __D)
> {
> - return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask_round (__A, __B,
> - __C, (__mmask32) -1,
> - __D);
> + return (__mmask32) __builtin_ia32_cmpph512_mask_round (__A, __B,
> + __C, (__mmask32) -1,
> + __D);
> }
>
> extern __inline __mmask32
> @@ -1019,23 +1019,23 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_cmp_round_ph_mask (__mmask32 __A, __m512h __B, __m512h __C,
> const int __D, const int __E)
> {
> - return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask_round (__B, __C,
> - __D, __A,
> - __E);
> + return (__mmask32) __builtin_ia32_cmpph512_mask_round (__B, __C,
> + __D, __A,
> + __E);
> }
>
> #else
> #define _mm512_cmp_ph_mask(A, B, C) \
> - (__builtin_ia32_vcmpph_v32hf_mask ((A), (B), (C), (-1)))
> + (__builtin_ia32_cmpph512_mask ((A), (B), (C), (-1)))
>
> #define _mm512_mask_cmp_ph_mask(A, B, C, D) \
> - (__builtin_ia32_vcmpph_v32hf_mask ((B), (C), (D), (A)))
> + (__builtin_ia32_cmpph512_mask ((B), (C), (D), (A)))
>
> -#define _mm512_cmp_round_ph_mask(A, B, C, D) \
> - (__builtin_ia32_vcmpph_v32hf_mask_round ((A), (B), (C), (-1), (D)))
> +#define _mm512_cmp_round_ph_mask(A, B, C, D) \
> + (__builtin_ia32_cmpph512_mask_round ((A), (B), (C), (-1), (D)))
>
> -#define _mm512_mask_cmp_round_ph_mask(A, B, C, D, E) \
> - (__builtin_ia32_vcmpph_v32hf_mask_round ((B), (C), (D), (A), (E)))
> +#define _mm512_mask_cmp_round_ph_mask(A, B, C, D, E) \
> + (__builtin_ia32_cmpph512_mask_round ((B), (C), (D), (A), (E)))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -1046,9 +1046,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_cmp_sh_mask (__m128h __A, __m128h __B, const int __C)
> {
> return (__mmask8)
> - __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B,
> - __C, (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + __builtin_ia32_cmpsh_mask_round (__A, __B,
> + __C, (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __mmask8
> @@ -1057,9 +1057,9 @@ _mm_mask_cmp_sh_mask (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D)
> {
> return (__mmask8)
> - __builtin_ia32_vcmpsh_v8hf_mask_round (__B, __C,
> - __D, __A,
> - _MM_FROUND_CUR_DIRECTION);
> + __builtin_ia32_cmpsh_mask_round (__B, __C,
> + __D, __A,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __mmask8
> @@ -1067,9 +1067,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_cmp_round_sh_mask (__m128h __A, __m128h __B, const int __C,
> const int __D)
> {
> - return (__mmask8) __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B,
> - __C, (__mmask8) -1,
> - __D);
> + return (__mmask8) __builtin_ia32_cmpsh_mask_round (__A, __B,
> + __C, (__mmask8) -1,
> + __D);
> }
>
> extern __inline __mmask8
> @@ -1077,25 +1077,25 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_cmp_round_sh_mask (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D, const int __E)
> {
> - return (__mmask8) __builtin_ia32_vcmpsh_v8hf_mask_round (__B, __C,
> - __D, __A,
> - __E);
> + return (__mmask8) __builtin_ia32_cmpsh_mask_round (__B, __C,
> + __D, __A,
> + __E);
> }
>
> #else
> -#define _mm_cmp_sh_mask(A, B, C) \
> - (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (C), (-1), \
> - (_MM_FROUND_CUR_DIRECTION)))
> +#define _mm_cmp_sh_mask(A, B, C) \
> + (__builtin_ia32_cmpsh_mask_round ((A), (B), (C), (-1), \
> + (_MM_FROUND_CUR_DIRECTION)))
>
> -#define _mm_mask_cmp_sh_mask(A, B, C, D) \
> - (__builtin_ia32_vcmpsh_v8hf_mask_round ((B), (C), (D), (A), \
> - (_MM_FROUND_CUR_DIRECTION)))
> +#define _mm_mask_cmp_sh_mask(A, B, C, D) \
> + (__builtin_ia32_cmpsh_mask_round ((B), (C), (D), (A), \
> + (_MM_FROUND_CUR_DIRECTION)))
>
> -#define _mm_cmp_round_sh_mask(A, B, C, D) \
> - (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (C), (-1), (D)))
> +#define _mm_cmp_round_sh_mask(A, B, C, D) \
> + (__builtin_ia32_cmpsh_mask_round ((A), (B), (C), (-1), (D)))
>
> -#define _mm_mask_cmp_round_sh_mask(A, B, C, D, E) \
> - (__builtin_ia32_vcmpsh_v8hf_mask_round ((B), (C), (D), (A), (E)))
> +#define _mm_mask_cmp_round_sh_mask(A, B, C, D, E) \
> + (__builtin_ia32_cmpsh_mask_round ((B), (C), (D), (A), (E)))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -1104,134 +1104,134 @@ extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_comieq_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_EQ_OS,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_EQ_OS,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_comilt_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LT_OS,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LT_OS,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_comile_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LE_OS,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LE_OS,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_comigt_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GT_OS,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GT_OS,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_comige_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GE_OS,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GE_OS,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_comineq_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_NEQ_US,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_NEQ_US,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_ucomieq_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_EQ_OQ,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_EQ_OQ,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_ucomilt_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LT_OQ,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LT_OQ,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_ucomile_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LE_OQ,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LE_OQ,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_ucomigt_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GT_OQ,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GT_OQ,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_ucomige_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GE_OQ,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GE_OQ,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_ucomineq_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_NEQ_UQ,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_NEQ_UQ,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> #ifdef __OPTIMIZE__
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> - _mm_comi_sh (__m128h __A, __m128h __B, const int __P)
> +_mm_comi_sh (__m128h __A, __m128h __B, const int __P)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, __P,
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, __P,
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline int
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_comi_round_sh (__m128h __A, __m128h __B, const int __P, const int __R)
> {
> - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, __P,
> - (__mmask8) -1,__R);
> + return __builtin_ia32_cmpsh_mask_round (__A, __B, __P,
> + (__mmask8) -1,__R);
> }
>
> #else
> -#define _mm_comi_round_sh(A, B, P, R) \
> - (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (P), (__mmask8) (-1), (R)))
> -#define _mm_comi_sh(A, B, P) \
> - (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (P), (__mmask8) (-1), \
> - _MM_FROUND_CUR_DIRECTION))
> +#define _mm_comi_round_sh(A, B, P, R) \
> + (__builtin_ia32_cmpsh_mask_round ((A), (B), (P), (__mmask8) (-1), (R)))
> +#define _mm_comi_sh(A, B, P) \
> + (__builtin_ia32_cmpsh_mask_round ((A), (B), (P), (__mmask8) (-1), \
> + _MM_FROUND_CUR_DIRECTION))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -1240,28 +1240,28 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_sqrt_ph (__m512h __A)
> {
> - return __builtin_ia32_vsqrtph_v32hf_mask_round (__A,
> - _mm512_setzero_ph(),
> - (__mmask32) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_sqrtph512_mask_round (__A,
> + _mm512_setzero_ph(),
> + (__mmask32) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_sqrt_ph (__m512h __A, __mmask32 __B, __m512h __C)
> {
> - return __builtin_ia32_vsqrtph_v32hf_mask_round (__C, __A, __B,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_sqrtph512_mask_round (__C, __A, __B,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_sqrt_ph (__mmask32 __A, __m512h __B)
> {
> - return __builtin_ia32_vsqrtph_v32hf_mask_round (__B,
> - _mm512_setzero_ph (),
> - __A,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_sqrtph512_mask_round (__B,
> + _mm512_setzero_ph (),
> + __A,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> #ifdef __OPTIMIZE__
> @@ -1269,9 +1269,9 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_sqrt_round_ph (__m512h __A, const int __B)
> {
> - return __builtin_ia32_vsqrtph_v32hf_mask_round (__A,
> - _mm512_setzero_ph(),
> - (__mmask32) -1, __B);
> + return __builtin_ia32_sqrtph512_mask_round (__A,
> + _mm512_setzero_ph(),
> + (__mmask32) -1, __B);
> }
>
> extern __inline __m512h
> @@ -1279,31 +1279,31 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_sqrt_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> const int __D)
> {
> - return __builtin_ia32_vsqrtph_v32hf_mask_round (__C, __A, __B, __D);
> + return __builtin_ia32_sqrtph512_mask_round (__C, __A, __B, __D);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_sqrt_round_ph (__mmask32 __A, __m512h __B, const int __C)
> {
> - return __builtin_ia32_vsqrtph_v32hf_mask_round (__B,
> - _mm512_setzero_ph (),
> - __A, __C);
> + return __builtin_ia32_sqrtph512_mask_round (__B,
> + _mm512_setzero_ph (),
> + __A, __C);
> }
>
> #else
> -#define _mm512_sqrt_round_ph(A, B) \
> - (__builtin_ia32_vsqrtph_v32hf_mask_round ((A), \
> - _mm512_setzero_ph (), \
> - (__mmask32)-1, (B)))
> +#define _mm512_sqrt_round_ph(A, B) \
> + (__builtin_ia32_sqrtph512_mask_round ((A), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, (B)))
>
> -#define _mm512_mask_sqrt_round_ph(A, B, C, D) \
> - (__builtin_ia32_vsqrtph_v32hf_mask_round ((C), (A), (B), (D)))
> +#define _mm512_mask_sqrt_round_ph(A, B, C, D) \
> + (__builtin_ia32_sqrtph512_mask_round ((C), (A), (B), (D)))
>
> -#define _mm512_maskz_sqrt_round_ph(A, B, C) \
> - (__builtin_ia32_vsqrtph_v32hf_mask_round ((B), \
> - _mm512_setzero_ph (), \
> - (A), (C)))
> +#define _mm512_maskz_sqrt_round_ph(A, B, C) \
> + (__builtin_ia32_sqrtph512_mask_round ((B), \
> + _mm512_setzero_ph (), \
> + (A), (C)))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -1312,23 +1312,23 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_rsqrt_ph (__m512h __A)
> {
> - return __builtin_ia32_vrsqrtph_v32hf_mask (__A, _mm512_setzero_ph (),
> - (__mmask32) -1);
> + return __builtin_ia32_rsqrtph512_mask (__A, _mm512_setzero_ph (),
> + (__mmask32) -1);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_rsqrt_ph (__m512h __A, __mmask32 __B, __m512h __C)
> {
> - return __builtin_ia32_vrsqrtph_v32hf_mask (__C, __A, __B);
> + return __builtin_ia32_rsqrtph512_mask (__C, __A, __B);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_rsqrt_ph (__mmask32 __A, __m512h __B)
> {
> - return __builtin_ia32_vrsqrtph_v32hf_mask (__B, _mm512_setzero_ph (),
> - __A);
> + return __builtin_ia32_rsqrtph512_mask (__B, _mm512_setzero_ph (),
> + __A);
> }
>
> /* Intrinsics vrsqrtsh. */
> @@ -1336,23 +1336,23 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_rsqrt_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vrsqrtsh_v8hf_mask (__B, __A, _mm_setzero_ph (),
> - (__mmask8) -1);
> + return __builtin_ia32_rsqrtsh_mask (__B, __A, _mm_setzero_ph (),
> + (__mmask8) -1);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_rsqrt_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vrsqrtsh_v8hf_mask (__D, __C, __A, __B);
> + return __builtin_ia32_rsqrtsh_mask (__D, __C, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_rsqrt_sh (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vrsqrtsh_v8hf_mask (__C, __B, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_rsqrtsh_mask (__C, __B, _mm_setzero_ph (),
> + __A);
> }
>
> /* Intrinsics vsqrtsh. */
> @@ -1360,27 +1360,27 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_sqrt_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__B, __A,
> - _mm_setzero_ph (),
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_sqrtsh_mask_round (__B, __A,
> + _mm_setzero_ph (),
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_sqrt_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__D, __C, __A, __B,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_sqrtsh_mask_round (__D, __C, __A, __B,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_sqrt_sh (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__C, __B,
> - _mm_setzero_ph (),
> - __A, _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_sqrtsh_mask_round (__C, __B,
> + _mm_setzero_ph (),
> + __A, _MM_FROUND_CUR_DIRECTION);
> }
>
> #ifdef __OPTIMIZE__
> @@ -1388,9 +1388,9 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_sqrt_round_sh (__m128h __A, __m128h __B, const int __C)
> {
> - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__B, __A,
> - _mm_setzero_ph (),
> - (__mmask8) -1, __C);
> + return __builtin_ia32_sqrtsh_mask_round (__B, __A,
> + _mm_setzero_ph (),
> + (__mmask8) -1, __C);
> }
>
> extern __inline __m128h
> @@ -1398,8 +1398,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_sqrt_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, const int __E)
> {
> - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__D, __C, __A, __B,
> - __E);
> + return __builtin_ia32_sqrtsh_mask_round (__D, __C, __A, __B,
> + __E);
> }
>
> extern __inline __m128h
> @@ -1407,24 +1407,24 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_sqrt_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D)
> {
> - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__C, __B,
> - _mm_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_sqrtsh_mask_round (__C, __B,
> + _mm_setzero_ph (),
> + __A, __D);
> }
>
> #else
> #define _mm_sqrt_round_sh(A, B, C) \
> - (__builtin_ia32_vsqrtsh_v8hf_mask_round ((B), (A), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, (C)))
> + (__builtin_ia32_sqrtsh_mask_round ((B), (A), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, (C)))
>
> #define _mm_mask_sqrt_round_sh(A, B, C, D, E) \
> - (__builtin_ia32_vsqrtsh_v8hf_mask_round ((D), (C), (A), (B), (E)))
> + (__builtin_ia32_sqrtsh_mask_round ((D), (C), (A), (B), (E)))
>
> -#define _mm_maskz_sqrt_round_sh(A, B, C, D) \
> - (__builtin_ia32_vsqrtsh_v8hf_mask_round ((C), (B), \
> - _mm_setzero_ph (), \
> - (A), (D)))
> +#define _mm_maskz_sqrt_round_sh(A, B, C, D) \
> + (__builtin_ia32_sqrtsh_mask_round ((C), (B), \
> + _mm_setzero_ph (), \
> + (A), (D)))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -1433,23 +1433,23 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_rcp_ph (__m512h __A)
> {
> - return __builtin_ia32_vrcpph_v32hf_mask (__A, _mm512_setzero_ph (),
> - (__mmask32) -1);
> + return __builtin_ia32_rcpph512_mask (__A, _mm512_setzero_ph (),
> + (__mmask32) -1);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_rcp_ph (__m512h __A, __mmask32 __B, __m512h __C)
> {
> - return __builtin_ia32_vrcpph_v32hf_mask (__C, __A, __B);
> + return __builtin_ia32_rcpph512_mask (__C, __A, __B);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_rcp_ph (__mmask32 __A, __m512h __B)
> {
> - return __builtin_ia32_vrcpph_v32hf_mask (__B, _mm512_setzero_ph (),
> - __A);
> + return __builtin_ia32_rcpph512_mask (__B, _mm512_setzero_ph (),
> + __A);
> }
>
> /* Intrinsics vrcpsh. */
> @@ -1457,23 +1457,23 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_rcp_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vrcpsh_v8hf_mask (__B, __A, _mm_setzero_ph (),
> - (__mmask8) -1);
> + return __builtin_ia32_rcpsh_mask (__B, __A, _mm_setzero_ph (),
> + (__mmask8) -1);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_rcp_sh (__m128h __A, __mmask32 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vrcpsh_v8hf_mask (__D, __C, __A, __B);
> + return __builtin_ia32_rcpsh_mask (__D, __C, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_rcp_sh (__mmask32 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vrcpsh_v8hf_mask (__C, __B, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_rcpsh_mask (__C, __B, _mm_setzero_ph (),
> + __A);
> }
>
> /* Intrinsics vscalefph. */
> @@ -1481,28 +1481,28 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_scalef_ph (__m512h __A, __m512h __B)
> {
> - return __builtin_ia32_vscalefph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_scalefph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_scalef_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> {
> - return __builtin_ia32_vscalefph_v32hf_mask_round (__C, __D, __A, __B,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_scalefph512_mask_round (__C, __D, __A, __B,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_scalef_ph (__mmask32 __A, __m512h __B, __m512h __C)
> {
> - return __builtin_ia32_vscalefph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_scalefph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> #ifdef __OPTIMIZE__
> @@ -1510,9 +1510,9 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_scalef_round_ph (__m512h __A, __m512h __B, const int __C)
> {
> - return __builtin_ia32_vscalefph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1, __C);
> + return __builtin_ia32_scalefph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1, __C);
> }
>
> extern __inline __m512h
> @@ -1520,8 +1520,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_scalef_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> __m512h __D, const int __E)
> {
> - return __builtin_ia32_vscalefph_v32hf_mask_round (__C, __D, __A, __B,
> - __E);
> + return __builtin_ia32_scalefph512_mask_round (__C, __D, __A, __B,
> + __E);
> }
>
> extern __inline __m512h
> @@ -1529,24 +1529,24 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_scalef_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> const int __D)
> {
> - return __builtin_ia32_vscalefph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_scalefph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A, __D);
> }
>
> #else
> -#define _mm512_scalef_round_ph(A, B, C) \
> - (__builtin_ia32_vscalefph_v32hf_mask_round ((A), (B), \
> - _mm512_setzero_ph (), \
> - (__mmask32)-1, (C)))
> +#define _mm512_scalef_round_ph(A, B, C) \
> + (__builtin_ia32_scalefph512_mask_round ((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, (C)))
>
> #define _mm512_mask_scalef_round_ph(A, B, C, D, E) \
> - (__builtin_ia32_vscalefph_v32hf_mask_round ((C), (D), (A), (B), (E)))
> + (__builtin_ia32_scalefph512_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm512_maskz_scalef_round_ph(A, B, C, D) \
> - (__builtin_ia32_vscalefph_v32hf_mask_round ((B), (C), \
> - _mm512_setzero_ph (), \
> - (A), (D)))
> +#define _mm512_maskz_scalef_round_ph(A, B, C, D) \
> + (__builtin_ia32_scalefph512_mask_round ((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), (D)))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -1555,28 +1555,28 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_scalef_sh (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vscalefsh_v8hf_mask_round (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_scalefsh_mask_round (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_scalef_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vscalefsh_v8hf_mask_round (__C, __D, __A, __B,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_scalefsh_mask_round (__C, __D, __A, __B,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_scalef_sh (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vscalefsh_v8hf_mask_round (__B, __C,
> - _mm_setzero_ph (),
> - __A,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_scalefsh_mask_round (__B, __C,
> + _mm_setzero_ph (),
> + __A,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> #ifdef __OPTIMIZE__
> @@ -1584,9 +1584,9 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_scalef_round_sh (__m128h __A, __m128h __B, const int __C)
> {
> - return __builtin_ia32_vscalefsh_v8hf_mask_round (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1, __C);
> + return __builtin_ia32_scalefsh_mask_round (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1, __C);
> }
>
> extern __inline __m128h
> @@ -1594,8 +1594,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_scalef_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, const int __E)
> {
> - return __builtin_ia32_vscalefsh_v8hf_mask_round (__C, __D, __A, __B,
> - __E);
> + return __builtin_ia32_scalefsh_mask_round (__C, __D, __A, __B,
> + __E);
> }
>
> extern __inline __m128h
> @@ -1603,23 +1603,23 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_scalef_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D)
> {
> - return __builtin_ia32_vscalefsh_v8hf_mask_round (__B, __C,
> - _mm_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_scalefsh_mask_round (__B, __C,
> + _mm_setzero_ph (),
> + __A, __D);
> }
>
> #else
> -#define _mm_scalef_round_sh(A, B, C) \
> - (__builtin_ia32_vscalefsh_v8hf_mask_round ((A), (B), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, (C)))
> +#define _mm_scalef_round_sh(A, B, C) \
> + (__builtin_ia32_scalefsh_mask_round ((A), (B), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, (C)))
>
> -#define _mm_mask_scalef_round_sh(A, B, C, D, E) \
> - (__builtin_ia32_vscalefsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> +#define _mm_mask_scalef_round_sh(A, B, C, D, E) \
> + (__builtin_ia32_scalefsh_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm_maskz_scalef_round_sh(A, B, C, D) \
> - (__builtin_ia32_vscalefsh_v8hf_mask_round ((B), (C), _mm_setzero_ph (), \
> - (A), (D)))
> +#define _mm_maskz_scalef_round_sh(A, B, C, D) \
> + (__builtin_ia32_scalefsh_mask_round ((B), (C), _mm_setzero_ph (), \
> + (A), (D)))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -1629,37 +1629,37 @@ extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_reduce_ph (__m512h __A, int __B)
> {
> - return __builtin_ia32_vreduceph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_reduceph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_reduce_ph (__m512h __A, __mmask32 __B, __m512h __C, int __D)
> {
> - return __builtin_ia32_vreduceph_v32hf_mask_round (__C, __D, __A, __B,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_reduceph512_mask_round (__C, __D, __A, __B,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_reduce_ph (__mmask32 __A, __m512h __B, int __C)
> {
> - return __builtin_ia32_vreduceph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_reduceph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_reduce_round_ph (__m512h __A, int __B, const int __C)
> {
> - return __builtin_ia32_vreduceph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1, __C);
> + return __builtin_ia32_reduceph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1, __C);
> }
>
> extern __inline __m512h
> @@ -1667,8 +1667,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_reduce_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> int __D, const int __E)
> {
> - return __builtin_ia32_vreduceph_v32hf_mask_round (__C, __D, __A, __B,
> - __E);
> + return __builtin_ia32_reduceph512_mask_round (__C, __D, __A, __B,
> + __E);
> }
>
> extern __inline __m512h
> @@ -1676,39 +1676,39 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_reduce_round_ph (__mmask32 __A, __m512h __B, int __C,
> const int __D)
> {
> - return __builtin_ia32_vreduceph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_reduceph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A, __D);
> }
>
> #else
> #define _mm512_reduce_ph(A, B) \
> - (__builtin_ia32_vreduceph_v32hf_mask_round ((A), (B), \
> - _mm512_setzero_ph (), \
> - (__mmask32)-1, \
> - _MM_FROUND_CUR_DIRECTION))
> + (__builtin_ia32_reduceph512_mask_round ((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, \
> + _MM_FROUND_CUR_DIRECTION))
>
> #define _mm512_mask_reduce_ph(A, B, C, D) \
> - (__builtin_ia32_vreduceph_v32hf_mask_round ((C), (D), (A), (B), \
> - _MM_FROUND_CUR_DIRECTION))
> + (__builtin_ia32_reduceph512_mask_round ((C), (D), (A), (B), \
> + _MM_FROUND_CUR_DIRECTION))
>
> #define _mm512_maskz_reduce_ph(A, B, C) \
> - (__builtin_ia32_vreduceph_v32hf_mask_round ((B), (C), \
> - _mm512_setzero_ph (), \
> - (A), _MM_FROUND_CUR_DIRECTION))
> + (__builtin_ia32_reduceph512_mask_round ((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), _MM_FROUND_CUR_DIRECTION))
>
> -#define _mm512_reduce_round_ph(A, B, C) \
> - (__builtin_ia32_vreduceph_v32hf_mask_round ((A), (B), \
> - _mm512_setzero_ph (), \
> - (__mmask32)-1, (C)))
> +#define _mm512_reduce_round_ph(A, B, C) \
> + (__builtin_ia32_reduceph512_mask_round ((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, (C)))
>
> #define _mm512_mask_reduce_round_ph(A, B, C, D, E) \
> - (__builtin_ia32_vreduceph_v32hf_mask_round ((C), (D), (A), (B), (E)))
> + (__builtin_ia32_reduceph512_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm512_maskz_reduce_round_ph(A, B, C, D) \
> - (__builtin_ia32_vreduceph_v32hf_mask_round ((B), (C), \
> - _mm512_setzero_ph (), \
> - (A), (D)))
> +#define _mm512_maskz_reduce_round_ph(A, B, C, D) \
> + (__builtin_ia32_reduceph512_mask_round ((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), (D)))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -1718,10 +1718,10 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_reduce_sh (__m128h __A, __m128h __B, int __C)
> {
> - return __builtin_ia32_vreducesh_v8hf_mask_round (__A, __B, __C,
> - _mm_setzero_ph (),
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_reducesh_mask_round (__A, __B, __C,
> + _mm_setzero_ph (),
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m128h
> @@ -1729,26 +1729,26 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_reduce_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, int __E)
> {
> - return __builtin_ia32_vreducesh_v8hf_mask_round (__C, __D, __E, __A, __B,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_reducesh_mask_round (__C, __D, __E, __A, __B,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_reduce_sh (__mmask8 __A, __m128h __B, __m128h __C, int __D)
> {
> - return __builtin_ia32_vreducesh_v8hf_mask_round (__B, __C, __D,
> - _mm_setzero_ph (), __A,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_reducesh_mask_round (__B, __C, __D,
> + _mm_setzero_ph (), __A,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_reduce_round_sh (__m128h __A, __m128h __B, int __C, const int __D)
> {
> - return __builtin_ia32_vreducesh_v8hf_mask_round (__A, __B, __C,
> - _mm_setzero_ph (),
> - (__mmask8) -1, __D);
> + return __builtin_ia32_reducesh_mask_round (__A, __B, __C,
> + _mm_setzero_ph (),
> + (__mmask8) -1, __D);
> }
>
> extern __inline __m128h
> @@ -1756,8 +1756,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_reduce_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, int __E, const int __F)
> {
> - return __builtin_ia32_vreducesh_v8hf_mask_round (__C, __D, __E, __A,
> - __B, __F);
> + return __builtin_ia32_reducesh_mask_round (__C, __D, __E, __A,
> + __B, __F);
> }
>
> extern __inline __m128h
> @@ -1765,81 +1765,81 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_reduce_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> int __D, const int __E)
> {
> - return __builtin_ia32_vreducesh_v8hf_mask_round (__B, __C, __D,
> - _mm_setzero_ph (),
> - __A, __E);
> + return __builtin_ia32_reducesh_mask_round (__B, __C, __D,
> + _mm_setzero_ph (),
> + __A, __E);
> }
>
> #else
> #define _mm_reduce_sh(A, B, C) \
> - (__builtin_ia32_vreducesh_v8hf_mask_round ((A), (B), (C), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, \
> - _MM_FROUND_CUR_DIRECTION))
> + (__builtin_ia32_reducesh_mask_round ((A), (B), (C), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, \
> + _MM_FROUND_CUR_DIRECTION))
>
> #define _mm_mask_reduce_sh(A, B, C, D, E) \
> - (__builtin_ia32_vreducesh_v8hf_mask_round ((C), (D), (E), (A), (B), \
> - _MM_FROUND_CUR_DIRECTION))
> + (__builtin_ia32_reducesh_mask_round ((C), (D), (E), (A), (B), \
> + _MM_FROUND_CUR_DIRECTION))
>
> #define _mm_maskz_reduce_sh(A, B, C, D) \
> - (__builtin_ia32_vreducesh_v8hf_mask_round ((B), (C), (D), \
> - _mm_setzero_ph (), \
> - (A), _MM_FROUND_CUR_DIRECTION))
> + (__builtin_ia32_reducesh_mask_round ((B), (C), (D), \
> + _mm_setzero_ph (), \
> + (A), _MM_FROUND_CUR_DIRECTION))
>
> #define _mm_reduce_round_sh(A, B, C, D) \
> - (__builtin_ia32_vreducesh_v8hf_mask_round ((A), (B), (C), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, (D)))
> + (__builtin_ia32_reducesh_mask_round ((A), (B), (C), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, (D)))
>
> #define _mm_mask_reduce_round_sh(A, B, C, D, E, F) \
> - (__builtin_ia32_vreducesh_v8hf_mask_round ((C), (D), (E), (A), (B), (F)))
> + (__builtin_ia32_reducesh_mask_round ((C), (D), (E), (A), (B), (F)))
>
> #define _mm_maskz_reduce_round_sh(A, B, C, D, E) \
> - (__builtin_ia32_vreducesh_v8hf_mask_round ((B), (C), (D), \
> - _mm_setzero_ph (), \
> - (A), (E)))
> + (__builtin_ia32_reducesh_mask_round ((B), (C), (D), \
> + _mm_setzero_ph (), \
> + (A), (E)))
>
> #endif /* __OPTIMIZE__ */
>
> /* Intrinsics vrndscaleph. */
> #ifdef __OPTIMIZE__
> extern __inline __m512h
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> + __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_roundscale_ph (__m512h __A, int __B)
> {
> - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_rndscaleph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_roundscale_ph (__m512h __A, __mmask32 __B,
> - __m512h __C, int __D)
> + __m512h __C, int __D)
> {
> - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__C, __D, __A, __B,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_rndscaleph512_mask_round (__C, __D, __A, __B,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_roundscale_ph (__mmask32 __A, __m512h __B, int __C)
> {
> - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_rndscaleph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m512h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_roundscale_round_ph (__m512h __A, int __B, const int __C)
> {
> - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__A, __B,
> - _mm512_setzero_ph (),
> - (__mmask32) -1,
> - __C);
> + return __builtin_ia32_rndscaleph512_mask_round (__A, __B,
> + _mm512_setzero_ph (),
> + (__mmask32) -1,
> + __C);
> }
>
> extern __inline __m512h
> @@ -1847,8 +1847,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_mask_roundscale_round_ph (__m512h __A, __mmask32 __B,
> __m512h __C, int __D, const int __E)
> {
> - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__C, __D, __A,
> - __B, __E);
> + return __builtin_ia32_rndscaleph512_mask_round (__C, __D, __A,
> + __B, __E);
> }
>
> extern __inline __m512h
> @@ -1856,52 +1856,52 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_roundscale_round_ph (__mmask32 __A, __m512h __B, int __C,
> const int __D)
> {
> - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__B, __C,
> - _mm512_setzero_ph (),
> - __A, __D);
> + return __builtin_ia32_rndscaleph512_mask_round (__B, __C,
> + _mm512_setzero_ph (),
> + __A, __D);
> }
>
> #else
> -#define _mm512_roundscale_ph(A, B) \
> - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((A), (B), \
> - _mm512_setzero_ph (), \
> - (__mmask32)-1, \
> - _MM_FROUND_CUR_DIRECTION))
> -
> -#define _mm512_mask_roundscale_ph(A, B, C, D) \
> - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((C), (D), (A), (B), \
> - _MM_FROUND_CUR_DIRECTION))
> -
> -#define _mm512_maskz_roundscale_ph(A, B, C) \
> - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((B), (C), \
> - _mm512_setzero_ph (), \
> - (A), \
> - _MM_FROUND_CUR_DIRECTION))
> -#define _mm512_roundscale_round_ph(A, B, C) \
> - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((A), (B), \
> - _mm512_setzero_ph (), \
> - (__mmask32)-1, (C)))
> +#define _mm512_roundscale_ph(A, B) \
> + (__builtin_ia32_rndscaleph512_mask_round ((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, \
> + _MM_FROUND_CUR_DIRECTION))
> +
> +#define _mm512_mask_roundscale_ph(A, B, C, D) \
> + (__builtin_ia32_rndscaleph512_mask_round ((C), (D), (A), (B), \
> + _MM_FROUND_CUR_DIRECTION))
> +
> +#define _mm512_maskz_roundscale_ph(A, B, C) \
> + (__builtin_ia32_rndscaleph512_mask_round ((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), \
> + _MM_FROUND_CUR_DIRECTION))
> +#define _mm512_roundscale_round_ph(A, B, C) \
> + (__builtin_ia32_rndscaleph512_mask_round ((A), (B), \
> + _mm512_setzero_ph (), \
> + (__mmask32)-1, (C)))
>
> #define _mm512_mask_roundscale_round_ph(A, B, C, D, E) \
> - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((C), (D), (A), (B), (E)))
> + (__builtin_ia32_rndscaleph512_mask_round ((C), (D), (A), (B), (E)))
>
> -#define _mm512_maskz_roundscale_round_ph(A, B, C, D) \
> - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((B), (C), \
> - _mm512_setzero_ph (), \
> - (A), (D)))
> +#define _mm512_maskz_roundscale_round_ph(A, B, C, D) \
> + (__builtin_ia32_rndscaleph512_mask_round ((B), (C), \
> + _mm512_setzero_ph (), \
> + (A), (D)))
>
> #endif /* __OPTIMIZE__ */
>
> /* Intrinsics vrndscalesh. */
> #ifdef __OPTIMIZE__
> extern __inline __m128h
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> + __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_roundscale_sh (__m128h __A, __m128h __B, int __C)
> {
> - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__A, __B, __C,
> - _mm_setzero_ph (),
> - (__mmask8) -1,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_rndscalesh_mask_round (__A, __B, __C,
> + _mm_setzero_ph (),
> + (__mmask8) -1,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m128h
> @@ -1909,27 +1909,27 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_roundscale_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, int __E)
> {
> - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__C, __D, __E, __A, __B,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_rndscalesh_mask_round (__C, __D, __E, __A, __B,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_roundscale_sh (__mmask8 __A, __m128h __B, __m128h __C, int __D)
> {
> - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__B, __C, __D,
> - _mm_setzero_ph (), __A,
> - _MM_FROUND_CUR_DIRECTION);
> + return __builtin_ia32_rndscalesh_mask_round (__B, __C, __D,
> + _mm_setzero_ph (), __A,
> + _MM_FROUND_CUR_DIRECTION);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_roundscale_round_sh (__m128h __A, __m128h __B, int __C, const int __D)
> {
> - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__A, __B, __C,
> - _mm_setzero_ph (),
> - (__mmask8) -1,
> - __D);
> + return __builtin_ia32_rndscalesh_mask_round (__A, __B, __C,
> + _mm_setzero_ph (),
> + (__mmask8) -1,
> + __D);
> }
>
> extern __inline __m128h
> @@ -1937,8 +1937,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_roundscale_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> __m128h __D, int __E, const int __F)
> {
> - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__C, __D, __E,
> - __A, __B, __F);
> + return __builtin_ia32_rndscalesh_mask_round (__C, __D, __E,
> + __A, __B, __F);
> }
>
> extern __inline __m128h
> @@ -1946,46 +1946,46 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_roundscale_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> int __D, const int __E)
> {
> - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__B, __C, __D,
> - _mm_setzero_ph (),
> - __A, __E);
> + return __builtin_ia32_rndscalesh_mask_round (__B, __C, __D,
> + _mm_setzero_ph (),
> + __A, __E);
> }
>
> #else
> #define _mm_roundscale_sh(A, B, C) \
> - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((A), (B), (C), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, \
> - _MM_FROUND_CUR_DIRECTION))
> + (__builtin_ia32_rndscalesh_mask_round ((A), (B), (C), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, \
> + _MM_FROUND_CUR_DIRECTION))
>
> #define _mm_mask_roundscale_sh(A, B, C, D, E) \
> - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((C), (D), (E), (A), (B), \
> - _MM_FROUND_CUR_DIRECTION))
> + (__builtin_ia32_rndscalesh_mask_round ((C), (D), (E), (A), (B), \
> + _MM_FROUND_CUR_DIRECTION))
>
> #define _mm_maskz_roundscale_sh(A, B, C, D) \
> - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((B), (C), (D), \
> - _mm_setzero_ph (), \
> - (A), _MM_FROUND_CUR_DIRECTION))
> + (__builtin_ia32_rndscalesh_mask_round ((B), (C), (D), \
> + _mm_setzero_ph (), \
> + (A), _MM_FROUND_CUR_DIRECTION))
>
> -#define _mm_roundscale_round_sh(A, B, C, D) \
> - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((A), (B), (C), \
> - _mm_setzero_ph (), \
> - (__mmask8)-1, (D)))
> +#define _mm_roundscale_round_sh(A, B, C, D) \
> + (__builtin_ia32_rndscalesh_mask_round ((A), (B), (C), \
> + _mm_setzero_ph (), \
> + (__mmask8)-1, (D)))
>
> #define _mm_mask_roundscale_round_sh(A, B, C, D, E, F) \
> - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((C), (D), (E), (A), (B), (F)))
> + (__builtin_ia32_rndscalesh_mask_round ((C), (D), (E), (A), (B), (F)))
>
> -#define _mm_maskz_roundscale_round_sh(A, B, C, D, E) \
> - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((B), (C), (D), \
> - _mm_setzero_ph (), \
> - (A), (E)))
> +#define _mm_maskz_roundscale_round_sh(A, B, C, D, E) \
> + (__builtin_ia32_rndscalesh_mask_round ((B), (C), (D), \
> + _mm_setzero_ph (), \
> + (A), (E)))
>
> #endif /* __OPTIMIZE__ */
>
> /* Intrinsics vfpclasssh. */
> #ifdef __OPTIMIZE__
> extern __inline __mmask8
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> + __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_fpclass_sh_mask (__m128h __A, const int __imm)
> {
> return (__mmask8) __builtin_ia32_fpclasssh_mask ((__v8hf) __A, __imm,
> @@ -2031,11 +2031,11 @@ _mm512_fpclass_ph_mask (__m512h __A, const int __imm)
>
> #else
> #define _mm512_mask_fpclass_ph_mask(u, x, c) \
> - ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x),\
> + ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x), \
> (int) (c),(__mmask8)(u)))
>
> #define _mm512_fpclass_ph_mask(x, c) \
> - ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x),\
> + ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x), \
> (int) (c),(__mmask8)-1))
> #endif /* __OPIMTIZE__ */
>
> @@ -2141,9 +2141,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_getexp_round_ph (__m512h __A, const int __R)
> {
> return (__m512h) __builtin_ia32_getexpph512_mask ((__v32hf) __A,
> - (__v32hf)
> - _mm512_setzero_ph (),
> - (__mmask32) -1, __R);
> + (__v32hf)
> + _mm512_setzero_ph (),
> + (__mmask32) -1, __R);
> }
>
> extern __inline __m512h
> @@ -2152,8 +2152,8 @@ _mm512_mask_getexp_round_ph (__m512h __W, __mmask32 __U, __m512h __A,
> const int __R)
> {
> return (__m512h) __builtin_ia32_getexpph512_mask ((__v32hf) __A,
> - (__v32hf) __W,
> - (__mmask32) __U, __R);
> + (__v32hf) __W,
> + (__mmask32) __U, __R);
> }
>
> extern __inline __m512h
> @@ -2161,37 +2161,37 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm512_maskz_getexp_round_ph (__mmask32 __U, __m512h __A, const int __R)
> {
> return (__m512h) __builtin_ia32_getexpph512_mask ((__v32hf) __A,
> - (__v32hf)
> - _mm512_setzero_ph (),
> - (__mmask32) __U, __R);
> + (__v32hf)
> + _mm512_setzero_ph (),
> + (__mmask32) __U, __R);
> }
>
> #else
> -#define _mm_getexp_round_sh(A, B, R) \
> - ((__m128h)__builtin_ia32_getexpsh_mask_round((__v8hf)(__m128h)(A), \
> - (__v8hf)(__m128h)(B), \
> - (__v8hf)_mm_setzero_ph(), \
> +#define _mm_getexp_round_sh(A, B, R) \
> + ((__m128h)__builtin_ia32_getexpsh_mask_round((__v8hf)(__m128h)(A), \
> + (__v8hf)(__m128h)(B), \
> + (__v8hf)_mm_setzero_ph(), \
> (__mmask8)-1, R))
>
> -#define _mm_mask_getexp_round_sh(W, U, A, B, C) \
> +#define _mm_mask_getexp_round_sh(W, U, A, B, C) \
> (__m128h)__builtin_ia32_getexpsh_mask_round(A, B, W, U, C)
>
> -#define _mm_maskz_getexp_round_sh(U, A, B, C) \
> - (__m128h)__builtin_ia32_getexpsh_mask_round(A, B, \
> - (__v8hf)_mm_setzero_ph(), \
> +#define _mm_maskz_getexp_round_sh(U, A, B, C) \
> + (__m128h)__builtin_ia32_getexpsh_mask_round(A, B, \
> + (__v8hf)_mm_setzero_ph(), \
> U, C)
>
> -#define _mm512_getexp_round_ph(A, R) \
> - ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> - (__v32hf)_mm512_setzero_ph(), (__mmask32)-1, R))
> +#define _mm512_getexp_round_ph(A, R) \
> + ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> + (__v32hf)_mm512_setzero_ph(), (__mmask32)-1, R))
>
> -#define _mm512_mask_getexp_round_ph(W, U, A, R) \
> - ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> - (__v32hf)(__m512h)(W), (__mmask32)(U), R))
> +#define _mm512_mask_getexp_round_ph(W, U, A, R) \
> + ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> + (__v32hf)(__m512h)(W), (__mmask32)(U), R))
>
> -#define _mm512_maskz_getexp_round_ph(U, A, R) \
> - ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> - (__v32hf)_mm512_setzero_ph(), (__mmask32)(U), R))
> +#define _mm512_maskz_getexp_round_ph(U, A, R) \
> + ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> + (__v32hf)_mm512_setzero_ph(), (__mmask32)(U), R))
>
> #endif /* __OPTIMIZE__ */
>
> diff --git a/gcc/config/i386/avx512fp16vlintrin.h b/gcc/config/i386/avx512fp16vlintrin.h
> index 206d60407fc..e9478792a03 100644
> --- a/gcc/config/i386/avx512fp16vlintrin.h
> +++ b/gcc/config/i386/avx512fp16vlintrin.h
> @@ -53,30 +53,30 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_add_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vaddph_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_addph128_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_add_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> {
> - return __builtin_ia32_vaddph_v16hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_addph256_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_add_ph (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vaddph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_addph128_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_add_ph (__mmask16 __A, __m256h __B, __m256h __C)
> {
> - return __builtin_ia32_vaddph_v16hf_mask (__B, __C,
> - _mm256_setzero_ph (), __A);
> + return __builtin_ia32_addph256_mask (__B, __C,
> + _mm256_setzero_ph (), __A);
> }
>
> extern __inline __m128h
> @@ -97,30 +97,30 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_sub_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vsubph_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_subph128_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_sub_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> {
> - return __builtin_ia32_vsubph_v16hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_subph256_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_sub_ph (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vsubph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_subph128_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_sub_ph (__mmask16 __A, __m256h __B, __m256h __C)
> {
> - return __builtin_ia32_vsubph_v16hf_mask (__B, __C,
> - _mm256_setzero_ph (), __A);
> + return __builtin_ia32_subph256_mask (__B, __C,
> + _mm256_setzero_ph (), __A);
> }
>
> extern __inline __m128h
> @@ -141,30 +141,30 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_mul_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vmulph_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_mulph128_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_mul_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> {
> - return __builtin_ia32_vmulph_v16hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_mulph256_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_mul_ph (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vmulph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_mulph128_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_mul_ph (__mmask16 __A, __m256h __B, __m256h __C)
> {
> - return __builtin_ia32_vmulph_v16hf_mask (__B, __C,
> - _mm256_setzero_ph (), __A);
> + return __builtin_ia32_mulph256_mask (__B, __C,
> + _mm256_setzero_ph (), __A);
> }
>
> extern __inline __m128h
> @@ -185,30 +185,30 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_div_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vdivph_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_divph128_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_div_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> {
> - return __builtin_ia32_vdivph_v16hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_divph256_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_div_ph (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vdivph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_divph128_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_div_ph (__mmask16 __A, __m256h __B, __m256h __C)
> {
> - return __builtin_ia32_vdivph_v16hf_mask (__B, __C,
> - _mm256_setzero_ph (), __A);
> + return __builtin_ia32_divph256_mask (__B, __C,
> + _mm256_setzero_ph (), __A);
> }
>
> /* Intrinsics v[max,min]ph. */
> @@ -216,96 +216,96 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_max_ph (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vmaxph_v8hf_mask (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1);
> + return __builtin_ia32_maxph128_mask (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_max_ph (__m256h __A, __m256h __B)
> {
> - return __builtin_ia32_vmaxph_v16hf_mask (__A, __B,
> - _mm256_setzero_ph (),
> - (__mmask16) -1);
> + return __builtin_ia32_maxph256_mask (__A, __B,
> + _mm256_setzero_ph (),
> + (__mmask16) -1);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_max_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vmaxph_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_maxph128_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_max_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> {
> - return __builtin_ia32_vmaxph_v16hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_maxph256_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_max_ph (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vmaxph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_maxph128_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_max_ph (__mmask16 __A, __m256h __B, __m256h __C)
> {
> - return __builtin_ia32_vmaxph_v16hf_mask (__B, __C,
> - _mm256_setzero_ph (), __A);
> + return __builtin_ia32_maxph256_mask (__B, __C,
> + _mm256_setzero_ph (), __A);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_min_ph (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vminph_v8hf_mask (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1);
> + return __builtin_ia32_minph128_mask (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_min_ph (__m256h __A, __m256h __B)
> {
> - return __builtin_ia32_vminph_v16hf_mask (__A, __B,
> - _mm256_setzero_ph (),
> - (__mmask16) -1);
> + return __builtin_ia32_minph256_mask (__A, __B,
> + _mm256_setzero_ph (),
> + (__mmask16) -1);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_min_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vminph_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_minph128_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_min_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> {
> - return __builtin_ia32_vminph_v16hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_minph256_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_min_ph (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vminph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_minph128_mask (__B, __C, _mm_setzero_ph (),
> + __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_min_ph (__mmask16 __A, __m256h __B, __m256h __C)
> {
> - return __builtin_ia32_vminph_v16hf_mask (__B, __C,
> - _mm256_setzero_ph (), __A);
> + return __builtin_ia32_minph256_mask (__B, __C,
> + _mm256_setzero_ph (), __A);
> }
>
> /* vcmpph */
> @@ -314,8 +314,8 @@ extern __inline __mmask8
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_cmp_ph_mask (__m128h __A, __m128h __B, const int __C)
> {
> - return (__mmask8) __builtin_ia32_vcmpph_v8hf_mask (__A, __B, __C,
> - (__mmask8) -1);
> + return (__mmask8) __builtin_ia32_cmpph128_mask (__A, __B, __C,
> + (__mmask8) -1);
> }
>
> extern __inline __mmask8
> @@ -323,15 +323,15 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_cmp_ph_mask (__mmask8 __A, __m128h __B, __m128h __C,
> const int __D)
> {
> - return (__mmask8) __builtin_ia32_vcmpph_v8hf_mask (__B, __C, __D, __A);
> + return (__mmask8) __builtin_ia32_cmpph128_mask (__B, __C, __D, __A);
> }
>
> extern __inline __mmask16
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_cmp_ph_mask (__m256h __A, __m256h __B, const int __C)
> {
> - return (__mmask16) __builtin_ia32_vcmpph_v16hf_mask (__A, __B, __C,
> - (__mmask16) -1);
> + return (__mmask16) __builtin_ia32_cmpph256_mask (__A, __B, __C,
> + (__mmask16) -1);
> }
>
> extern __inline __mmask16
> @@ -339,22 +339,22 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_cmp_ph_mask (__mmask16 __A, __m256h __B, __m256h __C,
> const int __D)
> {
> - return (__mmask16) __builtin_ia32_vcmpph_v16hf_mask (__B, __C, __D,
> - __A);
> + return (__mmask16) __builtin_ia32_cmpph256_mask (__B, __C, __D,
> + __A);
> }
>
> #else
> -#define _mm_cmp_ph_mask(A, B, C) \
> - (__builtin_ia32_vcmpph_v8hf_mask ((A), (B), (C), (-1)))
> +#define _mm_cmp_ph_mask(A, B, C) \
> + (__builtin_ia32_cmpph128_mask ((A), (B), (C), (-1)))
>
> -#define _mm_mask_cmp_ph_mask(A, B, C, D) \
> - (__builtin_ia32_vcmpph_v8hf_mask ((B), (C), (D), (A)))
> +#define _mm_mask_cmp_ph_mask(A, B, C, D) \
> + (__builtin_ia32_cmpph128_mask ((B), (C), (D), (A)))
>
> -#define _mm256_cmp_ph_mask(A, B, C) \
> - (__builtin_ia32_vcmpph_v16hf_mask ((A), (B), (C), (-1)))
> +#define _mm256_cmp_ph_mask(A, B, C) \
> + (__builtin_ia32_cmpph256_mask ((A), (B), (C), (-1)))
>
> -#define _mm256_mask_cmp_ph_mask(A, B, C, D) \
> - (__builtin_ia32_vcmpph_v16hf_mask ((B), (C), (D), (A)))
> +#define _mm256_mask_cmp_ph_mask(A, B, C, D) \
> + (__builtin_ia32_cmpph256_mask ((B), (C), (D), (A)))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -363,46 +363,46 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_sqrt_ph (__m128h __A)
> {
> - return __builtin_ia32_vsqrtph_v8hf_mask (__A, _mm_setzero_ph (),
> - (__mmask8) -1);
> + return __builtin_ia32_sqrtph128_mask (__A, _mm_setzero_ph (),
> + (__mmask8) -1);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_sqrt_ph (__m256h __A)
> {
> - return __builtin_ia32_vsqrtph_v16hf_mask (__A, _mm256_setzero_ph (),
> - (__mmask16) -1);
> + return __builtin_ia32_sqrtph256_mask (__A, _mm256_setzero_ph (),
> + (__mmask16) -1);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_sqrt_ph (__m128h __A, __mmask8 __B, __m128h __C)
> {
> - return __builtin_ia32_vsqrtph_v8hf_mask (__C, __A, __B);
> + return __builtin_ia32_sqrtph128_mask (__C, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_sqrt_ph (__m256h __A, __mmask16 __B, __m256h __C)
> {
> - return __builtin_ia32_vsqrtph_v16hf_mask (__C, __A, __B);
> + return __builtin_ia32_sqrtph256_mask (__C, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_sqrt_ph (__mmask8 __A, __m128h __B)
> {
> - return __builtin_ia32_vsqrtph_v8hf_mask (__B, _mm_setzero_ph (),
> - __A);
> + return __builtin_ia32_sqrtph128_mask (__B, _mm_setzero_ph (),
> + __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_sqrt_ph (__mmask16 __A, __m256h __B)
> {
> - return __builtin_ia32_vsqrtph_v16hf_mask (__B, _mm256_setzero_ph (),
> - __A);
> + return __builtin_ia32_sqrtph256_mask (__B, _mm256_setzero_ph (),
> + __A);
> }
>
> /* Intrinsics vrsqrtph. */
> @@ -410,45 +410,45 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_rsqrt_ph (__m128h __A)
> {
> - return __builtin_ia32_vrsqrtph_v8hf_mask (__A, _mm_setzero_ph (),
> - (__mmask8) -1);
> + return __builtin_ia32_rsqrtph128_mask (__A, _mm_setzero_ph (),
> + (__mmask8) -1);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_rsqrt_ph (__m256h __A)
> {
> - return __builtin_ia32_vrsqrtph_v16hf_mask (__A, _mm256_setzero_ph (),
> - (__mmask16) -1);
> + return __builtin_ia32_rsqrtph256_mask (__A, _mm256_setzero_ph (),
> + (__mmask16) -1);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_rsqrt_ph (__m128h __A, __mmask8 __B, __m128h __C)
> {
> - return __builtin_ia32_vrsqrtph_v8hf_mask (__C, __A, __B);
> + return __builtin_ia32_rsqrtph128_mask (__C, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_rsqrt_ph (__m256h __A, __mmask16 __B, __m256h __C)
> {
> - return __builtin_ia32_vrsqrtph_v16hf_mask (__C, __A, __B);
> + return __builtin_ia32_rsqrtph256_mask (__C, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_rsqrt_ph (__mmask8 __A, __m128h __B)
> {
> - return __builtin_ia32_vrsqrtph_v8hf_mask (__B, _mm_setzero_ph (), __A);
> + return __builtin_ia32_rsqrtph128_mask (__B, _mm_setzero_ph (), __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_rsqrt_ph (__mmask16 __A, __m256h __B)
> {
> - return __builtin_ia32_vrsqrtph_v16hf_mask (__B, _mm256_setzero_ph (),
> - __A);
> + return __builtin_ia32_rsqrtph256_mask (__B, _mm256_setzero_ph (),
> + __A);
> }
>
> /* Intrinsics vrcpph. */
> @@ -456,45 +456,45 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_rcp_ph (__m128h __A)
> {
> - return __builtin_ia32_vrcpph_v8hf_mask (__A, _mm_setzero_ph (),
> - (__mmask8) -1);
> + return __builtin_ia32_rcpph128_mask (__A, _mm_setzero_ph (),
> + (__mmask8) -1);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_rcp_ph (__m256h __A)
> {
> - return __builtin_ia32_vrcpph_v16hf_mask (__A, _mm256_setzero_ph (),
> - (__mmask16) -1);
> + return __builtin_ia32_rcpph256_mask (__A, _mm256_setzero_ph (),
> + (__mmask16) -1);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_rcp_ph (__m128h __A, __mmask8 __B, __m128h __C)
> {
> - return __builtin_ia32_vrcpph_v8hf_mask (__C, __A, __B);
> + return __builtin_ia32_rcpph128_mask (__C, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_rcp_ph (__m256h __A, __mmask16 __B, __m256h __C)
> {
> - return __builtin_ia32_vrcpph_v16hf_mask (__C, __A, __B);
> + return __builtin_ia32_rcpph256_mask (__C, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_rcp_ph (__mmask8 __A, __m128h __B)
> {
> - return __builtin_ia32_vrcpph_v8hf_mask (__B, _mm_setzero_ph (), __A);
> + return __builtin_ia32_rcpph128_mask (__B, _mm_setzero_ph (), __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_rcp_ph (__mmask16 __A, __m256h __B)
> {
> - return __builtin_ia32_vrcpph_v16hf_mask (__B, _mm256_setzero_ph (),
> - __A);
> + return __builtin_ia32_rcpph256_mask (__B, _mm256_setzero_ph (),
> + __A);
> }
>
> /* Intrinsics vscalefph. */
> @@ -502,25 +502,25 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_scalef_ph (__m128h __A, __m128h __B)
> {
> - return __builtin_ia32_vscalefph_v8hf_mask (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1);
> + return __builtin_ia32_scalefph128_mask (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_scalef_ph (__m256h __A, __m256h __B)
> {
> - return __builtin_ia32_vscalefph_v16hf_mask (__A, __B,
> - _mm256_setzero_ph (),
> - (__mmask16) -1);
> + return __builtin_ia32_scalefph256_mask (__A, __B,
> + _mm256_setzero_ph (),
> + (__mmask16) -1);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_scalef_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> {
> - return __builtin_ia32_vscalefph_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_scalefph128_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m256h
> @@ -528,24 +528,24 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_scalef_ph (__m256h __A, __mmask16 __B, __m256h __C,
> __m256h __D)
> {
> - return __builtin_ia32_vscalefph_v16hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_scalefph256_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_scalef_ph (__mmask8 __A, __m128h __B, __m128h __C)
> {
> - return __builtin_ia32_vscalefph_v8hf_mask (__B, __C,
> - _mm_setzero_ph (), __A);
> + return __builtin_ia32_scalefph128_mask (__B, __C,
> + _mm_setzero_ph (), __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_scalef_ph (__mmask16 __A, __m256h __B, __m256h __C)
> {
> - return __builtin_ia32_vscalefph_v16hf_mask (__B, __C,
> - _mm256_setzero_ph (),
> - __A);
> + return __builtin_ia32_scalefph256_mask (__B, __C,
> + _mm256_setzero_ph (),
> + __A);
> }
>
> /* Intrinsics vreduceph. */
> @@ -554,109 +554,109 @@ extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_reduce_ph (__m128h __A, int __B)
> {
> - return __builtin_ia32_vreduceph_v8hf_mask (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1);
> + return __builtin_ia32_reduceph128_mask (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_reduce_ph (__m128h __A, __mmask8 __B, __m128h __C, int __D)
> {
> - return __builtin_ia32_vreduceph_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_reduceph128_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_reduce_ph (__mmask8 __A, __m128h __B, int __C)
> {
> - return __builtin_ia32_vreduceph_v8hf_mask (__B, __C,
> - _mm_setzero_ph (), __A);
> + return __builtin_ia32_reduceph128_mask (__B, __C,
> + _mm_setzero_ph (), __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_reduce_ph (__m256h __A, int __B)
> {
> - return __builtin_ia32_vreduceph_v16hf_mask (__A, __B,
> - _mm256_setzero_ph (),
> - (__mmask16) -1);
> + return __builtin_ia32_reduceph256_mask (__A, __B,
> + _mm256_setzero_ph (),
> + (__mmask16) -1);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_reduce_ph (__m256h __A, __mmask16 __B, __m256h __C, int __D)
> {
> - return __builtin_ia32_vreduceph_v16hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_reduceph256_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_reduce_ph (__mmask16 __A, __m256h __B, int __C)
> {
> - return __builtin_ia32_vreduceph_v16hf_mask (__B, __C,
> - _mm256_setzero_ph (),
> - __A);
> + return __builtin_ia32_reduceph256_mask (__B, __C,
> + _mm256_setzero_ph (),
> + __A);
> }
>
> #else
> -#define _mm_reduce_ph(A, B) \
> - (__builtin_ia32_vreduceph_v8hf_mask ((A), (B),\
> - _mm_setzero_ph (), \
> - ((__mmask8)-1)))
> +#define _mm_reduce_ph(A, B) \
> + (__builtin_ia32_reduceph128_mask ((A), (B), \
> + _mm_setzero_ph (), \
> + ((__mmask8)-1)))
>
> -#define _mm_mask_reduce_ph(A, B, C, D) \
> - (__builtin_ia32_vreduceph_v8hf_mask ((C), (D), (A), (B)))
> +#define _mm_mask_reduce_ph(A, B, C, D) \
> + (__builtin_ia32_reduceph128_mask ((C), (D), (A), (B)))
>
> -#define _mm_maskz_reduce_ph(A, B, C) \
> - (__builtin_ia32_vreduceph_v8hf_mask ((B), (C), _mm_setzero_ph (), (A)))
> +#define _mm_maskz_reduce_ph(A, B, C) \
> + (__builtin_ia32_reduceph128_mask ((B), (C), _mm_setzero_ph (), (A)))
>
> #define _mm256_reduce_ph(A, B) \
> - (__builtin_ia32_vreduceph_v16hf_mask ((A), (B),\
> - _mm256_setzero_ph (), \
> - ((__mmask16)-1)))
> + (__builtin_ia32_reduceph256_mask ((A), (B), \
> + _mm256_setzero_ph (), \
> + ((__mmask16)-1)))
>
> -#define _mm256_mask_reduce_ph(A, B, C, D) \
> - (__builtin_ia32_vreduceph_v16hf_mask ((C), (D), (A), (B)))
> +#define _mm256_mask_reduce_ph(A, B, C, D) \
> + (__builtin_ia32_reduceph256_mask ((C), (D), (A), (B)))
>
> -#define _mm256_maskz_reduce_ph(A, B, C) \
> - (__builtin_ia32_vreduceph_v16hf_mask ((B), (C), _mm256_setzero_ph (), (A)))
> +#define _mm256_maskz_reduce_ph(A, B, C) \
> + (__builtin_ia32_reduceph256_mask ((B), (C), _mm256_setzero_ph (), (A)))
>
> #endif /* __OPTIMIZE__ */
>
> /* Intrinsics vrndscaleph. */
> #ifdef __OPTIMIZE__
> -extern __inline __m128h
> -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_roundscale_ph (__m128h __A, int __B)
> -{
> - return __builtin_ia32_vrndscaleph_v8hf_mask (__A, __B,
> - _mm_setzero_ph (),
> - (__mmask8) -1);
> -}
> + extern __inline __m128h
> + __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> + _mm_roundscale_ph (__m128h __A, int __B)
> + {
> + return __builtin_ia32_rndscaleph128_mask (__A, __B,
> + _mm_setzero_ph (),
> + (__mmask8) -1);
> + }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_roundscale_ph (__m128h __A, __mmask8 __B, __m128h __C, int __D)
> {
> - return __builtin_ia32_vrndscaleph_v8hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_rndscaleph128_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m128h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_roundscale_ph (__mmask8 __A, __m128h __B, int __C)
> {
> - return __builtin_ia32_vrndscaleph_v8hf_mask (__B, __C,
> - _mm_setzero_ph (), __A);
> + return __builtin_ia32_rndscaleph128_mask (__B, __C,
> + _mm_setzero_ph (), __A);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_roundscale_ph (__m256h __A, int __B)
> {
> - return __builtin_ia32_vrndscaleph_v16hf_mask (__A, __B,
> - _mm256_setzero_ph (),
> - (__mmask16) -1);
> + return __builtin_ia32_rndscaleph256_mask (__A, __B,
> + _mm256_setzero_ph (),
> + (__mmask16) -1);
> }
>
> extern __inline __m256h
> @@ -664,40 +664,40 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_roundscale_ph (__m256h __A, __mmask16 __B, __m256h __C,
> int __D)
> {
> - return __builtin_ia32_vrndscaleph_v16hf_mask (__C, __D, __A, __B);
> + return __builtin_ia32_rndscaleph256_mask (__C, __D, __A, __B);
> }
>
> extern __inline __m256h
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_roundscale_ph (__mmask16 __A, __m256h __B, int __C)
> {
> - return __builtin_ia32_vrndscaleph_v16hf_mask (__B, __C,
> - _mm256_setzero_ph (),
> - __A);
> + return __builtin_ia32_rndscaleph256_mask (__B, __C,
> + _mm256_setzero_ph (),
> + __A);
> }
>
> #else
> -#define _mm_roundscale_ph(A, B) \
> - (__builtin_ia32_vrndscaleph_v8hf_mask ((A), (B), _mm_setzero_ph (), \
> - ((__mmask8)-1)))
> +#define _mm_roundscale_ph(A, B) \
> + (__builtin_ia32_rndscaleph128_mask ((A), (B), _mm_setzero_ph (), \
> + ((__mmask8)-1)))
>
> -#define _mm_mask_roundscale_ph(A, B, C, D) \
> - (__builtin_ia32_vrndscaleph_v8hf_mask ((C), (D), (A), (B)))
> +#define _mm_mask_roundscale_ph(A, B, C, D) \
> + (__builtin_ia32_rndscaleph128_mask ((C), (D), (A), (B)))
>
> -#define _mm_maskz_roundscale_ph(A, B, C) \
> - (__builtin_ia32_vrndscaleph_v8hf_mask ((B), (C), _mm_setzero_ph (), (A)))
> +#define _mm_maskz_roundscale_ph(A, B, C) \
> + (__builtin_ia32_rndscaleph128_mask ((B), (C), _mm_setzero_ph (), (A)))
>
> -#define _mm256_roundscale_ph(A, B) \
> - (__builtin_ia32_vrndscaleph_v16hf_mask ((A), (B), \
> - _mm256_setzero_ph(), \
> - ((__mmask16)-1)))
> +#define _mm256_roundscale_ph(A, B) \
> + (__builtin_ia32_rndscaleph256_mask ((A), (B), \
> + _mm256_setzero_ph(), \
> + ((__mmask16)-1)))
>
> -#define _mm256_mask_roundscale_ph(A, B, C, D) \
> - (__builtin_ia32_vrndscaleph_v16hf_mask ((C), (D), (A), (B)))
> +#define _mm256_mask_roundscale_ph(A, B, C, D) \
> + (__builtin_ia32_rndscaleph256_mask ((C), (D), (A), (B)))
>
> -#define _mm256_maskz_roundscale_ph(A, B, C) \
> - (__builtin_ia32_vrndscaleph_v16hf_mask ((B), (C), \
> - _mm256_setzero_ph (), (A)))
> +#define _mm256_maskz_roundscale_ph(A, B, C) \
> + (__builtin_ia32_rndscaleph256_mask ((B), (C), \
> + _mm256_setzero_ph (), (A)))
>
> #endif /* __OPTIMIZE__ */
>
> @@ -705,7 +705,7 @@ _mm256_maskz_roundscale_ph (__mmask16 __A, __m256h __B, int __C)
> #ifdef __OPTIMIZE__
> extern __inline __mmask8
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm_mask_fpclass_ph_mask (__mmask8 __U, __m128h __A, const int __imm)
> + _mm_mask_fpclass_ph_mask (__mmask8 __U, __m128h __A, const int __imm)
> {
> return (__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) __A,
> __imm, __U);
> @@ -725,7 +725,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_fpclass_ph_mask (__mmask16 __U, __m256h __A, const int __imm)
> {
> return (__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) __A,
> - __imm, __U);
> + __imm, __U);
> }
>
> extern __inline __mmask16
> @@ -733,26 +733,26 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_fpclass_ph_mask (__m256h __A, const int __imm)
> {
> return (__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) __A,
> - __imm,
> - (__mmask16) -1);
> + __imm,
> + (__mmask16) -1);
> }
>
> #else
> #define _mm_fpclass_ph_mask(X, C) \
> - ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
> + ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
> (int) (C),(__mmask8)-1))
>
> #define _mm_mask_fpclass_ph_mask(u, X, C) \
> - ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
> + ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
> (int) (C),(__mmask8)(u)))
>
> #define _mm256_fpclass_ph_mask(X, C) \
> - ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
> - (int) (C),(__mmask16)-1))
> + ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
> + (int) (C),(__mmask16)-1))
>
> #define _mm256_mask_fpclass_ph_mask(u, X, C) \
> - ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
> - (int) (C),(__mmask16)(u)))
> + ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
> + (int) (C),(__mmask16)(u)))
> #endif /* __OPTIMIZE__ */
>
> /* Intrinsics vgetexpph, vgetexpsh. */
> @@ -761,9 +761,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_getexp_ph (__m256h __A)
> {
> return (__m256h) __builtin_ia32_getexpph256_mask ((__v16hf) __A,
> - (__v16hf)
> - _mm256_setzero_ph (),
> - (__mmask16) -1);
> + (__v16hf)
> + _mm256_setzero_ph (),
> + (__mmask16) -1);
> }
>
> extern __inline __m256h
> @@ -771,8 +771,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_mask_getexp_ph (__m256h __W, __mmask16 __U, __m256h __A)
> {
> return (__m256h) __builtin_ia32_getexpph256_mask ((__v16hf) __A,
> - (__v16hf) __W,
> - (__mmask16) __U);
> + (__v16hf) __W,
> + (__mmask16) __U);
> }
>
> extern __inline __m256h
> @@ -780,9 +780,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm256_maskz_getexp_ph (__mmask16 __U, __m256h __A)
> {
> return (__m256h) __builtin_ia32_getexpph256_mask ((__v16hf) __A,
> - (__v16hf)
> - _mm256_setzero_ph (),
> - (__mmask16) __U);
> + (__v16hf)
> + _mm256_setzero_ph (),
> + (__mmask16) __U);
> }
>
> extern __inline __m128h
> @@ -790,9 +790,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_getexp_ph (__m128h __A)
> {
> return (__m128h) __builtin_ia32_getexpph128_mask ((__v8hf) __A,
> - (__v8hf)
> - _mm_setzero_ph (),
> - (__mmask8) -1);
> + (__v8hf)
> + _mm_setzero_ph (),
> + (__mmask8) -1);
> }
>
> extern __inline __m128h
> @@ -800,8 +800,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_mask_getexp_ph (__m128h __W, __mmask8 __U, __m128h __A)
> {
> return (__m128h) __builtin_ia32_getexpph128_mask ((__v8hf) __A,
> - (__v8hf) __W,
> - (__mmask8) __U);
> + (__v8hf) __W,
> + (__mmask8) __U);
> }
>
> extern __inline __m128h
> @@ -809,9 +809,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> _mm_maskz_getexp_ph (__mmask8 __U, __m128h __A)
> {
> return (__m128h) __builtin_ia32_getexpph128_mask ((__v8hf) __A,
> - (__v8hf)
> - _mm_setzero_ph (),
> - (__mmask8) __U);
> + (__v8hf)
> + _mm_setzero_ph (),
> + (__mmask8) __U);
> }
>
>
> @@ -892,41 +892,41 @@ _mm_maskz_getmant_ph (__mmask8 __U, __m128h __A,
> }
>
> #else
> -#define _mm256_getmant_ph(X, B, C) \
> - ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> - (int)(((C)<<2) | (B)), \
> - (__v16hf)(__m256h)_mm256_setzero_ph (),\
> - (__mmask16)-1))
> -
> -#define _mm256_mask_getmant_ph(W, U, X, B, C) \
> - ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> - (int)(((C)<<2) | (B)), \
> - (__v16hf)(__m256h)(W), \
> - (__mmask16)(U)))
> -
> -#define _mm256_maskz_getmant_ph(U, X, B, C) \
> - ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> - (int)(((C)<<2) | (B)), \
> - (__v16hf)(__m256h)_mm256_setzero_ph (),\
> - (__mmask16)(U)))
> -
> -#define _mm_getmant_ph(X, B, C) \
> - ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> - (int)(((C)<<2) | (B)), \
> - (__v8hf)(__m128h)_mm_setzero_ph (), \
> - (__mmask8)-1))
> -
> -#define _mm_mask_getmant_ph(W, U, X, B, C) \
> - ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> - (int)(((C)<<2) | (B)), \
> - (__v8hf)(__m128h)(W), \
> - (__mmask8)(U)))
> -
> -#define _mm_maskz_getmant_ph(U, X, B, C) \
> - ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> - (int)(((C)<<2) | (B)), \
> - (__v8hf)(__m128h)_mm_setzero_ph (), \
> - (__mmask8)(U)))
> +#define _mm256_getmant_ph(X, B, C) \
> + ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> + (int)(((C)<<2) | (B)), \
> + (__v16hf)(__m256h)_mm256_setzero_ph (), \
> + (__mmask16)-1))
> +
> +#define _mm256_mask_getmant_ph(W, U, X, B, C) \
> + ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> + (int)(((C)<<2) | (B)), \
> + (__v16hf)(__m256h)(W), \
> + (__mmask16)(U)))
> +
> +#define _mm256_maskz_getmant_ph(U, X, B, C) \
> + ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> + (int)(((C)<<2) | (B)), \
> + (__v16hf)(__m256h)_mm256_setzero_ph (), \
> + (__mmask16)(U)))
> +
> +#define _mm_getmant_ph(X, B, C) \
> + ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> + (int)(((C)<<2) | (B)), \
> + (__v8hf)(__m128h)_mm_setzero_ph (), \
> + (__mmask8)-1))
> +
> +#define _mm_mask_getmant_ph(W, U, X, B, C) \
> + ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> + (int)(((C)<<2) | (B)), \
> + (__v8hf)(__m128h)(W), \
> + (__mmask8)(U)))
> +
> +#define _mm_maskz_getmant_ph(U, X, B, C) \
> + ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> + (int)(((C)<<2) | (B)), \
> + (__v8hf)(__m128h)_mm_setzero_ph (), \
> + (__mmask8)(U)))
>
> #endif /* __OPTIMIZE__ */
>
> diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
> index bfa1d56a7b8..10f6fd87cbb 100644
> --- a/gcc/config/i386/i386-builtin.def
> +++ b/gcc/config/i386/i386-builtin.def
> @@ -2775,49 +2775,49 @@ BDESC (0, OPTION_MASK_ISA2_AVX512BF16, CODE_FOR_avx512f_dpbf16ps_v4sf_mask, "__b
> BDESC (0, OPTION_MASK_ISA2_AVX512BF16, CODE_FOR_avx512f_dpbf16ps_v4sf_maskz, "__builtin_ia32_dpbf16ps_v4sf_maskz", IX86_BUILTIN_DPHI16PS_V4SF_MASKZ, UNKNOWN, (int) V4SF_FTYPE_V4SF_V8HI_V8HI_UQI)
>
> /* AVX512FP16. */
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv8hf3_mask, "__builtin_ia32_vaddph_v8hf_mask", IX86_BUILTIN_VADDPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv16hf3_mask, "__builtin_ia32_vaddph_v16hf_mask", IX86_BUILTIN_VADDPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask, "__builtin_ia32_vaddph_v32hf_mask", IX86_BUILTIN_VADDPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv8hf3_mask, "__builtin_ia32_vsubph_v8hf_mask", IX86_BUILTIN_VSUBPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv16hf3_mask, "__builtin_ia32_vsubph_v16hf_mask", IX86_BUILTIN_VSUBPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask, "__builtin_ia32_vsubph_v32hf_mask", IX86_BUILTIN_VSUBPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv8hf3_mask, "__builtin_ia32_vmulph_v8hf_mask", IX86_BUILTIN_VMULPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv16hf3_mask, "__builtin_ia32_vmulph_v16hf_mask", IX86_BUILTIN_VMULPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask, "__builtin_ia32_vmulph_v32hf_mask", IX86_BUILTIN_VMULPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv8hf3_mask, "__builtin_ia32_vdivph_v8hf_mask", IX86_BUILTIN_VDIVPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv16hf3_mask, "__builtin_ia32_vdivph_v16hf_mask", IX86_BUILTIN_VDIVPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask, "__builtin_ia32_vdivph_v32hf_mask", IX86_BUILTIN_VDIVPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask, "__builtin_ia32_vaddsh_v8hf_mask", IX86_BUILTIN_VADDSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask, "__builtin_ia32_vsubsh_v8hf_mask", IX86_BUILTIN_VSUBSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask, "__builtin_ia32_vmulsh_v8hf_mask", IX86_BUILTIN_VMULSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask, "__builtin_ia32_vdivsh_v8hf_mask", IX86_BUILTIN_VDIVSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv8hf3_mask, "__builtin_ia32_vmaxph_v8hf_mask", IX86_BUILTIN_VMAXPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv16hf3_mask, "__builtin_ia32_vmaxph_v16hf_mask", IX86_BUILTIN_VMAXPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask, "__builtin_ia32_vmaxph_v32hf_mask", IX86_BUILTIN_VMAXPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv8hf3_mask, "__builtin_ia32_vminph_v8hf_mask", IX86_BUILTIN_VMINPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv16hf3_mask, "__builtin_ia32_vminph_v16hf_mask", IX86_BUILTIN_VMINPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask, "__builtin_ia32_vminph_v32hf_mask", IX86_BUILTIN_VMINPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask, "__builtin_ia32_vmaxsh_v8hf_mask", IX86_BUILTIN_VMAXSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask, "__builtin_ia32_vminsh_v8hf_mask", IX86_BUILTIN_VMINSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_cmpv8hf3_mask, "__builtin_ia32_vcmpph_v8hf_mask", IX86_BUILTIN_VCMPPH_V8HF_MASK, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_cmpv16hf3_mask, "__builtin_ia32_vcmpph_v16hf_mask", IX86_BUILTIN_VCMPPH_V16HF_MASK, UNKNOWN, (int) UHI_FTYPE_V16HF_V16HF_INT_UHI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask, "__builtin_ia32_vcmpph_v32hf_mask", IX86_BUILTIN_VCMPPH_V32HF_MASK, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv8hf2_mask, "__builtin_ia32_vsqrtph_v8hf_mask", IX86_BUILTIN_VSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv16hf2_mask, "__builtin_ia32_vsqrtph_v16hf_mask", IX86_BUILTIN_VSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv8hf2_mask, "__builtin_ia32_vrsqrtph_v8hf_mask", IX86_BUILTIN_VRSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv16hf2_mask, "__builtin_ia32_vrsqrtph_v16hf_mask", IX86_BUILTIN_VRSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv32hf2_mask, "__builtin_ia32_vrsqrtph_v32hf_mask", IX86_BUILTIN_VRSQRTPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrsqrtv8hf2_mask, "__builtin_ia32_vrsqrtsh_v8hf_mask", IX86_BUILTIN_VRSQRTSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv8hf2_mask, "__builtin_ia32_vrcpph_v8hf_mask", IX86_BUILTIN_VRCPPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv16hf2_mask, "__builtin_ia32_vrcpph_v16hf_mask", IX86_BUILTIN_VRCPPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv32hf2_mask, "__builtin_ia32_vrcpph_v32hf_mask", IX86_BUILTIN_VRCPPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrcpv8hf2_mask, "__builtin_ia32_vrcpsh_v8hf_mask", IX86_BUILTIN_VRCPSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_scalefv8hf_mask, "__builtin_ia32_vscalefph_v8hf_mask", IX86_BUILTIN_VSCALEFPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_scalefv16hf_mask, "__builtin_ia32_vscalefph_v16hf_mask", IX86_BUILTIN_VSCALEFPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv8hf_mask, "__builtin_ia32_vreduceph_v8hf_mask", IX86_BUILTIN_VREDUCEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv16hf_mask, "__builtin_ia32_vreduceph_v16hf_mask", IX86_BUILTIN_VREDUCEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rndscalev8hf_mask, "__builtin_ia32_vrndscaleph_v8hf_mask", IX86_BUILTIN_VRNDSCALEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
> -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_rndscalev16hf_mask, "__builtin_ia32_vrndscaleph_v16hf_mask", IX86_BUILTIN_VRNDSCALEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv8hf3_mask, "__builtin_ia32_addph128_mask", IX86_BUILTIN_VADDPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv16hf3_mask, "__builtin_ia32_addph256_mask", IX86_BUILTIN_VADDPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask, "__builtin_ia32_addph512_mask", IX86_BUILTIN_VADDPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv8hf3_mask, "__builtin_ia32_subph128_mask", IX86_BUILTIN_VSUBPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv16hf3_mask, "__builtin_ia32_subph256_mask", IX86_BUILTIN_VSUBPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask, "__builtin_ia32_subph512_mask", IX86_BUILTIN_VSUBPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv8hf3_mask, "__builtin_ia32_mulph128_mask", IX86_BUILTIN_VMULPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv16hf3_mask, "__builtin_ia32_mulph256_mask", IX86_BUILTIN_VMULPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask, "__builtin_ia32_mulph512_mask", IX86_BUILTIN_VMULPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv8hf3_mask, "__builtin_ia32_divph128_mask", IX86_BUILTIN_VDIVPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv16hf3_mask, "__builtin_ia32_divph256_mask", IX86_BUILTIN_VDIVPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask, "__builtin_ia32_divph512_mask", IX86_BUILTIN_VDIVPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask, "__builtin_ia32_addsh_mask", IX86_BUILTIN_VADDSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask, "__builtin_ia32_subsh_mask", IX86_BUILTIN_VSUBSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask, "__builtin_ia32_mulsh_mask", IX86_BUILTIN_VMULSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask, "__builtin_ia32_divsh_mask", IX86_BUILTIN_VDIVSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv8hf3_mask, "__builtin_ia32_maxph128_mask", IX86_BUILTIN_VMAXPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv16hf3_mask, "__builtin_ia32_maxph256_mask", IX86_BUILTIN_VMAXPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask, "__builtin_ia32_maxph512_mask", IX86_BUILTIN_VMAXPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv8hf3_mask, "__builtin_ia32_minph128_mask", IX86_BUILTIN_VMINPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv16hf3_mask, "__builtin_ia32_minph256_mask", IX86_BUILTIN_VMINPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask, "__builtin_ia32_minph512_mask", IX86_BUILTIN_VMINPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask, "__builtin_ia32_maxsh_mask", IX86_BUILTIN_VMAXSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask, "__builtin_ia32_minsh_mask", IX86_BUILTIN_VMINSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_cmpv8hf3_mask, "__builtin_ia32_cmpph128_mask", IX86_BUILTIN_VCMPPH_V8HF_MASK, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_cmpv16hf3_mask, "__builtin_ia32_cmpph256_mask", IX86_BUILTIN_VCMPPH_V16HF_MASK, UNKNOWN, (int) UHI_FTYPE_V16HF_V16HF_INT_UHI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask, "__builtin_ia32_cmpph512_mask", IX86_BUILTIN_VCMPPH_V32HF_MASK, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv8hf2_mask, "__builtin_ia32_sqrtph128_mask", IX86_BUILTIN_VSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv16hf2_mask, "__builtin_ia32_sqrtph256_mask", IX86_BUILTIN_VSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv8hf2_mask, "__builtin_ia32_rsqrtph128_mask", IX86_BUILTIN_VRSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv16hf2_mask, "__builtin_ia32_rsqrtph256_mask", IX86_BUILTIN_VRSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv32hf2_mask, "__builtin_ia32_rsqrtph512_mask", IX86_BUILTIN_VRSQRTPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrsqrtv8hf2_mask, "__builtin_ia32_rsqrtsh_mask", IX86_BUILTIN_VRSQRTSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv8hf2_mask, "__builtin_ia32_rcpph128_mask", IX86_BUILTIN_VRCPPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv16hf2_mask, "__builtin_ia32_rcpph256_mask", IX86_BUILTIN_VRCPPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv32hf2_mask, "__builtin_ia32_rcpph512_mask", IX86_BUILTIN_VRCPPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrcpv8hf2_mask, "__builtin_ia32_rcpsh_mask", IX86_BUILTIN_VRCPSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_scalefv8hf_mask, "__builtin_ia32_scalefph128_mask", IX86_BUILTIN_VSCALEFPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_scalefv16hf_mask, "__builtin_ia32_scalefph256_mask", IX86_BUILTIN_VSCALEFPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv8hf_mask, "__builtin_ia32_reduceph128_mask", IX86_BUILTIN_VREDUCEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv16hf_mask, "__builtin_ia32_reduceph256_mask", IX86_BUILTIN_VREDUCEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rndscalev8hf_mask, "__builtin_ia32_rndscaleph128_mask", IX86_BUILTIN_VRNDSCALEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
> +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_rndscalev16hf_mask, "__builtin_ia32_rndscaleph256_mask", IX86_BUILTIN_VRNDSCALEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
> BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512dq_fpclassv16hf_mask, "__builtin_ia32_fpclassph256_mask", IX86_BUILTIN_FPCLASSPH256, UNKNOWN, (int) HI_FTYPE_V16HF_INT_UHI)
> BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512dq_fpclassv8hf_mask, "__builtin_ia32_fpclassph128_mask", IX86_BUILTIN_FPCLASSPH128, UNKNOWN, (int) QI_FTYPE_V8HF_INT_UQI)
> BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512dq_fpclassv32hf_mask, "__builtin_ia32_fpclassph512_mask", IX86_BUILTIN_FPCLASSPH512, UNKNOWN, (int) SI_FTYPE_V32HF_INT_USI)
> @@ -3027,28 +3027,28 @@ BDESC (OPTION_MASK_ISA_AVX512DQ, 0, CODE_FOR_avx512dq_rangepv16sf_mask_round, "_
> BDESC (OPTION_MASK_ISA_AVX512DQ, 0, CODE_FOR_avx512dq_rangepv8df_mask_round, "__builtin_ia32_rangepd512_mask", IX86_BUILTIN_RANGEPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_INT_V8DF_QI_INT)
>
> /* AVX512FP16. */
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask_round, "__builtin_ia32_vaddph_v32hf_mask_round", IX86_BUILTIN_VADDPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask_round, "__builtin_ia32_vsubph_v32hf_mask_round", IX86_BUILTIN_VSUBPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask_round, "__builtin_ia32_vmulph_v32hf_mask_round", IX86_BUILTIN_VMULPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask_round, "__builtin_ia32_vdivph_v32hf_mask_round", IX86_BUILTIN_VDIVPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask_round, "__builtin_ia32_vaddsh_v8hf_mask_round", IX86_BUILTIN_VADDSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask_round, "__builtin_ia32_vsubsh_v8hf_mask_round", IX86_BUILTIN_VSUBSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask_round, "__builtin_ia32_vmulsh_v8hf_mask_round", IX86_BUILTIN_VMULSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask_round, "__builtin_ia32_vdivsh_v8hf_mask_round", IX86_BUILTIN_VDIVSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask_round, "__builtin_ia32_vmaxph_v32hf_mask_round", IX86_BUILTIN_VMAXPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask_round, "__builtin_ia32_vminph_v32hf_mask_round", IX86_BUILTIN_VMINPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask_round, "__builtin_ia32_vmaxsh_v8hf_mask_round", IX86_BUILTIN_VMAXSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask_round, "__builtin_ia32_vminsh_v8hf_mask_round", IX86_BUILTIN_VMINSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask_round, "__builtin_ia32_vcmpph_v32hf_mask_round", IX86_BUILTIN_VCMPPH_V32HF_MASK_ROUND, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmcmpv8hf3_mask_round, "__builtin_ia32_vcmpsh_v8hf_mask_round", IX86_BUILTIN_VCMPSH_V8HF_MASK_ROUND, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv32hf2_mask_round, "__builtin_ia32_vsqrtph_v32hf_mask_round", IX86_BUILTIN_VSQRTPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsqrtv8hf2_mask_round, "__builtin_ia32_vsqrtsh_v8hf_mask_round", IX86_BUILTIN_VSQRTSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_scalefv32hf_mask_round, "__builtin_ia32_vscalefph_v32hf_mask_round", IX86_BUILTIN_VSCALEFPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmscalefv8hf_mask_round, "__builtin_ia32_vscalefsh_v8hf_mask_round", IX86_BUILTIN_VSCALEFSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv32hf_mask_round, "__builtin_ia32_vreduceph_v32hf_mask_round", IX86_BUILTIN_VREDUCEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducesv8hf_mask_round, "__builtin_ia32_vreducesh_v8hf_mask_round", IX86_BUILTIN_VREDUCESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_rndscalev32hf_mask_round, "__builtin_ia32_vrndscaleph_v32hf_mask_round", IX86_BUILTIN_VRNDSCALEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
> -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_rndscalev8hf_mask_round, "__builtin_ia32_vrndscalesh_v8hf_mask_round", IX86_BUILTIN_VRNDSCALESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask_round, "__builtin_ia32_addph512_mask_round", IX86_BUILTIN_VADDPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask_round, "__builtin_ia32_subph512_mask_round", IX86_BUILTIN_VSUBPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask_round, "__builtin_ia32_mulph512_mask_round", IX86_BUILTIN_VMULPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask_round, "__builtin_ia32_divph512_mask_round", IX86_BUILTIN_VDIVPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask_round, "__builtin_ia32_addsh_mask_round", IX86_BUILTIN_VADDSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask_round, "__builtin_ia32_subsh_mask_round", IX86_BUILTIN_VSUBSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask_round, "__builtin_ia32_mulsh_mask_round", IX86_BUILTIN_VMULSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask_round, "__builtin_ia32_divsh_mask_round", IX86_BUILTIN_VDIVSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask_round, "__builtin_ia32_maxph512_mask_round", IX86_BUILTIN_VMAXPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask_round, "__builtin_ia32_minph512_mask_round", IX86_BUILTIN_VMINPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask_round, "__builtin_ia32_maxsh_mask_round", IX86_BUILTIN_VMAXSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask_round, "__builtin_ia32_minsh_mask_round", IX86_BUILTIN_VMINSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask_round, "__builtin_ia32_cmpph512_mask_round", IX86_BUILTIN_VCMPPH_V32HF_MASK_ROUND, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmcmpv8hf3_mask_round, "__builtin_ia32_cmpsh_mask_round", IX86_BUILTIN_VCMPSH_V8HF_MASK_ROUND, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv32hf2_mask_round, "__builtin_ia32_sqrtph512_mask_round", IX86_BUILTIN_VSQRTPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsqrtv8hf2_mask_round, "__builtin_ia32_sqrtsh_mask_round", IX86_BUILTIN_VSQRTSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_scalefv32hf_mask_round, "__builtin_ia32_scalefph512_mask_round", IX86_BUILTIN_VSCALEFPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmscalefv8hf_mask_round, "__builtin_ia32_scalefsh_mask_round", IX86_BUILTIN_VSCALEFSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv32hf_mask_round, "__builtin_ia32_reduceph512_mask_round", IX86_BUILTIN_VREDUCEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducesv8hf_mask_round, "__builtin_ia32_reducesh_mask_round", IX86_BUILTIN_VREDUCESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_rndscalev32hf_mask_round, "__builtin_ia32_rndscaleph512_mask_round", IX86_BUILTIN_VRNDSCALEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
> +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_rndscalev8hf_mask_round, "__builtin_ia32_rndscalesh_mask_round", IX86_BUILTIN_VRNDSCALESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
> BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_getexpv32hf_mask_round, "__builtin_ia32_getexpph512_mask", IX86_BUILTIN_GETEXPPH512, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI_INT)
> BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_sgetexpv8hf_mask_round, "__builtin_ia32_getexpsh_mask_round", IX86_BUILTIN_GETEXPSH_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_getmantv32hf_mask_round, "__builtin_ia32_getmantph512_mask", IX86_BUILTIN_GETMANTPH512, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
> diff --git a/gcc/testsuite/gcc.target/i386/avx-1.c b/gcc/testsuite/gcc.target/i386/avx-1.c
> index b3cffa0644f..3a96e586418 100644
> --- a/gcc/testsuite/gcc.target/i386/avx-1.c
> +++ b/gcc/testsuite/gcc.target/i386/avx-1.c
> @@ -686,33 +686,33 @@
> #define __builtin_ia32_vpshld_v2di_mask(A, B, C, D, E) __builtin_ia32_vpshld_v2di_mask(A, B, 1, D, E)
>
> /* avx512fp16intrin.h */
> -#define __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vcmpph_v32hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v32hf_mask(A, B, 1, D)
> -#define __builtin_ia32_vcmpph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpph_v32hf_mask_round(A, B, 1, D, 8)
> -#define __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, 1, D, 8)
> -#define __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, D) __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, 8)
> -#define __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, E) __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, 8)
> -#define __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vreduceph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vreduceph_v32hf_mask_round(A, 123, C, D, 8)
> -#define __builtin_ia32_vreduceph_v8hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v8hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vreduceph_v16hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v16hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vreducesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vreducesh_v8hf_mask_round(A, B, 123, D, E, 8)
> -#define __builtin_ia32_vrndscaleph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vrndscaleph_v32hf_mask_round(A, 123, C, D, 8)
> -#define __builtin_ia32_vrndscaleph_v8hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v8hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vrndscaleph_v16hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v16hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, 123, D, E, 8)
> +#define __builtin_ia32_addph512_mask_round(A, B, C, D, E) __builtin_ia32_addph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_subph512_mask_round(A, B, C, D, E) __builtin_ia32_subph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_mulph512_mask_round(A, B, C, D, E) __builtin_ia32_mulph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_divph512_mask_round(A, B, C, D, E) __builtin_ia32_divph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_addsh_mask_round(A, B, C, D, E) __builtin_ia32_addsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_subsh_mask_round(A, B, C, D, E) __builtin_ia32_subsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_mulsh_mask_round(A, B, C, D, E) __builtin_ia32_mulsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_divsh_mask_round(A, B, C, D, E) __builtin_ia32_divsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_maxph512_mask_round(A, B, C, D, E) __builtin_ia32_maxph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_minph512_mask_round(A, B, C, D, E) __builtin_ia32_minph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_maxsh_mask_round(A, B, C, D, E) __builtin_ia32_maxsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_minsh_mask_round(A, B, C, D, E) __builtin_ia32_minsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_cmpph512_mask(A, B, C, D) __builtin_ia32_cmpph512_mask(A, B, 1, D)
> +#define __builtin_ia32_cmpph512_mask_round(A, B, C, D, E) __builtin_ia32_cmpph512_mask_round(A, B, 1, D, 8)
> +#define __builtin_ia32_cmpsh_mask_round(A, B, C, D, E) __builtin_ia32_cmpsh_mask_round(A, B, 1, D, 8)
> +#define __builtin_ia32_sqrtph512_mask_round(C, A, B, D) __builtin_ia32_sqrtph512_mask_round(C, A, B, 8)
> +#define __builtin_ia32_sqrtsh_mask_round(D, C, A, B, E) __builtin_ia32_sqrtsh_mask_round(D, C, A, B, 8)
> +#define __builtin_ia32_scalefph512_mask_round(A, B, C, D, E) __builtin_ia32_scalefph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_scalefsh_mask_round(A, B, C, D, E) __builtin_ia32_scalefsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_reduceph512_mask_round(A, B, C, D, E) __builtin_ia32_reduceph512_mask_round(A, 123, C, D, 8)
> +#define __builtin_ia32_reduceph128_mask(A, B, C, D) __builtin_ia32_reduceph128_mask(A, 123, C, D)
> +#define __builtin_ia32_reduceph256_mask(A, B, C, D) __builtin_ia32_reduceph256_mask(A, 123, C, D)
> +#define __builtin_ia32_reducesh_mask_round(A, B, C, D, E, F) __builtin_ia32_reducesh_mask_round(A, B, 123, D, E, 8)
> +#define __builtin_ia32_rndscaleph512_mask_round(A, B, C, D, E) __builtin_ia32_rndscaleph512_mask_round(A, 123, C, D, 8)
> +#define __builtin_ia32_rndscaleph128_mask(A, B, C, D) __builtin_ia32_rndscaleph128_mask(A, 123, C, D)
> +#define __builtin_ia32_rndscaleph256_mask(A, B, C, D) __builtin_ia32_rndscaleph256_mask(A, 123, C, D)
> +#define __builtin_ia32_rndscalesh_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesh_mask_round(A, B, 123, D, E, 8)
> #define __builtin_ia32_fpclassph512_mask(A, D, C) __builtin_ia32_fpclassph512_mask(A, 1, C)
> #define __builtin_ia32_fpclasssh_mask(A, D, U) __builtin_ia32_fpclasssh_mask(A, 1, U)
> #define __builtin_ia32_getexpph512_mask(A, B, C, D) __builtin_ia32_getexpph512_mask(A, B, C, 8)
> @@ -721,8 +721,8 @@
> #define __builtin_ia32_getmantsh_mask_round(A, B, C, W, U, D) __builtin_ia32_getmantsh_mask_round(A, B, 1, W, U, 4)
>
> /* avx512fp16vlintrin.h */
> -#define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
> -#define __builtin_ia32_vcmpph_v16hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v16hf_mask(A, B, 1, D)
> +#define __builtin_ia32_cmpph128_mask(A, B, C, D) __builtin_ia32_cmpph128_mask(A, B, 1, D)
> +#define __builtin_ia32_cmpph256_mask(A, B, C, D) __builtin_ia32_cmpph256_mask(A, B, 1, D)
> #define __builtin_ia32_fpclassph256_mask(A, D, C) __builtin_ia32_fpclassph256_mask(A, 1, C)
> #define __builtin_ia32_fpclassph128_mask(A, D, C) __builtin_ia32_fpclassph128_mask(A, 1, C)
> #define __builtin_ia32_getmantph256_mask(A, E, C, D) __builtin_ia32_getmantph256_mask(A, 1, C, D)
> diff --git a/gcc/testsuite/gcc.target/i386/sse-13.c b/gcc/testsuite/gcc.target/i386/sse-13.c
> index 67ef567e437..aafcd414530 100644
> --- a/gcc/testsuite/gcc.target/i386/sse-13.c
> +++ b/gcc/testsuite/gcc.target/i386/sse-13.c
> @@ -703,33 +703,33 @@
> #define __builtin_ia32_vpshld_v2di_mask(A, B, C, D, E) __builtin_ia32_vpshld_v2di_mask(A, B, 1, D, E)
>
> /* avx512fp16intrin.h */
> -#define __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vcmpph_v32hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v32hf_mask(A, B, 1, D)
> -#define __builtin_ia32_vcmpph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpph_v32hf_mask_round(A, B, 1, D, 8)
> -#define __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, 1, D, 8)
> -#define __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, D) __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, 8)
> -#define __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, E) __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, 8)
> -#define __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vreduceph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vreduceph_v32hf_mask_round(A, 123, C, D, 8)
> -#define __builtin_ia32_vreduceph_v8hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v8hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vreduceph_v16hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v16hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vreducesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vreducesh_v8hf_mask_round(A, B, 123, D, E, 8)
> -#define __builtin_ia32_vrndscaleph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vrndscaleph_v32hf_mask_round(A, 123, C, D, 8)
> -#define __builtin_ia32_vrndscaleph_v8hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v8hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vrndscaleph_v16hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v16hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, 123, D, E, 8)
> +#define __builtin_ia32_addph512_mask_round(A, B, C, D, E) __builtin_ia32_addph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_subph512_mask_round(A, B, C, D, E) __builtin_ia32_subph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_mulph512_mask_round(A, B, C, D, E) __builtin_ia32_mulph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_divph512_mask_round(A, B, C, D, E) __builtin_ia32_divph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_addsh_mask_round(A, B, C, D, E) __builtin_ia32_addsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_subsh_mask_round(A, B, C, D, E) __builtin_ia32_subsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_mulsh_mask_round(A, B, C, D, E) __builtin_ia32_mulsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_divsh_mask_round(A, B, C, D, E) __builtin_ia32_divsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_maxph512_mask_round(A, B, C, D, E) __builtin_ia32_maxph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_minph512_mask_round(A, B, C, D, E) __builtin_ia32_minph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_maxsh_mask_round(A, B, C, D, E) __builtin_ia32_maxsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_minsh_mask_round(A, B, C, D, E) __builtin_ia32_minsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_cmpph512_mask(A, B, C, D) __builtin_ia32_cmpph512_mask(A, B, 1, D)
> +#define __builtin_ia32_cmpph512_mask_round(A, B, C, D, E) __builtin_ia32_cmpph512_mask_round(A, B, 1, D, 8)
> +#define __builtin_ia32_cmpsh_mask_round(A, B, C, D, E) __builtin_ia32_cmpsh_mask_round(A, B, 1, D, 8)
> +#define __builtin_ia32_sqrtph512_mask_round(C, A, B, D) __builtin_ia32_sqrtph512_mask_round(C, A, B, 8)
> +#define __builtin_ia32_sqrtsh_mask_round(D, C, A, B, E) __builtin_ia32_sqrtsh_mask_round(D, C, A, B, 8)
> +#define __builtin_ia32_scalefph512_mask_round(A, B, C, D, E) __builtin_ia32_scalefph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_scalefsh_mask_round(A, B, C, D, E) __builtin_ia32_scalefsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_reduceph512_mask_round(A, B, C, D, E) __builtin_ia32_reduceph512_mask_round(A, 123, C, D, 8)
> +#define __builtin_ia32_reduceph128_mask(A, B, C, D) __builtin_ia32_reduceph128_mask(A, 123, C, D)
> +#define __builtin_ia32_reduceph256_mask(A, B, C, D) __builtin_ia32_reduceph256_mask(A, 123, C, D)
> +#define __builtin_ia32_reducesh_mask_round(A, B, C, D, E, F) __builtin_ia32_reducesh_mask_round(A, B, 123, D, E, 8)
> +#define __builtin_ia32_rndscaleph512_mask_round(A, B, C, D, E) __builtin_ia32_rndscaleph512_mask_round(A, 123, C, D, 8)
> +#define __builtin_ia32_rndscaleph128_mask(A, B, C, D) __builtin_ia32_rndscaleph128_mask(A, 123, C, D)
> +#define __builtin_ia32_rndscaleph256_mask(A, B, C, D) __builtin_ia32_rndscaleph256_mask(A, 123, C, D)
> +#define __builtin_ia32_rndscalesh_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesh_mask_round(A, B, 123, D, E, 8)
> #define __builtin_ia32_fpclassph512_mask(A, D, C) __builtin_ia32_fpclassph512_mask(A, 1, C)
> #define __builtin_ia32_fpclasssh_mask(A, D, U) __builtin_ia32_fpclasssh_mask(A, 1, U)
> #define __builtin_ia32_getexpph512_mask(A, B, C, D) __builtin_ia32_getexpph512_mask(A, B, C, 8)
> @@ -738,8 +738,8 @@
> #define __builtin_ia32_getmantsh_mask_round(A, B, C, W, U, D) __builtin_ia32_getmantsh_mask_round(A, B, 1, W, U, 4)
>
> /* avx512fp16vlintrin.h */
> -#define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
> -#define __builtin_ia32_vcmpph_v16hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v16hf_mask(A, B, 1, D)
> +#define __builtin_ia32_cmpph128_mask(A, B, C, D) __builtin_ia32_cmpph128_mask(A, B, 1, D)
> +#define __builtin_ia32_cmpph256_mask(A, B, C, D) __builtin_ia32_cmpph256_mask(A, B, 1, D)
> #define __builtin_ia32_fpclassph256_mask(A, D, C) __builtin_ia32_fpclassph256_mask(A, 1, C)
> #define __builtin_ia32_fpclassph128_mask(A, D, C) __builtin_ia32_fpclassph128_mask(A, 1, C)
> #define __builtin_ia32_getmantph256_mask(A, E, C, D) __builtin_ia32_getmantph256_mask(A, 1, C, D)
> diff --git a/gcc/testsuite/gcc.target/i386/sse-23.c b/gcc/testsuite/gcc.target/i386/sse-23.c
> index b3f07587acb..8b600282c67 100644
> --- a/gcc/testsuite/gcc.target/i386/sse-23.c
> +++ b/gcc/testsuite/gcc.target/i386/sse-23.c
> @@ -704,33 +704,33 @@
> #define __builtin_ia32_vpshld_v2di_mask(A, B, C, D, E) __builtin_ia32_vpshld_v2di_mask(A, B, 1, D, E)
>
> /* avx512fp16intrin.h */
> -#define __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vcmpph_v32hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v32hf_mask(A, B, 1, D)
> -#define __builtin_ia32_vcmpph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpph_v32hf_mask_round(A, B, 1, D, 8)
> -#define __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, 1, D, 8)
> -#define __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, D) __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, 8)
> -#define __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, E) __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, 8)
> -#define __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, 8)
> -#define __builtin_ia32_vreduceph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vreduceph_v32hf_mask_round(A, 123, C, D, 8)
> -#define __builtin_ia32_vreduceph_v8hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v8hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vreduceph_v16hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v16hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vreducesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vreducesh_v8hf_mask_round(A, B, 123, D, E, 8)
> -#define __builtin_ia32_vrndscaleph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vrndscaleph_v32hf_mask_round(A, 123, C, D, 8)
> -#define __builtin_ia32_vrndscaleph_v8hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v8hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vrndscaleph_v16hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v16hf_mask(A, 123, C, D)
> -#define __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, 123, D, E, 8)
> +#define __builtin_ia32_addph512_mask_round(A, B, C, D, E) __builtin_ia32_addph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_subph512_mask_round(A, B, C, D, E) __builtin_ia32_subph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_mulph512_mask_round(A, B, C, D, E) __builtin_ia32_mulph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_divph512_mask_round(A, B, C, D, E) __builtin_ia32_divph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_addsh_mask_round(A, B, C, D, E) __builtin_ia32_addsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_subsh_mask_round(A, B, C, D, E) __builtin_ia32_subsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_mulsh_mask_round(A, B, C, D, E) __builtin_ia32_mulsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_divsh_mask_round(A, B, C, D, E) __builtin_ia32_divsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_maxph512_mask_round(A, B, C, D, E) __builtin_ia32_maxph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_minph512_mask_round(A, B, C, D, E) __builtin_ia32_minph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_maxsh_mask_round(A, B, C, D, E) __builtin_ia32_maxsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_minsh_mask_round(A, B, C, D, E) __builtin_ia32_minsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_cmpph512_mask(A, B, C, D) __builtin_ia32_cmpph512_mask(A, B, 1, D)
> +#define __builtin_ia32_cmpph512_mask_round(A, B, C, D, E) __builtin_ia32_cmpph512_mask_round(A, B, 1, D, 8)
> +#define __builtin_ia32_cmpsh_mask_round(A, B, C, D, E) __builtin_ia32_cmpsh_mask_round(A, B, 1, D, 8)
> +#define __builtin_ia32_sqrtph512_mask_round(C, A, B, D) __builtin_ia32_sqrtph512_mask_round(C, A, B, 8)
> +#define __builtin_ia32_sqrtsh_mask_round(D, C, A, B, E) __builtin_ia32_sqrtsh_mask_round(D, C, A, B, 8)
> +#define __builtin_ia32_scalefph512_mask_round(A, B, C, D, E) __builtin_ia32_scalefph512_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_scalefsh_mask_round(A, B, C, D, E) __builtin_ia32_scalefsh_mask_round(A, B, C, D, 8)
> +#define __builtin_ia32_reduceph512_mask_round(A, B, C, D, E) __builtin_ia32_reduceph512_mask_round(A, 123, C, D, 8)
> +#define __builtin_ia32_reduceph128_mask(A, B, C, D) __builtin_ia32_reduceph128_mask(A, 123, C, D)
> +#define __builtin_ia32_reduceph256_mask(A, B, C, D) __builtin_ia32_reduceph256_mask(A, 123, C, D)
> +#define __builtin_ia32_reducesh_mask_round(A, B, C, D, E, F) __builtin_ia32_reducesh_mask_round(A, B, 123, D, E, 8)
> +#define __builtin_ia32_rndscaleph512_mask_round(A, B, C, D, E) __builtin_ia32_rndscaleph512_mask_round(A, 123, C, D, 8)
> +#define __builtin_ia32_rndscaleph128_mask(A, B, C, D) __builtin_ia32_rndscaleph128_mask(A, 123, C, D)
> +#define __builtin_ia32_rndscaleph256_mask(A, B, C, D) __builtin_ia32_rndscaleph256_mask(A, 123, C, D)
> +#define __builtin_ia32_rndscalesh_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesh_mask_round(A, B, 123, D, E, 8)
> #define __builtin_ia32_fpclassph512_mask(A, D, C) __builtin_ia32_fpclassph512_mask(A, 1, C)
> #define __builtin_ia32_fpclasssh_mask(A, D, U) __builtin_ia32_fpclasssh_mask(A, 1, U)
> #define __builtin_ia32_getexpph512_mask(A, B, C, D) __builtin_ia32_getexpph512_mask(A, B, C, 8)
> @@ -739,8 +739,8 @@
> #define __builtin_ia32_getmantsh_mask_round(A, B, C, W, U, D) __builtin_ia32_getmantsh_mask_round(A, B, 1, W, U, 4)
>
> /* avx512fp16vlintrin.h */
> -#define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
> -#define __builtin_ia32_vcmpph_v16hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v16hf_mask(A, B, 1, D)
> +#define __builtin_ia32_cmpph128_mask(A, B, C, D) __builtin_ia32_cmpph128_mask(A, B, 1, D)
> +#define __builtin_ia32_cmpph256_mask(A, B, C, D) __builtin_ia32_cmpph256_mask(A, B, 1, D)
> #define __builtin_ia32_fpclassph256_mask(A, D, C) __builtin_ia32_fpclassph256_mask(A, 1, C)
> #define __builtin_ia32_fpclassph128_mask(A, D, C) __builtin_ia32_fpclassph128_mask(A, 1, C)
> #define __builtin_ia32_getmantph256_mask(A, E, C, D) __builtin_ia32_getmantph256_mask(A, 1, C, D)
> --
> 2.18.1
>
On Wed, Sep 15, 2021 at 5:52 PM Hongyu Wang <wwwhhhyyy333@gmail.com> wrote:
>
> Sorry for missing that part.
>
> Updated patch.
Ok, thanks.
>
> Hongtao Liu via Gcc-patches <gcc-patches@gcc.gnu.org> 于2021年9月15日周三 下午5:16写道：
> >
> > On Wed, Sep 15, 2021 at 5:08 PM Hongyu Wang via Gcc-patches
> > <gcc-patches@gcc.gnu.org> wrote:
> > >
> > > Hi,
> > >
> > > For AVX512FP16 builtins, they all contain format like vaddph_v8hf,
> > > while AVX512F builtins use addps128 which succeeded SSE/AVX style.
> > > Adjust AVX512FP16 builtins to match such format.
> > >
> > > Bootstraped/regtested on x86-64-*-linux, ok for master?
> > >
> > > gcc/ChangeLog:
> > >
> > > * config/i386/avx512fp16intrin.h: Adjust all builtin calls.
> > > * config/i386/avx512fp16vlintrin.h: Likewise.
> > > * config/i386/i386-builtin.def: Adjust builtin name to match
> > > AVX512F style.
> > >
> >
> > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_vmsmaxv8hf3_mask, "__builtin_ia32_maxsh_mask",
> > IX86_BUILTIN_VMAXSH_V8HF_MASK, UNKNOWN, (int)
> > V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_vmsminv8hf3_mask, "__builtin_ia32_minsh_mask",
> > IX86_BUILTIN_VMINSH_V8HF_MASK, UNKNOWN, (int)
> > V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_cmpv8hf3_mask, "__builtin_ia32_cmpph128_mask",
> > IX86_BUILTIN_VCMPPH_V8HF_MASK, UNKNOWN, (int)
> > UQI_FTYPE_V8HF_V8HF_INT_UQI)
> > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512vl_cmpv16hf3_mask, "__builtin_ia32_cmpph256_mask",
> > IX86_BUILTIN_VCMPPH_V16HF_MASK, UNKNOWN, (int)
> > UHI_FTYPE_V16HF_V16HF_INT_UHI)
> > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512bw_cmpv32hf3_mask, "__builtin_ia32_cmpph512_mask",
> > IX86_BUILTIN_VCMPPH_V32HF_MASK, UNKNOWN, (int)
> > USI_FTYPE_V32HF_V32HF_INT_USI)
> > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_sqrtv8hf2_mask, "__builtin_ia32_sqrtph128_mask",
> > IX86_BUILTIN_VSQRTPH_V8HF_MASK, UNKNOWN, (int)
> > V8HF_FTYPE_V8HF_V8HF_UQI)
> > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_sqrtv16hf2_mask, "__builtin_ia32_sqrtph256_mask",
> > IX86_BUILTIN_VSQRTPH_V16HF_MASK, UNKNOWN, (int)
> > V16HF_FTYPE_V16HF_V16HF_UHI)
> > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_rsqrtv8hf2_mask, "__builtin_ia32_rsqrtph128_mask",
> > IX86_BUILTIN_VRSQRTPH_V8HF_MASK, UNKNOWN, (int)
> > V8HF_FTYPE_V8HF_V8HF_UQI)
> > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_rsqrtv16hf2_mask,
> > "__builtin_ia32_rsqrtph256_mask", IX86_BUILTIN_VRSQRTPH_V16HF_MASK,
> > UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_rsqrtv32hf2_mask,
> > "__builtin_ia32_rsqrtph512_mask", IX86_BUILTIN_VRSQRTPH_V32HF_MASK,
> > UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
> > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_vmrsqrtv8hf2_mask, "__builtin_ia32_rsqrtsh_mask",
> > IX86_BUILTIN_VRSQRTSH_V8HF_MASK, UNKNOWN, (int)
> > V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_rcpv8hf2_mask, "__builtin_ia32_rcpph128_mask",
> > IX86_BUILTIN_VRCPPH_V8HF_MASK, UNKNOWN, (int)
> > V8HF_FTYPE_V8HF_V8HF_UQI)
> > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_rcpv16hf2_mask, "__builtin_ia32_rcpph256_mask",
> > IX86_BUILTIN_VRCPPH_V16HF_MASK, UNKNOWN, (int)
> > V16HF_FTYPE_V16HF_V16HF_UHI)
> > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_rcpv32hf2_mask, "__builtin_ia32_rcpph512_mask",
> > IX86_BUILTIN_VRCPPH_V32HF_MASK, UNKNOWN, (int)
> > V32HF_FTYPE_V32HF_V32HF_USI)
> > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_vmrcpv8hf2_mask, "__builtin_ia32_rcpsh_mask",
> > IX86_BUILTIN_VRCPSH_V8HF_MASK, UNKNOWN, (int)
> > V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512fp16_scalefv8hf_mask,
> > "__builtin_ia32_scalefph128_mask", IX86_BUILTIN_VSCALEFPH_V8HF_MASK,
> > UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16,
> > CODE_FOR_avx512vl_scalefv16hf_mask, "__builtin_ia32_scalefph256_mask",
> > IX86_BUILTIN_VSCALEFPH_V16HF_MASK, UNKNOWN, (int)
> > V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > Could you also change IX86_BUILTIN_VSCALEFPH_V16HF_MASK
> > IX86_BUILTIN_VSCALEFPH256_MASK, similar for others.
> >
> > > gcc/testsuite/ChangeLog:
> > >
> > > * gcc.target/i386/avx-1.c: Adjust builtin macros.
> > > * gcc.target/i386/sse-13.c: Likewise.
> > > * gcc.target/i386/sse-23.c: Likewise.
> > > ---
> > > gcc/config/i386/avx512fp16intrin.h | 1236 ++++++++++++------------
> > > gcc/config/i386/avx512fp16vlintrin.h | 454 ++++-----
> > > gcc/config/i386/i386-builtin.def | 130 +--
> > > gcc/testsuite/gcc.target/i386/avx-1.c | 58 +-
> > > gcc/testsuite/gcc.target/i386/sse-13.c | 58 +-
> > > gcc/testsuite/gcc.target/i386/sse-23.c | 58 +-
> > > 6 files changed, 997 insertions(+), 997 deletions(-)
> > >
> > > diff --git a/gcc/config/i386/avx512fp16intrin.h b/gcc/config/i386/avx512fp16intrin.h
> > > index 2fbfc140c44..5d66ca5c820 100644
> > > --- a/gcc/config/i386/avx512fp16intrin.h
> > > +++ b/gcc/config/i386/avx512fp16intrin.h
> > > @@ -229,15 +229,15 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_add_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> > > {
> > > - return __builtin_ia32_vaddph_v32hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_addph512_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_add_ph (__mmask32 __A, __m512h __B, __m512h __C)
> > > {
> > > - return __builtin_ia32_vaddph_v32hf_mask (__B, __C,
> > > - _mm512_setzero_ph (), __A);
> > > + return __builtin_ia32_addph512_mask (__B, __C,
> > > + _mm512_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -251,15 +251,15 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_sub_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> > > {
> > > - return __builtin_ia32_vsubph_v32hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_subph512_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_sub_ph (__mmask32 __A, __m512h __B, __m512h __C)
> > > {
> > > - return __builtin_ia32_vsubph_v32hf_mask (__B, __C,
> > > - _mm512_setzero_ph (), __A);
> > > + return __builtin_ia32_subph512_mask (__B, __C,
> > > + _mm512_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -273,15 +273,15 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_mul_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> > > {
> > > - return __builtin_ia32_vmulph_v32hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_mulph512_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_mul_ph (__mmask32 __A, __m512h __B, __m512h __C)
> > > {
> > > - return __builtin_ia32_vmulph_v32hf_mask (__B, __C,
> > > - _mm512_setzero_ph (), __A);
> > > + return __builtin_ia32_mulph512_mask (__B, __C,
> > > + _mm512_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -295,15 +295,15 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_div_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> > > {
> > > - return __builtin_ia32_vdivph_v32hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_divph512_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_div_ph (__mmask32 __A, __m512h __B, __m512h __C)
> > > {
> > > - return __builtin_ia32_vdivph_v32hf_mask (__B, __C,
> > > - _mm512_setzero_ph (), __A);
> > > + return __builtin_ia32_divph512_mask (__B, __C,
> > > + _mm512_setzero_ph (), __A);
> > > }
> > >
> > > #ifdef __OPTIMIZE__
> > > @@ -311,9 +311,9 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_add_round_ph (__m512h __A, __m512h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vaddph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1, __C);
> > > + return __builtin_ia32_addph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1, __C);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -321,7 +321,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_add_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> > > __m512h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vaddph_v32hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_addph512_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -329,18 +329,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_add_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vaddph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_addph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_sub_round_ph (__m512h __A, __m512h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vsubph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1, __C);
> > > + return __builtin_ia32_subph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1, __C);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -348,7 +348,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_sub_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> > > __m512h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vsubph_v32hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_subph512_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -356,18 +356,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_sub_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vsubph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_subph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mul_round_ph (__m512h __A, __m512h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vmulph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1, __C);
> > > + return __builtin_ia32_mulph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1, __C);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -375,7 +375,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_mul_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> > > __m512h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vmulph_v32hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_mulph512_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -383,18 +383,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_mul_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vmulph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_mulph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_div_round_ph (__m512h __A, __m512h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vdivph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1, __C);
> > > + return __builtin_ia32_divph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1, __C);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -402,7 +402,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_div_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> > > __m512h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vdivph_v32hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_divph512_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -410,67 +410,67 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_div_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vdivph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_divph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A, __D);
> > > }
> > > #else
> > > #define _mm512_add_round_ph(A, B, C) \
> > > - ((__m512h)__builtin_ia32_vaddph_v32hf_mask_round((A), (B), \
> > > - _mm512_setzero_ph (),\
> > > - (__mmask32)-1, (C)))
> > > + ((__m512h)__builtin_ia32_addph512_mask_round((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, (C)))
> > >
> > > -#define _mm512_mask_add_round_ph(A, B, C, D, E) \
> > > - ((__m512h)__builtin_ia32_vaddph_v32hf_mask_round((C), (D), (A), (B), (E)))
> > > +#define _mm512_mask_add_round_ph(A, B, C, D, E) \
> > > + ((__m512h)__builtin_ia32_addph512_mask_round((C), (D), (A), (B), (E)))
> > >
> > > #define _mm512_maskz_add_round_ph(A, B, C, D) \
> > > - ((__m512h)__builtin_ia32_vaddph_v32hf_mask_round((B), (C), \
> > > - _mm512_setzero_ph (),\
> > > - (A), (D)))
> > > + ((__m512h)__builtin_ia32_addph512_mask_round((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #define _mm512_sub_round_ph(A, B, C) \
> > > - ((__m512h)__builtin_ia32_vsubph_v32hf_mask_round((A), (B), \
> > > - _mm512_setzero_ph (),\
> > > - (__mmask32)-1, (C)))
> > > + ((__m512h)__builtin_ia32_subph512_mask_round((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, (C)))
> > >
> > > -#define _mm512_mask_sub_round_ph(A, B, C, D, E) \
> > > - ((__m512h)__builtin_ia32_vsubph_v32hf_mask_round((C), (D), (A), (B), (E)))
> > > +#define _mm512_mask_sub_round_ph(A, B, C, D, E) \
> > > + ((__m512h)__builtin_ia32_subph512_mask_round((C), (D), (A), (B), (E)))
> > >
> > > #define _mm512_maskz_sub_round_ph(A, B, C, D) \
> > > - ((__m512h)__builtin_ia32_vsubph_v32hf_mask_round((B), (C), \
> > > - _mm512_setzero_ph (),\
> > > - (A), (D)))
> > > + ((__m512h)__builtin_ia32_subph512_mask_round((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #define _mm512_mul_round_ph(A, B, C) \
> > > - ((__m512h)__builtin_ia32_vmulph_v32hf_mask_round((A), (B), \
> > > - _mm512_setzero_ph (),\
> > > - (__mmask32)-1, (C)))
> > > + ((__m512h)__builtin_ia32_mulph512_mask_round((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, (C)))
> > >
> > > -#define _mm512_mask_mul_round_ph(A, B, C, D, E) \
> > > - ((__m512h)__builtin_ia32_vmulph_v32hf_mask_round((C), (D), (A), (B), (E)))
> > > +#define _mm512_mask_mul_round_ph(A, B, C, D, E) \
> > > + ((__m512h)__builtin_ia32_mulph512_mask_round((C), (D), (A), (B), (E)))
> > >
> > > #define _mm512_maskz_mul_round_ph(A, B, C, D) \
> > > - ((__m512h)__builtin_ia32_vmulph_v32hf_mask_round((B), (C), \
> > > - _mm512_setzero_ph (),\
> > > - (A), (D)))
> > > + ((__m512h)__builtin_ia32_mulph512_mask_round((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #define _mm512_div_round_ph(A, B, C) \
> > > - ((__m512h)__builtin_ia32_vdivph_v32hf_mask_round((A), (B), \
> > > - _mm512_setzero_ph (),\
> > > - (__mmask32)-1, (C)))
> > > + ((__m512h)__builtin_ia32_divph512_mask_round((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, (C)))
> > >
> > > -#define _mm512_mask_div_round_ph(A, B, C, D, E) \
> > > - ((__m512h)__builtin_ia32_vdivph_v32hf_mask_round((C), (D), (A), (B), (E)))
> > > +#define _mm512_mask_div_round_ph(A, B, C, D, E) \
> > > + ((__m512h)__builtin_ia32_divph512_mask_round((C), (D), (A), (B), (E)))
> > >
> > > #define _mm512_maskz_div_round_ph(A, B, C, D) \
> > > - ((__m512h)__builtin_ia32_vdivph_v32hf_mask_round((B), (C), \
> > > - _mm512_setzero_ph (),\
> > > - (A), (D)))
> > > + ((__m512h)__builtin_ia32_divph512_mask_round((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), (D)))
> > > #endif /* __OPTIMIZE__ */
> > >
> > > /* Intrinsics of v[add,sub,mul,div]sh. */
> > > extern __inline __m128h
> > > -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > + __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_add_sh (__m128h __A, __m128h __B)
> > > {
> > > __A[0] += __B[0];
> > > @@ -481,15 +481,15 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_add_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vaddsh_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_addsh_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_add_sh (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vaddsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_addsh_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -504,15 +504,15 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_sub_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vsubsh_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_subsh_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_sub_sh (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vsubsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_subsh_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -527,14 +527,14 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_mul_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vmulsh_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_mulsh_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_mul_sh (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vmulsh_v8hf_mask (__B, __C, _mm_setzero_ph (), __A);
> > > + return __builtin_ia32_mulsh_mask (__B, __C, _mm_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -549,15 +549,15 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_div_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vdivsh_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_divsh_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_div_sh (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vdivsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_divsh_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > #ifdef __OPTIMIZE__
> > > @@ -565,9 +565,9 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_add_round_sh (__m128h __A, __m128h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vaddsh_v8hf_mask_round (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1, __C);
> > > + return __builtin_ia32_addsh_mask_round (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1, __C);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -575,7 +575,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_add_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vaddsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_addsh_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -583,18 +583,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_add_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vaddsh_v8hf_mask_round (__B, __C,
> > > - _mm_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_addsh_mask_round (__B, __C,
> > > + _mm_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_sub_round_sh (__m128h __A, __m128h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vsubsh_v8hf_mask_round (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1, __C);
> > > + return __builtin_ia32_subsh_mask_round (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1, __C);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -602,7 +602,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_sub_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vsubsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_subsh_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -610,18 +610,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_sub_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vsubsh_v8hf_mask_round (__B, __C,
> > > - _mm_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_subsh_mask_round (__B, __C,
> > > + _mm_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mul_round_sh (__m128h __A, __m128h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vmulsh_v8hf_mask_round (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1, __C);
> > > + return __builtin_ia32_mulsh_mask_round (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1, __C);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -629,7 +629,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_mul_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vmulsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_mulsh_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -637,18 +637,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_mul_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vmulsh_v8hf_mask_round (__B, __C,
> > > - _mm_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_mulsh_mask_round (__B, __C,
> > > + _mm_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_div_round_sh (__m128h __A, __m128h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vdivsh_v8hf_mask_round (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1, __C);
> > > + return __builtin_ia32_divsh_mask_round (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1, __C);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -656,7 +656,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_div_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vdivsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_divsh_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -664,62 +664,62 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_div_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vdivsh_v8hf_mask_round (__B, __C,
> > > - _mm_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_divsh_mask_round (__B, __C,
> > > + _mm_setzero_ph (),
> > > + __A, __D);
> > > }
> > > #else
> > > #define _mm_add_round_sh(A, B, C) \
> > > - ((__m128h)__builtin_ia32_vaddsh_v8hf_mask_round ((A), (B), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, (C)))
> > > + ((__m128h)__builtin_ia32_addsh_mask_round ((A), (B), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, (C)))
> > >
> > > #define _mm_mask_add_round_sh(A, B, C, D, E) \
> > > - ((__m128h)__builtin_ia32_vaddsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> > > + ((__m128h)__builtin_ia32_addsh_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm_maskz_add_round_sh(A, B, C, D) \
> > > - ((__m128h)__builtin_ia32_vaddsh_v8hf_mask_round ((B), (C), \
> > > - _mm_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm_maskz_add_round_sh(A, B, C, D) \
> > > + ((__m128h)__builtin_ia32_addsh_mask_round ((B), (C), \
> > > + _mm_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #define _mm_sub_round_sh(A, B, C) \
> > > - ((__m128h)__builtin_ia32_vsubsh_v8hf_mask_round ((A), (B), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, (C)))
> > > + ((__m128h)__builtin_ia32_subsh_mask_round ((A), (B), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, (C)))
> > >
> > > #define _mm_mask_sub_round_sh(A, B, C, D, E) \
> > > - ((__m128h)__builtin_ia32_vsubsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> > > + ((__m128h)__builtin_ia32_subsh_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm_maskz_sub_round_sh(A, B, C, D) \
> > > - ((__m128h)__builtin_ia32_vsubsh_v8hf_mask_round ((B), (C), \
> > > - _mm_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm_maskz_sub_round_sh(A, B, C, D) \
> > > + ((__m128h)__builtin_ia32_subsh_mask_round ((B), (C), \
> > > + _mm_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #define _mm_mul_round_sh(A, B, C) \
> > > - ((__m128h)__builtin_ia32_vmulsh_v8hf_mask_round ((A), (B), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, (C)))
> > > + ((__m128h)__builtin_ia32_mulsh_mask_round ((A), (B), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, (C)))
> > >
> > > #define _mm_mask_mul_round_sh(A, B, C, D, E) \
> > > - ((__m128h)__builtin_ia32_vmulsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> > > + ((__m128h)__builtin_ia32_mulsh_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm_maskz_mul_round_sh(A, B, C, D) \
> > > - ((__m128h)__builtin_ia32_vmulsh_v8hf_mask_round ((B), (C), \
> > > - _mm_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm_maskz_mul_round_sh(A, B, C, D) \
> > > + ((__m128h)__builtin_ia32_mulsh_mask_round ((B), (C), \
> > > + _mm_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #define _mm_div_round_sh(A, B, C) \
> > > - ((__m128h)__builtin_ia32_vdivsh_v8hf_mask_round ((A), (B), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, (C)))
> > > + ((__m128h)__builtin_ia32_divsh_mask_round ((A), (B), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, (C)))
> > >
> > > #define _mm_mask_div_round_sh(A, B, C, D, E) \
> > > - ((__m128h)__builtin_ia32_vdivsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> > > + ((__m128h)__builtin_ia32_divsh_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm_maskz_div_round_sh(A, B, C, D) \
> > > - ((__m128h)__builtin_ia32_vdivsh_v8hf_mask_round ((B), (C), \
> > > - _mm_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm_maskz_div_round_sh(A, B, C, D) \
> > > + ((__m128h)__builtin_ia32_divsh_mask_round ((B), (C), \
> > > + _mm_setzero_ph (), \
> > > + (A), (D)))
> > > #endif /* __OPTIMIZE__ */
> > >
> > > /* Intrinsic vmaxph vminph. */
> > > @@ -727,48 +727,48 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_max_ph (__m512h __A, __m512h __B)
> > > {
> > > - return __builtin_ia32_vmaxph_v32hf_mask (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1);
> > > + return __builtin_ia32_maxph512_mask (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_max_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> > > {
> > > - return __builtin_ia32_vmaxph_v32hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_maxph512_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_max_ph (__mmask32 __A, __m512h __B, __m512h __C)
> > > {
> > > - return __builtin_ia32_vmaxph_v32hf_mask (__B, __C,
> > > - _mm512_setzero_ph (), __A);
> > > + return __builtin_ia32_maxph512_mask (__B, __C,
> > > + _mm512_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_min_ph (__m512h __A, __m512h __B)
> > > {
> > > - return __builtin_ia32_vminph_v32hf_mask (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1);
> > > + return __builtin_ia32_minph512_mask (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_min_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> > > {
> > > - return __builtin_ia32_vminph_v32hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_minph512_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_min_ph (__mmask32 __A, __m512h __B, __m512h __C)
> > > {
> > > - return __builtin_ia32_vminph_v32hf_mask (__B, __C,
> > > - _mm512_setzero_ph (), __A);
> > > + return __builtin_ia32_minph512_mask (__B, __C,
> > > + _mm512_setzero_ph (), __A);
> > > }
> > >
> > > #ifdef __OPTIMIZE__
> > > @@ -776,9 +776,9 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_max_round_ph (__m512h __A, __m512h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vmaxph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1, __C);
> > > + return __builtin_ia32_maxph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1, __C);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -786,7 +786,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_max_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> > > __m512h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vmaxph_v32hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_maxph512_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -794,18 +794,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_max_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vmaxph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_maxph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_min_round_ph (__m512h __A, __m512h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vminph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1, __C);
> > > + return __builtin_ia32_minph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1, __C);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -813,7 +813,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_min_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> > > __m512h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vminph_v32hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_minph512_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -821,37 +821,37 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_min_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vminph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_minph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > #else
> > > -#define _mm512_max_round_ph(A, B, C) \
> > > - (__builtin_ia32_vmaxph_v32hf_mask_round ((A), (B), \
> > > - _mm512_setzero_ph (), \
> > > - (__mmask32)-1, (C)))
> > > +#define _mm512_max_round_ph(A, B, C) \
> > > + (__builtin_ia32_maxph512_mask_round ((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, (C)))
> > >
> > > #define _mm512_mask_max_round_ph(A, B, C, D, E) \
> > > - (__builtin_ia32_vmaxph_v32hf_mask_round ((C), (D), (A), (B), (E)))
> > > + (__builtin_ia32_maxph512_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm512_maskz_max_round_ph(A, B, C, D) \
> > > - (__builtin_ia32_vmaxph_v32hf_mask_round ((B), (C), \
> > > - _mm512_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm512_maskz_max_round_ph(A, B, C, D) \
> > > + (__builtin_ia32_maxph512_mask_round ((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > -#define _mm512_min_round_ph(A, B, C) \
> > > - (__builtin_ia32_vminph_v32hf_mask_round ((A), (B), \
> > > - _mm512_setzero_ph (), \
> > > - (__mmask32)-1, (C)))
> > > +#define _mm512_min_round_ph(A, B, C) \
> > > + (__builtin_ia32_minph512_mask_round ((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, (C)))
> > >
> > > #define _mm512_mask_min_round_ph(A, B, C, D, E) \
> > > - (__builtin_ia32_vminph_v32hf_mask_round ((C), (D), (A), (B), (E)))
> > > + (__builtin_ia32_minph512_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm512_maskz_min_round_ph(A, B, C, D) \
> > > - (__builtin_ia32_vminph_v32hf_mask_round ((B), (C), \
> > > - _mm512_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm512_maskz_min_round_ph(A, B, C, D) \
> > > + (__builtin_ia32_minph512_mask_round ((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), (D)))
> > > #endif /* __OPTIMIZE__ */
> > >
> > > /* Intrinsic vmaxsh vminsh. */
> > > @@ -867,15 +867,15 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_max_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vmaxsh_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_maxsh_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_max_sh (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vmaxsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_maxsh_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -890,15 +890,15 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_min_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vminsh_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_minsh_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_min_sh (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vminsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_minsh_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > #ifdef __OPTIMIZE__
> > > @@ -906,9 +906,9 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_max_round_sh (__m128h __A, __m128h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vmaxsh_v8hf_mask_round (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1, __C);
> > > + return __builtin_ia32_maxsh_mask_round (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1, __C);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -916,7 +916,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_max_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vmaxsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_maxsh_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -924,18 +924,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_max_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vmaxsh_v8hf_mask_round (__B, __C,
> > > - _mm_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_maxsh_mask_round (__B, __C,
> > > + _mm_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_min_round_sh (__m128h __A, __m128h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vminsh_v8hf_mask_round (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1, __C);
> > > + return __builtin_ia32_minsh_mask_round (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1, __C);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -943,7 +943,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_min_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vminsh_v8hf_mask_round (__C, __D, __A, __B, __E);
> > > + return __builtin_ia32_minsh_mask_round (__C, __D, __A, __B, __E);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -951,37 +951,37 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_min_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vminsh_v8hf_mask_round (__B, __C,
> > > - _mm_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_minsh_mask_round (__B, __C,
> > > + _mm_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > #else
> > > -#define _mm_max_round_sh(A, B, C) \
> > > - (__builtin_ia32_vmaxsh_v8hf_mask_round ((A), (B), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, (C)))
> > > +#define _mm_max_round_sh(A, B, C) \
> > > + (__builtin_ia32_maxsh_mask_round ((A), (B), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, (C)))
> > >
> > > -#define _mm_mask_max_round_sh(A, B, C, D, E) \
> > > - (__builtin_ia32_vmaxsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> > > +#define _mm_mask_max_round_sh(A, B, C, D, E) \
> > > + (__builtin_ia32_maxsh_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm_maskz_max_round_sh(A, B, C, D) \
> > > - (__builtin_ia32_vmaxsh_v8hf_mask_round ((B), (C), \
> > > - _mm_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm_maskz_max_round_sh(A, B, C, D) \
> > > + (__builtin_ia32_maxsh_mask_round ((B), (C), \
> > > + _mm_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > -#define _mm_min_round_sh(A, B, C) \
> > > - (__builtin_ia32_vminsh_v8hf_mask_round ((A), (B), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, (C)))
> > > +#define _mm_min_round_sh(A, B, C) \
> > > + (__builtin_ia32_minsh_mask_round ((A), (B), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, (C)))
> > >
> > > -#define _mm_mask_min_round_sh(A, B, C, D, E) \
> > > - (__builtin_ia32_vminsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> > > +#define _mm_mask_min_round_sh(A, B, C, D, E) \
> > > + (__builtin_ia32_minsh_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm_maskz_min_round_sh(A, B, C, D) \
> > > - (__builtin_ia32_vminsh_v8hf_mask_round ((B), (C), \
> > > - _mm_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm_maskz_min_round_sh(A, B, C, D) \
> > > + (__builtin_ia32_minsh_mask_round ((B), (C), \
> > > + _mm_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -991,8 +991,8 @@ extern __inline __mmask32
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_cmp_ph_mask (__m512h __A, __m512h __B, const int __C)
> > > {
> > > - return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask (__A, __B, __C,
> > > - (__mmask32) -1);
> > > + return (__mmask32) __builtin_ia32_cmpph512_mask (__A, __B, __C,
> > > + (__mmask32) -1);
> > > }
> > >
> > > extern __inline __mmask32
> > > @@ -1000,8 +1000,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_cmp_ph_mask (__mmask32 __A, __m512h __B, __m512h __C,
> > > const int __D)
> > > {
> > > - return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask (__B, __C, __D,
> > > - __A);
> > > + return (__mmask32) __builtin_ia32_cmpph512_mask (__B, __C, __D,
> > > + __A);
> > > }
> > >
> > > extern __inline __mmask32
> > > @@ -1009,9 +1009,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_cmp_round_ph_mask (__m512h __A, __m512h __B, const int __C,
> > > const int __D)
> > > {
> > > - return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask_round (__A, __B,
> > > - __C, (__mmask32) -1,
> > > - __D);
> > > + return (__mmask32) __builtin_ia32_cmpph512_mask_round (__A, __B,
> > > + __C, (__mmask32) -1,
> > > + __D);
> > > }
> > >
> > > extern __inline __mmask32
> > > @@ -1019,23 +1019,23 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_cmp_round_ph_mask (__mmask32 __A, __m512h __B, __m512h __C,
> > > const int __D, const int __E)
> > > {
> > > - return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask_round (__B, __C,
> > > - __D, __A,
> > > - __E);
> > > + return (__mmask32) __builtin_ia32_cmpph512_mask_round (__B, __C,
> > > + __D, __A,
> > > + __E);
> > > }
> > >
> > > #else
> > > #define _mm512_cmp_ph_mask(A, B, C) \
> > > - (__builtin_ia32_vcmpph_v32hf_mask ((A), (B), (C), (-1)))
> > > + (__builtin_ia32_cmpph512_mask ((A), (B), (C), (-1)))
> > >
> > > #define _mm512_mask_cmp_ph_mask(A, B, C, D) \
> > > - (__builtin_ia32_vcmpph_v32hf_mask ((B), (C), (D), (A)))
> > > + (__builtin_ia32_cmpph512_mask ((B), (C), (D), (A)))
> > >
> > > -#define _mm512_cmp_round_ph_mask(A, B, C, D) \
> > > - (__builtin_ia32_vcmpph_v32hf_mask_round ((A), (B), (C), (-1), (D)))
> > > +#define _mm512_cmp_round_ph_mask(A, B, C, D) \
> > > + (__builtin_ia32_cmpph512_mask_round ((A), (B), (C), (-1), (D)))
> > >
> > > -#define _mm512_mask_cmp_round_ph_mask(A, B, C, D, E) \
> > > - (__builtin_ia32_vcmpph_v32hf_mask_round ((B), (C), (D), (A), (E)))
> > > +#define _mm512_mask_cmp_round_ph_mask(A, B, C, D, E) \
> > > + (__builtin_ia32_cmpph512_mask_round ((B), (C), (D), (A), (E)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -1046,9 +1046,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_cmp_sh_mask (__m128h __A, __m128h __B, const int __C)
> > > {
> > > return (__mmask8)
> > > - __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B,
> > > - __C, (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + __builtin_ia32_cmpsh_mask_round (__A, __B,
> > > + __C, (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __mmask8
> > > @@ -1057,9 +1057,9 @@ _mm_mask_cmp_sh_mask (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D)
> > > {
> > > return (__mmask8)
> > > - __builtin_ia32_vcmpsh_v8hf_mask_round (__B, __C,
> > > - __D, __A,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + __builtin_ia32_cmpsh_mask_round (__B, __C,
> > > + __D, __A,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __mmask8
> > > @@ -1067,9 +1067,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_cmp_round_sh_mask (__m128h __A, __m128h __B, const int __C,
> > > const int __D)
> > > {
> > > - return (__mmask8) __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B,
> > > - __C, (__mmask8) -1,
> > > - __D);
> > > + return (__mmask8) __builtin_ia32_cmpsh_mask_round (__A, __B,
> > > + __C, (__mmask8) -1,
> > > + __D);
> > > }
> > >
> > > extern __inline __mmask8
> > > @@ -1077,25 +1077,25 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_cmp_round_sh_mask (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D, const int __E)
> > > {
> > > - return (__mmask8) __builtin_ia32_vcmpsh_v8hf_mask_round (__B, __C,
> > > - __D, __A,
> > > - __E);
> > > + return (__mmask8) __builtin_ia32_cmpsh_mask_round (__B, __C,
> > > + __D, __A,
> > > + __E);
> > > }
> > >
> > > #else
> > > -#define _mm_cmp_sh_mask(A, B, C) \
> > > - (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (C), (-1), \
> > > - (_MM_FROUND_CUR_DIRECTION)))
> > > +#define _mm_cmp_sh_mask(A, B, C) \
> > > + (__builtin_ia32_cmpsh_mask_round ((A), (B), (C), (-1), \
> > > + (_MM_FROUND_CUR_DIRECTION)))
> > >
> > > -#define _mm_mask_cmp_sh_mask(A, B, C, D) \
> > > - (__builtin_ia32_vcmpsh_v8hf_mask_round ((B), (C), (D), (A), \
> > > - (_MM_FROUND_CUR_DIRECTION)))
> > > +#define _mm_mask_cmp_sh_mask(A, B, C, D) \
> > > + (__builtin_ia32_cmpsh_mask_round ((B), (C), (D), (A), \
> > > + (_MM_FROUND_CUR_DIRECTION)))
> > >
> > > -#define _mm_cmp_round_sh_mask(A, B, C, D) \
> > > - (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (C), (-1), (D)))
> > > +#define _mm_cmp_round_sh_mask(A, B, C, D) \
> > > + (__builtin_ia32_cmpsh_mask_round ((A), (B), (C), (-1), (D)))
> > >
> > > -#define _mm_mask_cmp_round_sh_mask(A, B, C, D, E) \
> > > - (__builtin_ia32_vcmpsh_v8hf_mask_round ((B), (C), (D), (A), (E)))
> > > +#define _mm_mask_cmp_round_sh_mask(A, B, C, D, E) \
> > > + (__builtin_ia32_cmpsh_mask_round ((B), (C), (D), (A), (E)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -1104,134 +1104,134 @@ extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_comieq_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_EQ_OS,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_EQ_OS,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_comilt_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LT_OS,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LT_OS,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_comile_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LE_OS,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LE_OS,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_comigt_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GT_OS,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GT_OS,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_comige_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GE_OS,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GE_OS,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_comineq_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_NEQ_US,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_NEQ_US,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_ucomieq_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_EQ_OQ,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_EQ_OQ,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_ucomilt_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LT_OQ,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LT_OQ,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_ucomile_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LE_OQ,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LE_OQ,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_ucomigt_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GT_OQ,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GT_OQ,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_ucomige_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GE_OQ,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GE_OQ,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_ucomineq_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_NEQ_UQ,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_NEQ_UQ,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > #ifdef __OPTIMIZE__
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > - _mm_comi_sh (__m128h __A, __m128h __B, const int __P)
> > > +_mm_comi_sh (__m128h __A, __m128h __B, const int __P)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, __P,
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, __P,
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline int
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_comi_round_sh (__m128h __A, __m128h __B, const int __P, const int __R)
> > > {
> > > - return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, __P,
> > > - (__mmask8) -1,__R);
> > > + return __builtin_ia32_cmpsh_mask_round (__A, __B, __P,
> > > + (__mmask8) -1,__R);
> > > }
> > >
> > > #else
> > > -#define _mm_comi_round_sh(A, B, P, R) \
> > > - (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (P), (__mmask8) (-1), (R)))
> > > -#define _mm_comi_sh(A, B, P) \
> > > - (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (P), (__mmask8) (-1), \
> > > - _MM_FROUND_CUR_DIRECTION))
> > > +#define _mm_comi_round_sh(A, B, P, R) \
> > > + (__builtin_ia32_cmpsh_mask_round ((A), (B), (P), (__mmask8) (-1), (R)))
> > > +#define _mm_comi_sh(A, B, P) \
> > > + (__builtin_ia32_cmpsh_mask_round ((A), (B), (P), (__mmask8) (-1), \
> > > + _MM_FROUND_CUR_DIRECTION))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -1240,28 +1240,28 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_sqrt_ph (__m512h __A)
> > > {
> > > - return __builtin_ia32_vsqrtph_v32hf_mask_round (__A,
> > > - _mm512_setzero_ph(),
> > > - (__mmask32) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_sqrtph512_mask_round (__A,
> > > + _mm512_setzero_ph(),
> > > + (__mmask32) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_sqrt_ph (__m512h __A, __mmask32 __B, __m512h __C)
> > > {
> > > - return __builtin_ia32_vsqrtph_v32hf_mask_round (__C, __A, __B,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_sqrtph512_mask_round (__C, __A, __B,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_sqrt_ph (__mmask32 __A, __m512h __B)
> > > {
> > > - return __builtin_ia32_vsqrtph_v32hf_mask_round (__B,
> > > - _mm512_setzero_ph (),
> > > - __A,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_sqrtph512_mask_round (__B,
> > > + _mm512_setzero_ph (),
> > > + __A,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > #ifdef __OPTIMIZE__
> > > @@ -1269,9 +1269,9 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_sqrt_round_ph (__m512h __A, const int __B)
> > > {
> > > - return __builtin_ia32_vsqrtph_v32hf_mask_round (__A,
> > > - _mm512_setzero_ph(),
> > > - (__mmask32) -1, __B);
> > > + return __builtin_ia32_sqrtph512_mask_round (__A,
> > > + _mm512_setzero_ph(),
> > > + (__mmask32) -1, __B);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -1279,31 +1279,31 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_sqrt_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vsqrtph_v32hf_mask_round (__C, __A, __B, __D);
> > > + return __builtin_ia32_sqrtph512_mask_round (__C, __A, __B, __D);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_sqrt_round_ph (__mmask32 __A, __m512h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vsqrtph_v32hf_mask_round (__B,
> > > - _mm512_setzero_ph (),
> > > - __A, __C);
> > > + return __builtin_ia32_sqrtph512_mask_round (__B,
> > > + _mm512_setzero_ph (),
> > > + __A, __C);
> > > }
> > >
> > > #else
> > > -#define _mm512_sqrt_round_ph(A, B) \
> > > - (__builtin_ia32_vsqrtph_v32hf_mask_round ((A), \
> > > - _mm512_setzero_ph (), \
> > > - (__mmask32)-1, (B)))
> > > +#define _mm512_sqrt_round_ph(A, B) \
> > > + (__builtin_ia32_sqrtph512_mask_round ((A), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, (B)))
> > >
> > > -#define _mm512_mask_sqrt_round_ph(A, B, C, D) \
> > > - (__builtin_ia32_vsqrtph_v32hf_mask_round ((C), (A), (B), (D)))
> > > +#define _mm512_mask_sqrt_round_ph(A, B, C, D) \
> > > + (__builtin_ia32_sqrtph512_mask_round ((C), (A), (B), (D)))
> > >
> > > -#define _mm512_maskz_sqrt_round_ph(A, B, C) \
> > > - (__builtin_ia32_vsqrtph_v32hf_mask_round ((B), \
> > > - _mm512_setzero_ph (), \
> > > - (A), (C)))
> > > +#define _mm512_maskz_sqrt_round_ph(A, B, C) \
> > > + (__builtin_ia32_sqrtph512_mask_round ((B), \
> > > + _mm512_setzero_ph (), \
> > > + (A), (C)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -1312,23 +1312,23 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_rsqrt_ph (__m512h __A)
> > > {
> > > - return __builtin_ia32_vrsqrtph_v32hf_mask (__A, _mm512_setzero_ph (),
> > > - (__mmask32) -1);
> > > + return __builtin_ia32_rsqrtph512_mask (__A, _mm512_setzero_ph (),
> > > + (__mmask32) -1);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_rsqrt_ph (__m512h __A, __mmask32 __B, __m512h __C)
> > > {
> > > - return __builtin_ia32_vrsqrtph_v32hf_mask (__C, __A, __B);
> > > + return __builtin_ia32_rsqrtph512_mask (__C, __A, __B);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_rsqrt_ph (__mmask32 __A, __m512h __B)
> > > {
> > > - return __builtin_ia32_vrsqrtph_v32hf_mask (__B, _mm512_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_rsqrtph512_mask (__B, _mm512_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > /* Intrinsics vrsqrtsh. */
> > > @@ -1336,23 +1336,23 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_rsqrt_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vrsqrtsh_v8hf_mask (__B, __A, _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > + return __builtin_ia32_rsqrtsh_mask (__B, __A, _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_rsqrt_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vrsqrtsh_v8hf_mask (__D, __C, __A, __B);
> > > + return __builtin_ia32_rsqrtsh_mask (__D, __C, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_rsqrt_sh (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vrsqrtsh_v8hf_mask (__C, __B, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_rsqrtsh_mask (__C, __B, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > /* Intrinsics vsqrtsh. */
> > > @@ -1360,27 +1360,27 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_sqrt_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__B, __A,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_sqrtsh_mask_round (__B, __A,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_sqrt_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__D, __C, __A, __B,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_sqrtsh_mask_round (__D, __C, __A, __B,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_sqrt_sh (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__C, __B,
> > > - _mm_setzero_ph (),
> > > - __A, _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_sqrtsh_mask_round (__C, __B,
> > > + _mm_setzero_ph (),
> > > + __A, _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > #ifdef __OPTIMIZE__
> > > @@ -1388,9 +1388,9 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_sqrt_round_sh (__m128h __A, __m128h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__B, __A,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1, __C);
> > > + return __builtin_ia32_sqrtsh_mask_round (__B, __A,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1, __C);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -1398,8 +1398,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_sqrt_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__D, __C, __A, __B,
> > > - __E);
> > > + return __builtin_ia32_sqrtsh_mask_round (__D, __C, __A, __B,
> > > + __E);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -1407,24 +1407,24 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_sqrt_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vsqrtsh_v8hf_mask_round (__C, __B,
> > > - _mm_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_sqrtsh_mask_round (__C, __B,
> > > + _mm_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > #else
> > > #define _mm_sqrt_round_sh(A, B, C) \
> > > - (__builtin_ia32_vsqrtsh_v8hf_mask_round ((B), (A), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, (C)))
> > > + (__builtin_ia32_sqrtsh_mask_round ((B), (A), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, (C)))
> > >
> > > #define _mm_mask_sqrt_round_sh(A, B, C, D, E) \
> > > - (__builtin_ia32_vsqrtsh_v8hf_mask_round ((D), (C), (A), (B), (E)))
> > > + (__builtin_ia32_sqrtsh_mask_round ((D), (C), (A), (B), (E)))
> > >
> > > -#define _mm_maskz_sqrt_round_sh(A, B, C, D) \
> > > - (__builtin_ia32_vsqrtsh_v8hf_mask_round ((C), (B), \
> > > - _mm_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm_maskz_sqrt_round_sh(A, B, C, D) \
> > > + (__builtin_ia32_sqrtsh_mask_round ((C), (B), \
> > > + _mm_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -1433,23 +1433,23 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_rcp_ph (__m512h __A)
> > > {
> > > - return __builtin_ia32_vrcpph_v32hf_mask (__A, _mm512_setzero_ph (),
> > > - (__mmask32) -1);
> > > + return __builtin_ia32_rcpph512_mask (__A, _mm512_setzero_ph (),
> > > + (__mmask32) -1);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_rcp_ph (__m512h __A, __mmask32 __B, __m512h __C)
> > > {
> > > - return __builtin_ia32_vrcpph_v32hf_mask (__C, __A, __B);
> > > + return __builtin_ia32_rcpph512_mask (__C, __A, __B);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_rcp_ph (__mmask32 __A, __m512h __B)
> > > {
> > > - return __builtin_ia32_vrcpph_v32hf_mask (__B, _mm512_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_rcpph512_mask (__B, _mm512_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > /* Intrinsics vrcpsh. */
> > > @@ -1457,23 +1457,23 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_rcp_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vrcpsh_v8hf_mask (__B, __A, _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > + return __builtin_ia32_rcpsh_mask (__B, __A, _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_rcp_sh (__m128h __A, __mmask32 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vrcpsh_v8hf_mask (__D, __C, __A, __B);
> > > + return __builtin_ia32_rcpsh_mask (__D, __C, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_rcp_sh (__mmask32 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vrcpsh_v8hf_mask (__C, __B, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_rcpsh_mask (__C, __B, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > /* Intrinsics vscalefph. */
> > > @@ -1481,28 +1481,28 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_scalef_ph (__m512h __A, __m512h __B)
> > > {
> > > - return __builtin_ia32_vscalefph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_scalefph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_scalef_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
> > > {
> > > - return __builtin_ia32_vscalefph_v32hf_mask_round (__C, __D, __A, __B,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_scalefph512_mask_round (__C, __D, __A, __B,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_scalef_ph (__mmask32 __A, __m512h __B, __m512h __C)
> > > {
> > > - return __builtin_ia32_vscalefph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_scalefph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > #ifdef __OPTIMIZE__
> > > @@ -1510,9 +1510,9 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_scalef_round_ph (__m512h __A, __m512h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vscalefph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1, __C);
> > > + return __builtin_ia32_scalefph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1, __C);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -1520,8 +1520,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_scalef_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> > > __m512h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vscalefph_v32hf_mask_round (__C, __D, __A, __B,
> > > - __E);
> > > + return __builtin_ia32_scalefph512_mask_round (__C, __D, __A, __B,
> > > + __E);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -1529,24 +1529,24 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_scalef_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vscalefph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_scalefph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > #else
> > > -#define _mm512_scalef_round_ph(A, B, C) \
> > > - (__builtin_ia32_vscalefph_v32hf_mask_round ((A), (B), \
> > > - _mm512_setzero_ph (), \
> > > - (__mmask32)-1, (C)))
> > > +#define _mm512_scalef_round_ph(A, B, C) \
> > > + (__builtin_ia32_scalefph512_mask_round ((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, (C)))
> > >
> > > #define _mm512_mask_scalef_round_ph(A, B, C, D, E) \
> > > - (__builtin_ia32_vscalefph_v32hf_mask_round ((C), (D), (A), (B), (E)))
> > > + (__builtin_ia32_scalefph512_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm512_maskz_scalef_round_ph(A, B, C, D) \
> > > - (__builtin_ia32_vscalefph_v32hf_mask_round ((B), (C), \
> > > - _mm512_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm512_maskz_scalef_round_ph(A, B, C, D) \
> > > + (__builtin_ia32_scalefph512_mask_round ((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -1555,28 +1555,28 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_scalef_sh (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vscalefsh_v8hf_mask_round (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_scalefsh_mask_round (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_scalef_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vscalefsh_v8hf_mask_round (__C, __D, __A, __B,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_scalefsh_mask_round (__C, __D, __A, __B,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_scalef_sh (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vscalefsh_v8hf_mask_round (__B, __C,
> > > - _mm_setzero_ph (),
> > > - __A,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_scalefsh_mask_round (__B, __C,
> > > + _mm_setzero_ph (),
> > > + __A,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > #ifdef __OPTIMIZE__
> > > @@ -1584,9 +1584,9 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_scalef_round_sh (__m128h __A, __m128h __B, const int __C)
> > > {
> > > - return __builtin_ia32_vscalefsh_v8hf_mask_round (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1, __C);
> > > + return __builtin_ia32_scalefsh_mask_round (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1, __C);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -1594,8 +1594,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_scalef_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, const int __E)
> > > {
> > > - return __builtin_ia32_vscalefsh_v8hf_mask_round (__C, __D, __A, __B,
> > > - __E);
> > > + return __builtin_ia32_scalefsh_mask_round (__C, __D, __A, __B,
> > > + __E);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -1603,23 +1603,23 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_scalef_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vscalefsh_v8hf_mask_round (__B, __C,
> > > - _mm_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_scalefsh_mask_round (__B, __C,
> > > + _mm_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > #else
> > > -#define _mm_scalef_round_sh(A, B, C) \
> > > - (__builtin_ia32_vscalefsh_v8hf_mask_round ((A), (B), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, (C)))
> > > +#define _mm_scalef_round_sh(A, B, C) \
> > > + (__builtin_ia32_scalefsh_mask_round ((A), (B), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, (C)))
> > >
> > > -#define _mm_mask_scalef_round_sh(A, B, C, D, E) \
> > > - (__builtin_ia32_vscalefsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
> > > +#define _mm_mask_scalef_round_sh(A, B, C, D, E) \
> > > + (__builtin_ia32_scalefsh_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm_maskz_scalef_round_sh(A, B, C, D) \
> > > - (__builtin_ia32_vscalefsh_v8hf_mask_round ((B), (C), _mm_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm_maskz_scalef_round_sh(A, B, C, D) \
> > > + (__builtin_ia32_scalefsh_mask_round ((B), (C), _mm_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -1629,37 +1629,37 @@ extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_reduce_ph (__m512h __A, int __B)
> > > {
> > > - return __builtin_ia32_vreduceph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_reduceph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_reduce_ph (__m512h __A, __mmask32 __B, __m512h __C, int __D)
> > > {
> > > - return __builtin_ia32_vreduceph_v32hf_mask_round (__C, __D, __A, __B,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_reduceph512_mask_round (__C, __D, __A, __B,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_reduce_ph (__mmask32 __A, __m512h __B, int __C)
> > > {
> > > - return __builtin_ia32_vreduceph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_reduceph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_reduce_round_ph (__m512h __A, int __B, const int __C)
> > > {
> > > - return __builtin_ia32_vreduceph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1, __C);
> > > + return __builtin_ia32_reduceph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1, __C);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -1667,8 +1667,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_reduce_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
> > > int __D, const int __E)
> > > {
> > > - return __builtin_ia32_vreduceph_v32hf_mask_round (__C, __D, __A, __B,
> > > - __E);
> > > + return __builtin_ia32_reduceph512_mask_round (__C, __D, __A, __B,
> > > + __E);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -1676,39 +1676,39 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_reduce_round_ph (__mmask32 __A, __m512h __B, int __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vreduceph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_reduceph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > #else
> > > #define _mm512_reduce_ph(A, B) \
> > > - (__builtin_ia32_vreduceph_v32hf_mask_round ((A), (B), \
> > > - _mm512_setzero_ph (), \
> > > - (__mmask32)-1, \
> > > - _MM_FROUND_CUR_DIRECTION))
> > > + (__builtin_ia32_reduceph512_mask_round ((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, \
> > > + _MM_FROUND_CUR_DIRECTION))
> > >
> > > #define _mm512_mask_reduce_ph(A, B, C, D) \
> > > - (__builtin_ia32_vreduceph_v32hf_mask_round ((C), (D), (A), (B), \
> > > - _MM_FROUND_CUR_DIRECTION))
> > > + (__builtin_ia32_reduceph512_mask_round ((C), (D), (A), (B), \
> > > + _MM_FROUND_CUR_DIRECTION))
> > >
> > > #define _mm512_maskz_reduce_ph(A, B, C) \
> > > - (__builtin_ia32_vreduceph_v32hf_mask_round ((B), (C), \
> > > - _mm512_setzero_ph (), \
> > > - (A), _MM_FROUND_CUR_DIRECTION))
> > > + (__builtin_ia32_reduceph512_mask_round ((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), _MM_FROUND_CUR_DIRECTION))
> > >
> > > -#define _mm512_reduce_round_ph(A, B, C) \
> > > - (__builtin_ia32_vreduceph_v32hf_mask_round ((A), (B), \
> > > - _mm512_setzero_ph (), \
> > > - (__mmask32)-1, (C)))
> > > +#define _mm512_reduce_round_ph(A, B, C) \
> > > + (__builtin_ia32_reduceph512_mask_round ((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, (C)))
> > >
> > > #define _mm512_mask_reduce_round_ph(A, B, C, D, E) \
> > > - (__builtin_ia32_vreduceph_v32hf_mask_round ((C), (D), (A), (B), (E)))
> > > + (__builtin_ia32_reduceph512_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm512_maskz_reduce_round_ph(A, B, C, D) \
> > > - (__builtin_ia32_vreduceph_v32hf_mask_round ((B), (C), \
> > > - _mm512_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm512_maskz_reduce_round_ph(A, B, C, D) \
> > > + (__builtin_ia32_reduceph512_mask_round ((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -1718,10 +1718,10 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_reduce_sh (__m128h __A, __m128h __B, int __C)
> > > {
> > > - return __builtin_ia32_vreducesh_v8hf_mask_round (__A, __B, __C,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_reducesh_mask_round (__A, __B, __C,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -1729,26 +1729,26 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_reduce_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, int __E)
> > > {
> > > - return __builtin_ia32_vreducesh_v8hf_mask_round (__C, __D, __E, __A, __B,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_reducesh_mask_round (__C, __D, __E, __A, __B,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_reduce_sh (__mmask8 __A, __m128h __B, __m128h __C, int __D)
> > > {
> > > - return __builtin_ia32_vreducesh_v8hf_mask_round (__B, __C, __D,
> > > - _mm_setzero_ph (), __A,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_reducesh_mask_round (__B, __C, __D,
> > > + _mm_setzero_ph (), __A,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_reduce_round_sh (__m128h __A, __m128h __B, int __C, const int __D)
> > > {
> > > - return __builtin_ia32_vreducesh_v8hf_mask_round (__A, __B, __C,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1, __D);
> > > + return __builtin_ia32_reducesh_mask_round (__A, __B, __C,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1, __D);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -1756,8 +1756,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_reduce_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, int __E, const int __F)
> > > {
> > > - return __builtin_ia32_vreducesh_v8hf_mask_round (__C, __D, __E, __A,
> > > - __B, __F);
> > > + return __builtin_ia32_reducesh_mask_round (__C, __D, __E, __A,
> > > + __B, __F);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -1765,81 +1765,81 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_reduce_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> > > int __D, const int __E)
> > > {
> > > - return __builtin_ia32_vreducesh_v8hf_mask_round (__B, __C, __D,
> > > - _mm_setzero_ph (),
> > > - __A, __E);
> > > + return __builtin_ia32_reducesh_mask_round (__B, __C, __D,
> > > + _mm_setzero_ph (),
> > > + __A, __E);
> > > }
> > >
> > > #else
> > > #define _mm_reduce_sh(A, B, C) \
> > > - (__builtin_ia32_vreducesh_v8hf_mask_round ((A), (B), (C), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, \
> > > - _MM_FROUND_CUR_DIRECTION))
> > > + (__builtin_ia32_reducesh_mask_round ((A), (B), (C), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, \
> > > + _MM_FROUND_CUR_DIRECTION))
> > >
> > > #define _mm_mask_reduce_sh(A, B, C, D, E) \
> > > - (__builtin_ia32_vreducesh_v8hf_mask_round ((C), (D), (E), (A), (B), \
> > > - _MM_FROUND_CUR_DIRECTION))
> > > + (__builtin_ia32_reducesh_mask_round ((C), (D), (E), (A), (B), \
> > > + _MM_FROUND_CUR_DIRECTION))
> > >
> > > #define _mm_maskz_reduce_sh(A, B, C, D) \
> > > - (__builtin_ia32_vreducesh_v8hf_mask_round ((B), (C), (D), \
> > > - _mm_setzero_ph (), \
> > > - (A), _MM_FROUND_CUR_DIRECTION))
> > > + (__builtin_ia32_reducesh_mask_round ((B), (C), (D), \
> > > + _mm_setzero_ph (), \
> > > + (A), _MM_FROUND_CUR_DIRECTION))
> > >
> > > #define _mm_reduce_round_sh(A, B, C, D) \
> > > - (__builtin_ia32_vreducesh_v8hf_mask_round ((A), (B), (C), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, (D)))
> > > + (__builtin_ia32_reducesh_mask_round ((A), (B), (C), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, (D)))
> > >
> > > #define _mm_mask_reduce_round_sh(A, B, C, D, E, F) \
> > > - (__builtin_ia32_vreducesh_v8hf_mask_round ((C), (D), (E), (A), (B), (F)))
> > > + (__builtin_ia32_reducesh_mask_round ((C), (D), (E), (A), (B), (F)))
> > >
> > > #define _mm_maskz_reduce_round_sh(A, B, C, D, E) \
> > > - (__builtin_ia32_vreducesh_v8hf_mask_round ((B), (C), (D), \
> > > - _mm_setzero_ph (), \
> > > - (A), (E)))
> > > + (__builtin_ia32_reducesh_mask_round ((B), (C), (D), \
> > > + _mm_setzero_ph (), \
> > > + (A), (E)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > /* Intrinsics vrndscaleph. */
> > > #ifdef __OPTIMIZE__
> > > extern __inline __m512h
> > > -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > + __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_roundscale_ph (__m512h __A, int __B)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_rndscaleph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_roundscale_ph (__m512h __A, __mmask32 __B,
> > > - __m512h __C, int __D)
> > > + __m512h __C, int __D)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__C, __D, __A, __B,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_rndscaleph512_mask_round (__C, __D, __A, __B,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_roundscale_ph (__mmask32 __A, __m512h __B, int __C)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_rndscaleph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m512h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_roundscale_round_ph (__m512h __A, int __B, const int __C)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__A, __B,
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1,
> > > - __C);
> > > + return __builtin_ia32_rndscaleph512_mask_round (__A, __B,
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1,
> > > + __C);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -1847,8 +1847,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_mask_roundscale_round_ph (__m512h __A, __mmask32 __B,
> > > __m512h __C, int __D, const int __E)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__C, __D, __A,
> > > - __B, __E);
> > > + return __builtin_ia32_rndscaleph512_mask_round (__C, __D, __A,
> > > + __B, __E);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -1856,52 +1856,52 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_roundscale_round_ph (__mmask32 __A, __m512h __B, int __C,
> > > const int __D)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v32hf_mask_round (__B, __C,
> > > - _mm512_setzero_ph (),
> > > - __A, __D);
> > > + return __builtin_ia32_rndscaleph512_mask_round (__B, __C,
> > > + _mm512_setzero_ph (),
> > > + __A, __D);
> > > }
> > >
> > > #else
> > > -#define _mm512_roundscale_ph(A, B) \
> > > - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((A), (B), \
> > > - _mm512_setzero_ph (), \
> > > - (__mmask32)-1, \
> > > - _MM_FROUND_CUR_DIRECTION))
> > > -
> > > -#define _mm512_mask_roundscale_ph(A, B, C, D) \
> > > - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((C), (D), (A), (B), \
> > > - _MM_FROUND_CUR_DIRECTION))
> > > -
> > > -#define _mm512_maskz_roundscale_ph(A, B, C) \
> > > - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((B), (C), \
> > > - _mm512_setzero_ph (), \
> > > - (A), \
> > > - _MM_FROUND_CUR_DIRECTION))
> > > -#define _mm512_roundscale_round_ph(A, B, C) \
> > > - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((A), (B), \
> > > - _mm512_setzero_ph (), \
> > > - (__mmask32)-1, (C)))
> > > +#define _mm512_roundscale_ph(A, B) \
> > > + (__builtin_ia32_rndscaleph512_mask_round ((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, \
> > > + _MM_FROUND_CUR_DIRECTION))
> > > +
> > > +#define _mm512_mask_roundscale_ph(A, B, C, D) \
> > > + (__builtin_ia32_rndscaleph512_mask_round ((C), (D), (A), (B), \
> > > + _MM_FROUND_CUR_DIRECTION))
> > > +
> > > +#define _mm512_maskz_roundscale_ph(A, B, C) \
> > > + (__builtin_ia32_rndscaleph512_mask_round ((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), \
> > > + _MM_FROUND_CUR_DIRECTION))
> > > +#define _mm512_roundscale_round_ph(A, B, C) \
> > > + (__builtin_ia32_rndscaleph512_mask_round ((A), (B), \
> > > + _mm512_setzero_ph (), \
> > > + (__mmask32)-1, (C)))
> > >
> > > #define _mm512_mask_roundscale_round_ph(A, B, C, D, E) \
> > > - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((C), (D), (A), (B), (E)))
> > > + (__builtin_ia32_rndscaleph512_mask_round ((C), (D), (A), (B), (E)))
> > >
> > > -#define _mm512_maskz_roundscale_round_ph(A, B, C, D) \
> > > - (__builtin_ia32_vrndscaleph_v32hf_mask_round ((B), (C), \
> > > - _mm512_setzero_ph (), \
> > > - (A), (D)))
> > > +#define _mm512_maskz_roundscale_round_ph(A, B, C, D) \
> > > + (__builtin_ia32_rndscaleph512_mask_round ((B), (C), \
> > > + _mm512_setzero_ph (), \
> > > + (A), (D)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > /* Intrinsics vrndscalesh. */
> > > #ifdef __OPTIMIZE__
> > > extern __inline __m128h
> > > -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > + __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_roundscale_sh (__m128h __A, __m128h __B, int __C)
> > > {
> > > - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__A, __B, __C,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_rndscalesh_mask_round (__A, __B, __C,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -1909,27 +1909,27 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_roundscale_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, int __E)
> > > {
> > > - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__C, __D, __E, __A, __B,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_rndscalesh_mask_round (__C, __D, __E, __A, __B,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_roundscale_sh (__mmask8 __A, __m128h __B, __m128h __C, int __D)
> > > {
> > > - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__B, __C, __D,
> > > - _mm_setzero_ph (), __A,
> > > - _MM_FROUND_CUR_DIRECTION);
> > > + return __builtin_ia32_rndscalesh_mask_round (__B, __C, __D,
> > > + _mm_setzero_ph (), __A,
> > > + _MM_FROUND_CUR_DIRECTION);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_roundscale_round_sh (__m128h __A, __m128h __B, int __C, const int __D)
> > > {
> > > - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__A, __B, __C,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1,
> > > - __D);
> > > + return __builtin_ia32_rndscalesh_mask_round (__A, __B, __C,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1,
> > > + __D);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -1937,8 +1937,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_roundscale_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
> > > __m128h __D, int __E, const int __F)
> > > {
> > > - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__C, __D, __E,
> > > - __A, __B, __F);
> > > + return __builtin_ia32_rndscalesh_mask_round (__C, __D, __E,
> > > + __A, __B, __F);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -1946,46 +1946,46 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_roundscale_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
> > > int __D, const int __E)
> > > {
> > > - return __builtin_ia32_vrndscalesh_v8hf_mask_round (__B, __C, __D,
> > > - _mm_setzero_ph (),
> > > - __A, __E);
> > > + return __builtin_ia32_rndscalesh_mask_round (__B, __C, __D,
> > > + _mm_setzero_ph (),
> > > + __A, __E);
> > > }
> > >
> > > #else
> > > #define _mm_roundscale_sh(A, B, C) \
> > > - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((A), (B), (C), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, \
> > > - _MM_FROUND_CUR_DIRECTION))
> > > + (__builtin_ia32_rndscalesh_mask_round ((A), (B), (C), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, \
> > > + _MM_FROUND_CUR_DIRECTION))
> > >
> > > #define _mm_mask_roundscale_sh(A, B, C, D, E) \
> > > - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((C), (D), (E), (A), (B), \
> > > - _MM_FROUND_CUR_DIRECTION))
> > > + (__builtin_ia32_rndscalesh_mask_round ((C), (D), (E), (A), (B), \
> > > + _MM_FROUND_CUR_DIRECTION))
> > >
> > > #define _mm_maskz_roundscale_sh(A, B, C, D) \
> > > - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((B), (C), (D), \
> > > - _mm_setzero_ph (), \
> > > - (A), _MM_FROUND_CUR_DIRECTION))
> > > + (__builtin_ia32_rndscalesh_mask_round ((B), (C), (D), \
> > > + _mm_setzero_ph (), \
> > > + (A), _MM_FROUND_CUR_DIRECTION))
> > >
> > > -#define _mm_roundscale_round_sh(A, B, C, D) \
> > > - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((A), (B), (C), \
> > > - _mm_setzero_ph (), \
> > > - (__mmask8)-1, (D)))
> > > +#define _mm_roundscale_round_sh(A, B, C, D) \
> > > + (__builtin_ia32_rndscalesh_mask_round ((A), (B), (C), \
> > > + _mm_setzero_ph (), \
> > > + (__mmask8)-1, (D)))
> > >
> > > #define _mm_mask_roundscale_round_sh(A, B, C, D, E, F) \
> > > - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((C), (D), (E), (A), (B), (F)))
> > > + (__builtin_ia32_rndscalesh_mask_round ((C), (D), (E), (A), (B), (F)))
> > >
> > > -#define _mm_maskz_roundscale_round_sh(A, B, C, D, E) \
> > > - (__builtin_ia32_vrndscalesh_v8hf_mask_round ((B), (C), (D), \
> > > - _mm_setzero_ph (), \
> > > - (A), (E)))
> > > +#define _mm_maskz_roundscale_round_sh(A, B, C, D, E) \
> > > + (__builtin_ia32_rndscalesh_mask_round ((B), (C), (D), \
> > > + _mm_setzero_ph (), \
> > > + (A), (E)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > /* Intrinsics vfpclasssh. */
> > > #ifdef __OPTIMIZE__
> > > extern __inline __mmask8
> > > -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > + __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_fpclass_sh_mask (__m128h __A, const int __imm)
> > > {
> > > return (__mmask8) __builtin_ia32_fpclasssh_mask ((__v8hf) __A, __imm,
> > > @@ -2031,11 +2031,11 @@ _mm512_fpclass_ph_mask (__m512h __A, const int __imm)
> > >
> > > #else
> > > #define _mm512_mask_fpclass_ph_mask(u, x, c) \
> > > - ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x),\
> > > + ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x), \
> > > (int) (c),(__mmask8)(u)))
> > >
> > > #define _mm512_fpclass_ph_mask(x, c) \
> > > - ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x),\
> > > + ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x), \
> > > (int) (c),(__mmask8)-1))
> > > #endif /* __OPIMTIZE__ */
> > >
> > > @@ -2141,9 +2141,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_getexp_round_ph (__m512h __A, const int __R)
> > > {
> > > return (__m512h) __builtin_ia32_getexpph512_mask ((__v32hf) __A,
> > > - (__v32hf)
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) -1, __R);
> > > + (__v32hf)
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) -1, __R);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -2152,8 +2152,8 @@ _mm512_mask_getexp_round_ph (__m512h __W, __mmask32 __U, __m512h __A,
> > > const int __R)
> > > {
> > > return (__m512h) __builtin_ia32_getexpph512_mask ((__v32hf) __A,
> > > - (__v32hf) __W,
> > > - (__mmask32) __U, __R);
> > > + (__v32hf) __W,
> > > + (__mmask32) __U, __R);
> > > }
> > >
> > > extern __inline __m512h
> > > @@ -2161,37 +2161,37 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm512_maskz_getexp_round_ph (__mmask32 __U, __m512h __A, const int __R)
> > > {
> > > return (__m512h) __builtin_ia32_getexpph512_mask ((__v32hf) __A,
> > > - (__v32hf)
> > > - _mm512_setzero_ph (),
> > > - (__mmask32) __U, __R);
> > > + (__v32hf)
> > > + _mm512_setzero_ph (),
> > > + (__mmask32) __U, __R);
> > > }
> > >
> > > #else
> > > -#define _mm_getexp_round_sh(A, B, R) \
> > > - ((__m128h)__builtin_ia32_getexpsh_mask_round((__v8hf)(__m128h)(A), \
> > > - (__v8hf)(__m128h)(B), \
> > > - (__v8hf)_mm_setzero_ph(), \
> > > +#define _mm_getexp_round_sh(A, B, R) \
> > > + ((__m128h)__builtin_ia32_getexpsh_mask_round((__v8hf)(__m128h)(A), \
> > > + (__v8hf)(__m128h)(B), \
> > > + (__v8hf)_mm_setzero_ph(), \
> > > (__mmask8)-1, R))
> > >
> > > -#define _mm_mask_getexp_round_sh(W, U, A, B, C) \
> > > +#define _mm_mask_getexp_round_sh(W, U, A, B, C) \
> > > (__m128h)__builtin_ia32_getexpsh_mask_round(A, B, W, U, C)
> > >
> > > -#define _mm_maskz_getexp_round_sh(U, A, B, C) \
> > > - (__m128h)__builtin_ia32_getexpsh_mask_round(A, B, \
> > > - (__v8hf)_mm_setzero_ph(), \
> > > +#define _mm_maskz_getexp_round_sh(U, A, B, C) \
> > > + (__m128h)__builtin_ia32_getexpsh_mask_round(A, B, \
> > > + (__v8hf)_mm_setzero_ph(), \
> > > U, C)
> > >
> > > -#define _mm512_getexp_round_ph(A, R) \
> > > - ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> > > - (__v32hf)_mm512_setzero_ph(), (__mmask32)-1, R))
> > > +#define _mm512_getexp_round_ph(A, R) \
> > > + ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> > > + (__v32hf)_mm512_setzero_ph(), (__mmask32)-1, R))
> > >
> > > -#define _mm512_mask_getexp_round_ph(W, U, A, R) \
> > > - ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> > > - (__v32hf)(__m512h)(W), (__mmask32)(U), R))
> > > +#define _mm512_mask_getexp_round_ph(W, U, A, R) \
> > > + ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> > > + (__v32hf)(__m512h)(W), (__mmask32)(U), R))
> > >
> > > -#define _mm512_maskz_getexp_round_ph(U, A, R) \
> > > - ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> > > - (__v32hf)_mm512_setzero_ph(), (__mmask32)(U), R))
> > > +#define _mm512_maskz_getexp_round_ph(U, A, R) \
> > > + ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
> > > + (__v32hf)_mm512_setzero_ph(), (__mmask32)(U), R))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > diff --git a/gcc/config/i386/avx512fp16vlintrin.h b/gcc/config/i386/avx512fp16vlintrin.h
> > > index 206d60407fc..e9478792a03 100644
> > > --- a/gcc/config/i386/avx512fp16vlintrin.h
> > > +++ b/gcc/config/i386/avx512fp16vlintrin.h
> > > @@ -53,30 +53,30 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_add_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vaddph_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_addph128_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_add_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> > > {
> > > - return __builtin_ia32_vaddph_v16hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_addph256_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_add_ph (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vaddph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_addph128_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_add_ph (__mmask16 __A, __m256h __B, __m256h __C)
> > > {
> > > - return __builtin_ia32_vaddph_v16hf_mask (__B, __C,
> > > - _mm256_setzero_ph (), __A);
> > > + return __builtin_ia32_addph256_mask (__B, __C,
> > > + _mm256_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -97,30 +97,30 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_sub_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vsubph_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_subph128_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_sub_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> > > {
> > > - return __builtin_ia32_vsubph_v16hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_subph256_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_sub_ph (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vsubph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_subph128_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_sub_ph (__mmask16 __A, __m256h __B, __m256h __C)
> > > {
> > > - return __builtin_ia32_vsubph_v16hf_mask (__B, __C,
> > > - _mm256_setzero_ph (), __A);
> > > + return __builtin_ia32_subph256_mask (__B, __C,
> > > + _mm256_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -141,30 +141,30 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_mul_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vmulph_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_mulph128_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_mul_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> > > {
> > > - return __builtin_ia32_vmulph_v16hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_mulph256_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_mul_ph (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vmulph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_mulph128_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_mul_ph (__mmask16 __A, __m256h __B, __m256h __C)
> > > {
> > > - return __builtin_ia32_vmulph_v16hf_mask (__B, __C,
> > > - _mm256_setzero_ph (), __A);
> > > + return __builtin_ia32_mulph256_mask (__B, __C,
> > > + _mm256_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -185,30 +185,30 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_div_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vdivph_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_divph128_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_div_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> > > {
> > > - return __builtin_ia32_vdivph_v16hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_divph256_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_div_ph (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vdivph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_divph128_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_div_ph (__mmask16 __A, __m256h __B, __m256h __C)
> > > {
> > > - return __builtin_ia32_vdivph_v16hf_mask (__B, __C,
> > > - _mm256_setzero_ph (), __A);
> > > + return __builtin_ia32_divph256_mask (__B, __C,
> > > + _mm256_setzero_ph (), __A);
> > > }
> > >
> > > /* Intrinsics v[max,min]ph. */
> > > @@ -216,96 +216,96 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_max_ph (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vmaxph_v8hf_mask (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > + return __builtin_ia32_maxph128_mask (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_max_ph (__m256h __A, __m256h __B)
> > > {
> > > - return __builtin_ia32_vmaxph_v16hf_mask (__A, __B,
> > > - _mm256_setzero_ph (),
> > > - (__mmask16) -1);
> > > + return __builtin_ia32_maxph256_mask (__A, __B,
> > > + _mm256_setzero_ph (),
> > > + (__mmask16) -1);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_max_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vmaxph_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_maxph128_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_max_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> > > {
> > > - return __builtin_ia32_vmaxph_v16hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_maxph256_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_max_ph (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vmaxph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_maxph128_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_max_ph (__mmask16 __A, __m256h __B, __m256h __C)
> > > {
> > > - return __builtin_ia32_vmaxph_v16hf_mask (__B, __C,
> > > - _mm256_setzero_ph (), __A);
> > > + return __builtin_ia32_maxph256_mask (__B, __C,
> > > + _mm256_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_min_ph (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vminph_v8hf_mask (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > + return __builtin_ia32_minph128_mask (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_min_ph (__m256h __A, __m256h __B)
> > > {
> > > - return __builtin_ia32_vminph_v16hf_mask (__A, __B,
> > > - _mm256_setzero_ph (),
> > > - (__mmask16) -1);
> > > + return __builtin_ia32_minph256_mask (__A, __B,
> > > + _mm256_setzero_ph (),
> > > + (__mmask16) -1);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_min_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vminph_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_minph128_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_min_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
> > > {
> > > - return __builtin_ia32_vminph_v16hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_minph256_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_min_ph (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vminph_v8hf_mask (__B, __C, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_minph128_mask (__B, __C, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_min_ph (__mmask16 __A, __m256h __B, __m256h __C)
> > > {
> > > - return __builtin_ia32_vminph_v16hf_mask (__B, __C,
> > > - _mm256_setzero_ph (), __A);
> > > + return __builtin_ia32_minph256_mask (__B, __C,
> > > + _mm256_setzero_ph (), __A);
> > > }
> > >
> > > /* vcmpph */
> > > @@ -314,8 +314,8 @@ extern __inline __mmask8
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_cmp_ph_mask (__m128h __A, __m128h __B, const int __C)
> > > {
> > > - return (__mmask8) __builtin_ia32_vcmpph_v8hf_mask (__A, __B, __C,
> > > - (__mmask8) -1);
> > > + return (__mmask8) __builtin_ia32_cmpph128_mask (__A, __B, __C,
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __mmask8
> > > @@ -323,15 +323,15 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_cmp_ph_mask (__mmask8 __A, __m128h __B, __m128h __C,
> > > const int __D)
> > > {
> > > - return (__mmask8) __builtin_ia32_vcmpph_v8hf_mask (__B, __C, __D, __A);
> > > + return (__mmask8) __builtin_ia32_cmpph128_mask (__B, __C, __D, __A);
> > > }
> > >
> > > extern __inline __mmask16
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_cmp_ph_mask (__m256h __A, __m256h __B, const int __C)
> > > {
> > > - return (__mmask16) __builtin_ia32_vcmpph_v16hf_mask (__A, __B, __C,
> > > - (__mmask16) -1);
> > > + return (__mmask16) __builtin_ia32_cmpph256_mask (__A, __B, __C,
> > > + (__mmask16) -1);
> > > }
> > >
> > > extern __inline __mmask16
> > > @@ -339,22 +339,22 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_cmp_ph_mask (__mmask16 __A, __m256h __B, __m256h __C,
> > > const int __D)
> > > {
> > > - return (__mmask16) __builtin_ia32_vcmpph_v16hf_mask (__B, __C, __D,
> > > - __A);
> > > + return (__mmask16) __builtin_ia32_cmpph256_mask (__B, __C, __D,
> > > + __A);
> > > }
> > >
> > > #else
> > > -#define _mm_cmp_ph_mask(A, B, C) \
> > > - (__builtin_ia32_vcmpph_v8hf_mask ((A), (B), (C), (-1)))
> > > +#define _mm_cmp_ph_mask(A, B, C) \
> > > + (__builtin_ia32_cmpph128_mask ((A), (B), (C), (-1)))
> > >
> > > -#define _mm_mask_cmp_ph_mask(A, B, C, D) \
> > > - (__builtin_ia32_vcmpph_v8hf_mask ((B), (C), (D), (A)))
> > > +#define _mm_mask_cmp_ph_mask(A, B, C, D) \
> > > + (__builtin_ia32_cmpph128_mask ((B), (C), (D), (A)))
> > >
> > > -#define _mm256_cmp_ph_mask(A, B, C) \
> > > - (__builtin_ia32_vcmpph_v16hf_mask ((A), (B), (C), (-1)))
> > > +#define _mm256_cmp_ph_mask(A, B, C) \
> > > + (__builtin_ia32_cmpph256_mask ((A), (B), (C), (-1)))
> > >
> > > -#define _mm256_mask_cmp_ph_mask(A, B, C, D) \
> > > - (__builtin_ia32_vcmpph_v16hf_mask ((B), (C), (D), (A)))
> > > +#define _mm256_mask_cmp_ph_mask(A, B, C, D) \
> > > + (__builtin_ia32_cmpph256_mask ((B), (C), (D), (A)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -363,46 +363,46 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_sqrt_ph (__m128h __A)
> > > {
> > > - return __builtin_ia32_vsqrtph_v8hf_mask (__A, _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > + return __builtin_ia32_sqrtph128_mask (__A, _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_sqrt_ph (__m256h __A)
> > > {
> > > - return __builtin_ia32_vsqrtph_v16hf_mask (__A, _mm256_setzero_ph (),
> > > - (__mmask16) -1);
> > > + return __builtin_ia32_sqrtph256_mask (__A, _mm256_setzero_ph (),
> > > + (__mmask16) -1);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_sqrt_ph (__m128h __A, __mmask8 __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vsqrtph_v8hf_mask (__C, __A, __B);
> > > + return __builtin_ia32_sqrtph128_mask (__C, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_sqrt_ph (__m256h __A, __mmask16 __B, __m256h __C)
> > > {
> > > - return __builtin_ia32_vsqrtph_v16hf_mask (__C, __A, __B);
> > > + return __builtin_ia32_sqrtph256_mask (__C, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_sqrt_ph (__mmask8 __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vsqrtph_v8hf_mask (__B, _mm_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_sqrtph128_mask (__B, _mm_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_sqrt_ph (__mmask16 __A, __m256h __B)
> > > {
> > > - return __builtin_ia32_vsqrtph_v16hf_mask (__B, _mm256_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_sqrtph256_mask (__B, _mm256_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > /* Intrinsics vrsqrtph. */
> > > @@ -410,45 +410,45 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_rsqrt_ph (__m128h __A)
> > > {
> > > - return __builtin_ia32_vrsqrtph_v8hf_mask (__A, _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > + return __builtin_ia32_rsqrtph128_mask (__A, _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_rsqrt_ph (__m256h __A)
> > > {
> > > - return __builtin_ia32_vrsqrtph_v16hf_mask (__A, _mm256_setzero_ph (),
> > > - (__mmask16) -1);
> > > + return __builtin_ia32_rsqrtph256_mask (__A, _mm256_setzero_ph (),
> > > + (__mmask16) -1);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_rsqrt_ph (__m128h __A, __mmask8 __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vrsqrtph_v8hf_mask (__C, __A, __B);
> > > + return __builtin_ia32_rsqrtph128_mask (__C, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_rsqrt_ph (__m256h __A, __mmask16 __B, __m256h __C)
> > > {
> > > - return __builtin_ia32_vrsqrtph_v16hf_mask (__C, __A, __B);
> > > + return __builtin_ia32_rsqrtph256_mask (__C, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_rsqrt_ph (__mmask8 __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vrsqrtph_v8hf_mask (__B, _mm_setzero_ph (), __A);
> > > + return __builtin_ia32_rsqrtph128_mask (__B, _mm_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_rsqrt_ph (__mmask16 __A, __m256h __B)
> > > {
> > > - return __builtin_ia32_vrsqrtph_v16hf_mask (__B, _mm256_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_rsqrtph256_mask (__B, _mm256_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > /* Intrinsics vrcpph. */
> > > @@ -456,45 +456,45 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_rcp_ph (__m128h __A)
> > > {
> > > - return __builtin_ia32_vrcpph_v8hf_mask (__A, _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > + return __builtin_ia32_rcpph128_mask (__A, _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_rcp_ph (__m256h __A)
> > > {
> > > - return __builtin_ia32_vrcpph_v16hf_mask (__A, _mm256_setzero_ph (),
> > > - (__mmask16) -1);
> > > + return __builtin_ia32_rcpph256_mask (__A, _mm256_setzero_ph (),
> > > + (__mmask16) -1);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_rcp_ph (__m128h __A, __mmask8 __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vrcpph_v8hf_mask (__C, __A, __B);
> > > + return __builtin_ia32_rcpph128_mask (__C, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_rcp_ph (__m256h __A, __mmask16 __B, __m256h __C)
> > > {
> > > - return __builtin_ia32_vrcpph_v16hf_mask (__C, __A, __B);
> > > + return __builtin_ia32_rcpph256_mask (__C, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_rcp_ph (__mmask8 __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vrcpph_v8hf_mask (__B, _mm_setzero_ph (), __A);
> > > + return __builtin_ia32_rcpph128_mask (__B, _mm_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_rcp_ph (__mmask16 __A, __m256h __B)
> > > {
> > > - return __builtin_ia32_vrcpph_v16hf_mask (__B, _mm256_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_rcpph256_mask (__B, _mm256_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > /* Intrinsics vscalefph. */
> > > @@ -502,25 +502,25 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_scalef_ph (__m128h __A, __m128h __B)
> > > {
> > > - return __builtin_ia32_vscalefph_v8hf_mask (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > + return __builtin_ia32_scalefph128_mask (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_scalef_ph (__m256h __A, __m256h __B)
> > > {
> > > - return __builtin_ia32_vscalefph_v16hf_mask (__A, __B,
> > > - _mm256_setzero_ph (),
> > > - (__mmask16) -1);
> > > + return __builtin_ia32_scalefph256_mask (__A, __B,
> > > + _mm256_setzero_ph (),
> > > + (__mmask16) -1);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_scalef_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
> > > {
> > > - return __builtin_ia32_vscalefph_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_scalefph128_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > @@ -528,24 +528,24 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_scalef_ph (__m256h __A, __mmask16 __B, __m256h __C,
> > > __m256h __D)
> > > {
> > > - return __builtin_ia32_vscalefph_v16hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_scalefph256_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_scalef_ph (__mmask8 __A, __m128h __B, __m128h __C)
> > > {
> > > - return __builtin_ia32_vscalefph_v8hf_mask (__B, __C,
> > > - _mm_setzero_ph (), __A);
> > > + return __builtin_ia32_scalefph128_mask (__B, __C,
> > > + _mm_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_scalef_ph (__mmask16 __A, __m256h __B, __m256h __C)
> > > {
> > > - return __builtin_ia32_vscalefph_v16hf_mask (__B, __C,
> > > - _mm256_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_scalefph256_mask (__B, __C,
> > > + _mm256_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > /* Intrinsics vreduceph. */
> > > @@ -554,109 +554,109 @@ extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_reduce_ph (__m128h __A, int __B)
> > > {
> > > - return __builtin_ia32_vreduceph_v8hf_mask (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > + return __builtin_ia32_reduceph128_mask (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_reduce_ph (__m128h __A, __mmask8 __B, __m128h __C, int __D)
> > > {
> > > - return __builtin_ia32_vreduceph_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_reduceph128_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_reduce_ph (__mmask8 __A, __m128h __B, int __C)
> > > {
> > > - return __builtin_ia32_vreduceph_v8hf_mask (__B, __C,
> > > - _mm_setzero_ph (), __A);
> > > + return __builtin_ia32_reduceph128_mask (__B, __C,
> > > + _mm_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_reduce_ph (__m256h __A, int __B)
> > > {
> > > - return __builtin_ia32_vreduceph_v16hf_mask (__A, __B,
> > > - _mm256_setzero_ph (),
> > > - (__mmask16) -1);
> > > + return __builtin_ia32_reduceph256_mask (__A, __B,
> > > + _mm256_setzero_ph (),
> > > + (__mmask16) -1);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_reduce_ph (__m256h __A, __mmask16 __B, __m256h __C, int __D)
> > > {
> > > - return __builtin_ia32_vreduceph_v16hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_reduceph256_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_reduce_ph (__mmask16 __A, __m256h __B, int __C)
> > > {
> > > - return __builtin_ia32_vreduceph_v16hf_mask (__B, __C,
> > > - _mm256_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_reduceph256_mask (__B, __C,
> > > + _mm256_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > #else
> > > -#define _mm_reduce_ph(A, B) \
> > > - (__builtin_ia32_vreduceph_v8hf_mask ((A), (B),\
> > > - _mm_setzero_ph (), \
> > > - ((__mmask8)-1)))
> > > +#define _mm_reduce_ph(A, B) \
> > > + (__builtin_ia32_reduceph128_mask ((A), (B), \
> > > + _mm_setzero_ph (), \
> > > + ((__mmask8)-1)))
> > >
> > > -#define _mm_mask_reduce_ph(A, B, C, D) \
> > > - (__builtin_ia32_vreduceph_v8hf_mask ((C), (D), (A), (B)))
> > > +#define _mm_mask_reduce_ph(A, B, C, D) \
> > > + (__builtin_ia32_reduceph128_mask ((C), (D), (A), (B)))
> > >
> > > -#define _mm_maskz_reduce_ph(A, B, C) \
> > > - (__builtin_ia32_vreduceph_v8hf_mask ((B), (C), _mm_setzero_ph (), (A)))
> > > +#define _mm_maskz_reduce_ph(A, B, C) \
> > > + (__builtin_ia32_reduceph128_mask ((B), (C), _mm_setzero_ph (), (A)))
> > >
> > > #define _mm256_reduce_ph(A, B) \
> > > - (__builtin_ia32_vreduceph_v16hf_mask ((A), (B),\
> > > - _mm256_setzero_ph (), \
> > > - ((__mmask16)-1)))
> > > + (__builtin_ia32_reduceph256_mask ((A), (B), \
> > > + _mm256_setzero_ph (), \
> > > + ((__mmask16)-1)))
> > >
> > > -#define _mm256_mask_reduce_ph(A, B, C, D) \
> > > - (__builtin_ia32_vreduceph_v16hf_mask ((C), (D), (A), (B)))
> > > +#define _mm256_mask_reduce_ph(A, B, C, D) \
> > > + (__builtin_ia32_reduceph256_mask ((C), (D), (A), (B)))
> > >
> > > -#define _mm256_maskz_reduce_ph(A, B, C) \
> > > - (__builtin_ia32_vreduceph_v16hf_mask ((B), (C), _mm256_setzero_ph (), (A)))
> > > +#define _mm256_maskz_reduce_ph(A, B, C) \
> > > + (__builtin_ia32_reduceph256_mask ((B), (C), _mm256_setzero_ph (), (A)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > /* Intrinsics vrndscaleph. */
> > > #ifdef __OPTIMIZE__
> > > -extern __inline __m128h
> > > -__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > -_mm_roundscale_ph (__m128h __A, int __B)
> > > -{
> > > - return __builtin_ia32_vrndscaleph_v8hf_mask (__A, __B,
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > -}
> > > + extern __inline __m128h
> > > + __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > + _mm_roundscale_ph (__m128h __A, int __B)
> > > + {
> > > + return __builtin_ia32_rndscaleph128_mask (__A, __B,
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > + }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_roundscale_ph (__m128h __A, __mmask8 __B, __m128h __C, int __D)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v8hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_rndscaleph128_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m128h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_roundscale_ph (__mmask8 __A, __m128h __B, int __C)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v8hf_mask (__B, __C,
> > > - _mm_setzero_ph (), __A);
> > > + return __builtin_ia32_rndscaleph128_mask (__B, __C,
> > > + _mm_setzero_ph (), __A);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_roundscale_ph (__m256h __A, int __B)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v16hf_mask (__A, __B,
> > > - _mm256_setzero_ph (),
> > > - (__mmask16) -1);
> > > + return __builtin_ia32_rndscaleph256_mask (__A, __B,
> > > + _mm256_setzero_ph (),
> > > + (__mmask16) -1);
> > > }
> > >
> > > extern __inline __m256h
> > > @@ -664,40 +664,40 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_roundscale_ph (__m256h __A, __mmask16 __B, __m256h __C,
> > > int __D)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v16hf_mask (__C, __D, __A, __B);
> > > + return __builtin_ia32_rndscaleph256_mask (__C, __D, __A, __B);
> > > }
> > >
> > > extern __inline __m256h
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_roundscale_ph (__mmask16 __A, __m256h __B, int __C)
> > > {
> > > - return __builtin_ia32_vrndscaleph_v16hf_mask (__B, __C,
> > > - _mm256_setzero_ph (),
> > > - __A);
> > > + return __builtin_ia32_rndscaleph256_mask (__B, __C,
> > > + _mm256_setzero_ph (),
> > > + __A);
> > > }
> > >
> > > #else
> > > -#define _mm_roundscale_ph(A, B) \
> > > - (__builtin_ia32_vrndscaleph_v8hf_mask ((A), (B), _mm_setzero_ph (), \
> > > - ((__mmask8)-1)))
> > > +#define _mm_roundscale_ph(A, B) \
> > > + (__builtin_ia32_rndscaleph128_mask ((A), (B), _mm_setzero_ph (), \
> > > + ((__mmask8)-1)))
> > >
> > > -#define _mm_mask_roundscale_ph(A, B, C, D) \
> > > - (__builtin_ia32_vrndscaleph_v8hf_mask ((C), (D), (A), (B)))
> > > +#define _mm_mask_roundscale_ph(A, B, C, D) \
> > > + (__builtin_ia32_rndscaleph128_mask ((C), (D), (A), (B)))
> > >
> > > -#define _mm_maskz_roundscale_ph(A, B, C) \
> > > - (__builtin_ia32_vrndscaleph_v8hf_mask ((B), (C), _mm_setzero_ph (), (A)))
> > > +#define _mm_maskz_roundscale_ph(A, B, C) \
> > > + (__builtin_ia32_rndscaleph128_mask ((B), (C), _mm_setzero_ph (), (A)))
> > >
> > > -#define _mm256_roundscale_ph(A, B) \
> > > - (__builtin_ia32_vrndscaleph_v16hf_mask ((A), (B), \
> > > - _mm256_setzero_ph(), \
> > > - ((__mmask16)-1)))
> > > +#define _mm256_roundscale_ph(A, B) \
> > > + (__builtin_ia32_rndscaleph256_mask ((A), (B), \
> > > + _mm256_setzero_ph(), \
> > > + ((__mmask16)-1)))
> > >
> > > -#define _mm256_mask_roundscale_ph(A, B, C, D) \
> > > - (__builtin_ia32_vrndscaleph_v16hf_mask ((C), (D), (A), (B)))
> > > +#define _mm256_mask_roundscale_ph(A, B, C, D) \
> > > + (__builtin_ia32_rndscaleph256_mask ((C), (D), (A), (B)))
> > >
> > > -#define _mm256_maskz_roundscale_ph(A, B, C) \
> > > - (__builtin_ia32_vrndscaleph_v16hf_mask ((B), (C), \
> > > - _mm256_setzero_ph (), (A)))
> > > +#define _mm256_maskz_roundscale_ph(A, B, C) \
> > > + (__builtin_ia32_rndscaleph256_mask ((B), (C), \
> > > + _mm256_setzero_ph (), (A)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > @@ -705,7 +705,7 @@ _mm256_maskz_roundscale_ph (__mmask16 __A, __m256h __B, int __C)
> > > #ifdef __OPTIMIZE__
> > > extern __inline __mmask8
> > > __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > -_mm_mask_fpclass_ph_mask (__mmask8 __U, __m128h __A, const int __imm)
> > > + _mm_mask_fpclass_ph_mask (__mmask8 __U, __m128h __A, const int __imm)
> > > {
> > > return (__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) __A,
> > > __imm, __U);
> > > @@ -725,7 +725,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_fpclass_ph_mask (__mmask16 __U, __m256h __A, const int __imm)
> > > {
> > > return (__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) __A,
> > > - __imm, __U);
> > > + __imm, __U);
> > > }
> > >
> > > extern __inline __mmask16
> > > @@ -733,26 +733,26 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_fpclass_ph_mask (__m256h __A, const int __imm)
> > > {
> > > return (__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) __A,
> > > - __imm,
> > > - (__mmask16) -1);
> > > + __imm,
> > > + (__mmask16) -1);
> > > }
> > >
> > > #else
> > > #define _mm_fpclass_ph_mask(X, C) \
> > > - ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
> > > + ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
> > > (int) (C),(__mmask8)-1))
> > >
> > > #define _mm_mask_fpclass_ph_mask(u, X, C) \
> > > - ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
> > > + ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
> > > (int) (C),(__mmask8)(u)))
> > >
> > > #define _mm256_fpclass_ph_mask(X, C) \
> > > - ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
> > > - (int) (C),(__mmask16)-1))
> > > + ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
> > > + (int) (C),(__mmask16)-1))
> > >
> > > #define _mm256_mask_fpclass_ph_mask(u, X, C) \
> > > - ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
> > > - (int) (C),(__mmask16)(u)))
> > > + ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
> > > + (int) (C),(__mmask16)(u)))
> > > #endif /* __OPTIMIZE__ */
> > >
> > > /* Intrinsics vgetexpph, vgetexpsh. */
> > > @@ -761,9 +761,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_getexp_ph (__m256h __A)
> > > {
> > > return (__m256h) __builtin_ia32_getexpph256_mask ((__v16hf) __A,
> > > - (__v16hf)
> > > - _mm256_setzero_ph (),
> > > - (__mmask16) -1);
> > > + (__v16hf)
> > > + _mm256_setzero_ph (),
> > > + (__mmask16) -1);
> > > }
> > >
> > > extern __inline __m256h
> > > @@ -771,8 +771,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_mask_getexp_ph (__m256h __W, __mmask16 __U, __m256h __A)
> > > {
> > > return (__m256h) __builtin_ia32_getexpph256_mask ((__v16hf) __A,
> > > - (__v16hf) __W,
> > > - (__mmask16) __U);
> > > + (__v16hf) __W,
> > > + (__mmask16) __U);
> > > }
> > >
> > > extern __inline __m256h
> > > @@ -780,9 +780,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm256_maskz_getexp_ph (__mmask16 __U, __m256h __A)
> > > {
> > > return (__m256h) __builtin_ia32_getexpph256_mask ((__v16hf) __A,
> > > - (__v16hf)
> > > - _mm256_setzero_ph (),
> > > - (__mmask16) __U);
> > > + (__v16hf)
> > > + _mm256_setzero_ph (),
> > > + (__mmask16) __U);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -790,9 +790,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_getexp_ph (__m128h __A)
> > > {
> > > return (__m128h) __builtin_ia32_getexpph128_mask ((__v8hf) __A,
> > > - (__v8hf)
> > > - _mm_setzero_ph (),
> > > - (__mmask8) -1);
> > > + (__v8hf)
> > > + _mm_setzero_ph (),
> > > + (__mmask8) -1);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -800,8 +800,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_mask_getexp_ph (__m128h __W, __mmask8 __U, __m128h __A)
> > > {
> > > return (__m128h) __builtin_ia32_getexpph128_mask ((__v8hf) __A,
> > > - (__v8hf) __W,
> > > - (__mmask8) __U);
> > > + (__v8hf) __W,
> > > + (__mmask8) __U);
> > > }
> > >
> > > extern __inline __m128h
> > > @@ -809,9 +809,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> > > _mm_maskz_getexp_ph (__mmask8 __U, __m128h __A)
> > > {
> > > return (__m128h) __builtin_ia32_getexpph128_mask ((__v8hf) __A,
> > > - (__v8hf)
> > > - _mm_setzero_ph (),
> > > - (__mmask8) __U);
> > > + (__v8hf)
> > > + _mm_setzero_ph (),
> > > + (__mmask8) __U);
> > > }
> > >
> > >
> > > @@ -892,41 +892,41 @@ _mm_maskz_getmant_ph (__mmask8 __U, __m128h __A,
> > > }
> > >
> > > #else
> > > -#define _mm256_getmant_ph(X, B, C) \
> > > - ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> > > - (int)(((C)<<2) | (B)), \
> > > - (__v16hf)(__m256h)_mm256_setzero_ph (),\
> > > - (__mmask16)-1))
> > > -
> > > -#define _mm256_mask_getmant_ph(W, U, X, B, C) \
> > > - ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> > > - (int)(((C)<<2) | (B)), \
> > > - (__v16hf)(__m256h)(W), \
> > > - (__mmask16)(U)))
> > > -
> > > -#define _mm256_maskz_getmant_ph(U, X, B, C) \
> > > - ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> > > - (int)(((C)<<2) | (B)), \
> > > - (__v16hf)(__m256h)_mm256_setzero_ph (),\
> > > - (__mmask16)(U)))
> > > -
> > > -#define _mm_getmant_ph(X, B, C) \
> > > - ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> > > - (int)(((C)<<2) | (B)), \
> > > - (__v8hf)(__m128h)_mm_setzero_ph (), \
> > > - (__mmask8)-1))
> > > -
> > > -#define _mm_mask_getmant_ph(W, U, X, B, C) \
> > > - ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> > > - (int)(((C)<<2) | (B)), \
> > > - (__v8hf)(__m128h)(W), \
> > > - (__mmask8)(U)))
> > > -
> > > -#define _mm_maskz_getmant_ph(U, X, B, C) \
> > > - ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> > > - (int)(((C)<<2) | (B)), \
> > > - (__v8hf)(__m128h)_mm_setzero_ph (), \
> > > - (__mmask8)(U)))
> > > +#define _mm256_getmant_ph(X, B, C) \
> > > + ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> > > + (int)(((C)<<2) | (B)), \
> > > + (__v16hf)(__m256h)_mm256_setzero_ph (), \
> > > + (__mmask16)-1))
> > > +
> > > +#define _mm256_mask_getmant_ph(W, U, X, B, C) \
> > > + ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> > > + (int)(((C)<<2) | (B)), \
> > > + (__v16hf)(__m256h)(W), \
> > > + (__mmask16)(U)))
> > > +
> > > +#define _mm256_maskz_getmant_ph(U, X, B, C) \
> > > + ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
> > > + (int)(((C)<<2) | (B)), \
> > > + (__v16hf)(__m256h)_mm256_setzero_ph (), \
> > > + (__mmask16)(U)))
> > > +
> > > +#define _mm_getmant_ph(X, B, C) \
> > > + ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> > > + (int)(((C)<<2) | (B)), \
> > > + (__v8hf)(__m128h)_mm_setzero_ph (), \
> > > + (__mmask8)-1))
> > > +
> > > +#define _mm_mask_getmant_ph(W, U, X, B, C) \
> > > + ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> > > + (int)(((C)<<2) | (B)), \
> > > + (__v8hf)(__m128h)(W), \
> > > + (__mmask8)(U)))
> > > +
> > > +#define _mm_maskz_getmant_ph(U, X, B, C) \
> > > + ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
> > > + (int)(((C)<<2) | (B)), \
> > > + (__v8hf)(__m128h)_mm_setzero_ph (), \
> > > + (__mmask8)(U)))
> > >
> > > #endif /* __OPTIMIZE__ */
> > >
> > > diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
> > > index bfa1d56a7b8..10f6fd87cbb 100644
> > > --- a/gcc/config/i386/i386-builtin.def
> > > +++ b/gcc/config/i386/i386-builtin.def
> > > @@ -2775,49 +2775,49 @@ BDESC (0, OPTION_MASK_ISA2_AVX512BF16, CODE_FOR_avx512f_dpbf16ps_v4sf_mask, "__b
> > > BDESC (0, OPTION_MASK_ISA2_AVX512BF16, CODE_FOR_avx512f_dpbf16ps_v4sf_maskz, "__builtin_ia32_dpbf16ps_v4sf_maskz", IX86_BUILTIN_DPHI16PS_V4SF_MASKZ, UNKNOWN, (int) V4SF_FTYPE_V4SF_V8HI_V8HI_UQI)
> > >
> > > /* AVX512FP16. */
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv8hf3_mask, "__builtin_ia32_vaddph_v8hf_mask", IX86_BUILTIN_VADDPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv16hf3_mask, "__builtin_ia32_vaddph_v16hf_mask", IX86_BUILTIN_VADDPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask, "__builtin_ia32_vaddph_v32hf_mask", IX86_BUILTIN_VADDPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv8hf3_mask, "__builtin_ia32_vsubph_v8hf_mask", IX86_BUILTIN_VSUBPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv16hf3_mask, "__builtin_ia32_vsubph_v16hf_mask", IX86_BUILTIN_VSUBPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask, "__builtin_ia32_vsubph_v32hf_mask", IX86_BUILTIN_VSUBPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv8hf3_mask, "__builtin_ia32_vmulph_v8hf_mask", IX86_BUILTIN_VMULPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv16hf3_mask, "__builtin_ia32_vmulph_v16hf_mask", IX86_BUILTIN_VMULPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask, "__builtin_ia32_vmulph_v32hf_mask", IX86_BUILTIN_VMULPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv8hf3_mask, "__builtin_ia32_vdivph_v8hf_mask", IX86_BUILTIN_VDIVPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv16hf3_mask, "__builtin_ia32_vdivph_v16hf_mask", IX86_BUILTIN_VDIVPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask, "__builtin_ia32_vdivph_v32hf_mask", IX86_BUILTIN_VDIVPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask, "__builtin_ia32_vaddsh_v8hf_mask", IX86_BUILTIN_VADDSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask, "__builtin_ia32_vsubsh_v8hf_mask", IX86_BUILTIN_VSUBSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask, "__builtin_ia32_vmulsh_v8hf_mask", IX86_BUILTIN_VMULSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask, "__builtin_ia32_vdivsh_v8hf_mask", IX86_BUILTIN_VDIVSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv8hf3_mask, "__builtin_ia32_vmaxph_v8hf_mask", IX86_BUILTIN_VMAXPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv16hf3_mask, "__builtin_ia32_vmaxph_v16hf_mask", IX86_BUILTIN_VMAXPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask, "__builtin_ia32_vmaxph_v32hf_mask", IX86_BUILTIN_VMAXPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv8hf3_mask, "__builtin_ia32_vminph_v8hf_mask", IX86_BUILTIN_VMINPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv16hf3_mask, "__builtin_ia32_vminph_v16hf_mask", IX86_BUILTIN_VMINPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask, "__builtin_ia32_vminph_v32hf_mask", IX86_BUILTIN_VMINPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask, "__builtin_ia32_vmaxsh_v8hf_mask", IX86_BUILTIN_VMAXSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask, "__builtin_ia32_vminsh_v8hf_mask", IX86_BUILTIN_VMINSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_cmpv8hf3_mask, "__builtin_ia32_vcmpph_v8hf_mask", IX86_BUILTIN_VCMPPH_V8HF_MASK, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_cmpv16hf3_mask, "__builtin_ia32_vcmpph_v16hf_mask", IX86_BUILTIN_VCMPPH_V16HF_MASK, UNKNOWN, (int) UHI_FTYPE_V16HF_V16HF_INT_UHI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask, "__builtin_ia32_vcmpph_v32hf_mask", IX86_BUILTIN_VCMPPH_V32HF_MASK, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv8hf2_mask, "__builtin_ia32_vsqrtph_v8hf_mask", IX86_BUILTIN_VSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv16hf2_mask, "__builtin_ia32_vsqrtph_v16hf_mask", IX86_BUILTIN_VSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv8hf2_mask, "__builtin_ia32_vrsqrtph_v8hf_mask", IX86_BUILTIN_VRSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv16hf2_mask, "__builtin_ia32_vrsqrtph_v16hf_mask", IX86_BUILTIN_VRSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv32hf2_mask, "__builtin_ia32_vrsqrtph_v32hf_mask", IX86_BUILTIN_VRSQRTPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrsqrtv8hf2_mask, "__builtin_ia32_vrsqrtsh_v8hf_mask", IX86_BUILTIN_VRSQRTSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv8hf2_mask, "__builtin_ia32_vrcpph_v8hf_mask", IX86_BUILTIN_VRCPPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv16hf2_mask, "__builtin_ia32_vrcpph_v16hf_mask", IX86_BUILTIN_VRCPPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv32hf2_mask, "__builtin_ia32_vrcpph_v32hf_mask", IX86_BUILTIN_VRCPPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrcpv8hf2_mask, "__builtin_ia32_vrcpsh_v8hf_mask", IX86_BUILTIN_VRCPSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_scalefv8hf_mask, "__builtin_ia32_vscalefph_v8hf_mask", IX86_BUILTIN_VSCALEFPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_scalefv16hf_mask, "__builtin_ia32_vscalefph_v16hf_mask", IX86_BUILTIN_VSCALEFPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv8hf_mask, "__builtin_ia32_vreduceph_v8hf_mask", IX86_BUILTIN_VREDUCEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv16hf_mask, "__builtin_ia32_vreduceph_v16hf_mask", IX86_BUILTIN_VREDUCEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rndscalev8hf_mask, "__builtin_ia32_vrndscaleph_v8hf_mask", IX86_BUILTIN_VRNDSCALEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
> > > -BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_rndscalev16hf_mask, "__builtin_ia32_vrndscaleph_v16hf_mask", IX86_BUILTIN_VRNDSCALEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv8hf3_mask, "__builtin_ia32_addph128_mask", IX86_BUILTIN_VADDPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv16hf3_mask, "__builtin_ia32_addph256_mask", IX86_BUILTIN_VADDPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask, "__builtin_ia32_addph512_mask", IX86_BUILTIN_VADDPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv8hf3_mask, "__builtin_ia32_subph128_mask", IX86_BUILTIN_VSUBPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv16hf3_mask, "__builtin_ia32_subph256_mask", IX86_BUILTIN_VSUBPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask, "__builtin_ia32_subph512_mask", IX86_BUILTIN_VSUBPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv8hf3_mask, "__builtin_ia32_mulph128_mask", IX86_BUILTIN_VMULPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv16hf3_mask, "__builtin_ia32_mulph256_mask", IX86_BUILTIN_VMULPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask, "__builtin_ia32_mulph512_mask", IX86_BUILTIN_VMULPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv8hf3_mask, "__builtin_ia32_divph128_mask", IX86_BUILTIN_VDIVPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv16hf3_mask, "__builtin_ia32_divph256_mask", IX86_BUILTIN_VDIVPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask, "__builtin_ia32_divph512_mask", IX86_BUILTIN_VDIVPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask, "__builtin_ia32_addsh_mask", IX86_BUILTIN_VADDSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask, "__builtin_ia32_subsh_mask", IX86_BUILTIN_VSUBSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask, "__builtin_ia32_mulsh_mask", IX86_BUILTIN_VMULSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask, "__builtin_ia32_divsh_mask", IX86_BUILTIN_VDIVSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv8hf3_mask, "__builtin_ia32_maxph128_mask", IX86_BUILTIN_VMAXPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv16hf3_mask, "__builtin_ia32_maxph256_mask", IX86_BUILTIN_VMAXPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask, "__builtin_ia32_maxph512_mask", IX86_BUILTIN_VMAXPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv8hf3_mask, "__builtin_ia32_minph128_mask", IX86_BUILTIN_VMINPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv16hf3_mask, "__builtin_ia32_minph256_mask", IX86_BUILTIN_VMINPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask, "__builtin_ia32_minph512_mask", IX86_BUILTIN_VMINPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask, "__builtin_ia32_maxsh_mask", IX86_BUILTIN_VMAXSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask, "__builtin_ia32_minsh_mask", IX86_BUILTIN_VMINSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_cmpv8hf3_mask, "__builtin_ia32_cmpph128_mask", IX86_BUILTIN_VCMPPH_V8HF_MASK, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_cmpv16hf3_mask, "__builtin_ia32_cmpph256_mask", IX86_BUILTIN_VCMPPH_V16HF_MASK, UNKNOWN, (int) UHI_FTYPE_V16HF_V16HF_INT_UHI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask, "__builtin_ia32_cmpph512_mask", IX86_BUILTIN_VCMPPH_V32HF_MASK, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv8hf2_mask, "__builtin_ia32_sqrtph128_mask", IX86_BUILTIN_VSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv16hf2_mask, "__builtin_ia32_sqrtph256_mask", IX86_BUILTIN_VSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv8hf2_mask, "__builtin_ia32_rsqrtph128_mask", IX86_BUILTIN_VRSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv16hf2_mask, "__builtin_ia32_rsqrtph256_mask", IX86_BUILTIN_VRSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv32hf2_mask, "__builtin_ia32_rsqrtph512_mask", IX86_BUILTIN_VRSQRTPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrsqrtv8hf2_mask, "__builtin_ia32_rsqrtsh_mask", IX86_BUILTIN_VRSQRTSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv8hf2_mask, "__builtin_ia32_rcpph128_mask", IX86_BUILTIN_VRCPPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv16hf2_mask, "__builtin_ia32_rcpph256_mask", IX86_BUILTIN_VRCPPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv32hf2_mask, "__builtin_ia32_rcpph512_mask", IX86_BUILTIN_VRCPPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrcpv8hf2_mask, "__builtin_ia32_rcpsh_mask", IX86_BUILTIN_VRCPSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_scalefv8hf_mask, "__builtin_ia32_scalefph128_mask", IX86_BUILTIN_VSCALEFPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_scalefv16hf_mask, "__builtin_ia32_scalefph256_mask", IX86_BUILTIN_VSCALEFPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv8hf_mask, "__builtin_ia32_reduceph128_mask", IX86_BUILTIN_VREDUCEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv16hf_mask, "__builtin_ia32_reduceph256_mask", IX86_BUILTIN_VREDUCEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rndscalev8hf_mask, "__builtin_ia32_rndscaleph128_mask", IX86_BUILTIN_VRNDSCALEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
> > > +BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_rndscalev16hf_mask, "__builtin_ia32_rndscaleph256_mask", IX86_BUILTIN_VRNDSCALEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
> > > BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512dq_fpclassv16hf_mask, "__builtin_ia32_fpclassph256_mask", IX86_BUILTIN_FPCLASSPH256, UNKNOWN, (int) HI_FTYPE_V16HF_INT_UHI)
> > > BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512dq_fpclassv8hf_mask, "__builtin_ia32_fpclassph128_mask", IX86_BUILTIN_FPCLASSPH128, UNKNOWN, (int) QI_FTYPE_V8HF_INT_UQI)
> > > BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512dq_fpclassv32hf_mask, "__builtin_ia32_fpclassph512_mask", IX86_BUILTIN_FPCLASSPH512, UNKNOWN, (int) SI_FTYPE_V32HF_INT_USI)
> > > @@ -3027,28 +3027,28 @@ BDESC (OPTION_MASK_ISA_AVX512DQ, 0, CODE_FOR_avx512dq_rangepv16sf_mask_round, "_
> > > BDESC (OPTION_MASK_ISA_AVX512DQ, 0, CODE_FOR_avx512dq_rangepv8df_mask_round, "__builtin_ia32_rangepd512_mask", IX86_BUILTIN_RANGEPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_INT_V8DF_QI_INT)
> > >
> > > /* AVX512FP16. */
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask_round, "__builtin_ia32_vaddph_v32hf_mask_round", IX86_BUILTIN_VADDPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask_round, "__builtin_ia32_vsubph_v32hf_mask_round", IX86_BUILTIN_VSUBPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask_round, "__builtin_ia32_vmulph_v32hf_mask_round", IX86_BUILTIN_VMULPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask_round, "__builtin_ia32_vdivph_v32hf_mask_round", IX86_BUILTIN_VDIVPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask_round, "__builtin_ia32_vaddsh_v8hf_mask_round", IX86_BUILTIN_VADDSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask_round, "__builtin_ia32_vsubsh_v8hf_mask_round", IX86_BUILTIN_VSUBSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask_round, "__builtin_ia32_vmulsh_v8hf_mask_round", IX86_BUILTIN_VMULSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask_round, "__builtin_ia32_vdivsh_v8hf_mask_round", IX86_BUILTIN_VDIVSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask_round, "__builtin_ia32_vmaxph_v32hf_mask_round", IX86_BUILTIN_VMAXPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask_round, "__builtin_ia32_vminph_v32hf_mask_round", IX86_BUILTIN_VMINPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask_round, "__builtin_ia32_vmaxsh_v8hf_mask_round", IX86_BUILTIN_VMAXSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask_round, "__builtin_ia32_vminsh_v8hf_mask_round", IX86_BUILTIN_VMINSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask_round, "__builtin_ia32_vcmpph_v32hf_mask_round", IX86_BUILTIN_VCMPPH_V32HF_MASK_ROUND, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmcmpv8hf3_mask_round, "__builtin_ia32_vcmpsh_v8hf_mask_round", IX86_BUILTIN_VCMPSH_V8HF_MASK_ROUND, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv32hf2_mask_round, "__builtin_ia32_vsqrtph_v32hf_mask_round", IX86_BUILTIN_VSQRTPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsqrtv8hf2_mask_round, "__builtin_ia32_vsqrtsh_v8hf_mask_round", IX86_BUILTIN_VSQRTSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_scalefv32hf_mask_round, "__builtin_ia32_vscalefph_v32hf_mask_round", IX86_BUILTIN_VSCALEFPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmscalefv8hf_mask_round, "__builtin_ia32_vscalefsh_v8hf_mask_round", IX86_BUILTIN_VSCALEFSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv32hf_mask_round, "__builtin_ia32_vreduceph_v32hf_mask_round", IX86_BUILTIN_VREDUCEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducesv8hf_mask_round, "__builtin_ia32_vreducesh_v8hf_mask_round", IX86_BUILTIN_VREDUCESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_rndscalev32hf_mask_round, "__builtin_ia32_vrndscaleph_v32hf_mask_round", IX86_BUILTIN_VRNDSCALEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
> > > -BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_rndscalev8hf_mask_round, "__builtin_ia32_vrndscalesh_v8hf_mask_round", IX86_BUILTIN_VRNDSCALESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask_round, "__builtin_ia32_addph512_mask_round", IX86_BUILTIN_VADDPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask_round, "__builtin_ia32_subph512_mask_round", IX86_BUILTIN_VSUBPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask_round, "__builtin_ia32_mulph512_mask_round", IX86_BUILTIN_VMULPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask_round, "__builtin_ia32_divph512_mask_round", IX86_BUILTIN_VDIVPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask_round, "__builtin_ia32_addsh_mask_round", IX86_BUILTIN_VADDSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask_round, "__builtin_ia32_subsh_mask_round", IX86_BUILTIN_VSUBSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask_round, "__builtin_ia32_mulsh_mask_round", IX86_BUILTIN_VMULSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask_round, "__builtin_ia32_divsh_mask_round", IX86_BUILTIN_VDIVSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask_round, "__builtin_ia32_maxph512_mask_round", IX86_BUILTIN_VMAXPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask_round, "__builtin_ia32_minph512_mask_round", IX86_BUILTIN_VMINPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask_round, "__builtin_ia32_maxsh_mask_round", IX86_BUILTIN_VMAXSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask_round, "__builtin_ia32_minsh_mask_round", IX86_BUILTIN_VMINSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask_round, "__builtin_ia32_cmpph512_mask_round", IX86_BUILTIN_VCMPPH_V32HF_MASK_ROUND, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmcmpv8hf3_mask_round, "__builtin_ia32_cmpsh_mask_round", IX86_BUILTIN_VCMPSH_V8HF_MASK_ROUND, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv32hf2_mask_round, "__builtin_ia32_sqrtph512_mask_round", IX86_BUILTIN_VSQRTPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsqrtv8hf2_mask_round, "__builtin_ia32_sqrtsh_mask_round", IX86_BUILTIN_VSQRTSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_scalefv32hf_mask_round, "__builtin_ia32_scalefph512_mask_round", IX86_BUILTIN_VSCALEFPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmscalefv8hf_mask_round, "__builtin_ia32_scalefsh_mask_round", IX86_BUILTIN_VSCALEFSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv32hf_mask_round, "__builtin_ia32_reduceph512_mask_round", IX86_BUILTIN_VREDUCEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducesv8hf_mask_round, "__builtin_ia32_reducesh_mask_round", IX86_BUILTIN_VREDUCESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_rndscalev32hf_mask_round, "__builtin_ia32_rndscaleph512_mask_round", IX86_BUILTIN_VRNDSCALEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
> > > +BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_rndscalev8hf_mask_round, "__builtin_ia32_rndscalesh_mask_round", IX86_BUILTIN_VRNDSCALESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
> > > BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_getexpv32hf_mask_round, "__builtin_ia32_getexpph512_mask", IX86_BUILTIN_GETEXPPH512, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI_INT)
> > > BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_sgetexpv8hf_mask_round, "__builtin_ia32_getexpsh_mask_round", IX86_BUILTIN_GETEXPSH_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
> > > BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_getmantv32hf_mask_round, "__builtin_ia32_getmantph512_mask", IX86_BUILTIN_GETMANTPH512, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
> > > diff --git a/gcc/testsuite/gcc.target/i386/avx-1.c b/gcc/testsuite/gcc.target/i386/avx-1.c
> > > index b3cffa0644f..3a96e586418 100644
> > > --- a/gcc/testsuite/gcc.target/i386/avx-1.c
> > > +++ b/gcc/testsuite/gcc.target/i386/avx-1.c
> > > @@ -686,33 +686,33 @@
> > > #define __builtin_ia32_vpshld_v2di_mask(A, B, C, D, E) __builtin_ia32_vpshld_v2di_mask(A, B, 1, D, E)
> > >
> > > /* avx512fp16intrin.h */
> > > -#define __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vcmpph_v32hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v32hf_mask(A, B, 1, D)
> > > -#define __builtin_ia32_vcmpph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpph_v32hf_mask_round(A, B, 1, D, 8)
> > > -#define __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, 1, D, 8)
> > > -#define __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, D) __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, 8)
> > > -#define __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, E) __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, 8)
> > > -#define __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vreduceph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vreduceph_v32hf_mask_round(A, 123, C, D, 8)
> > > -#define __builtin_ia32_vreduceph_v8hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v8hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vreduceph_v16hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v16hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vreducesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vreducesh_v8hf_mask_round(A, B, 123, D, E, 8)
> > > -#define __builtin_ia32_vrndscaleph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vrndscaleph_v32hf_mask_round(A, 123, C, D, 8)
> > > -#define __builtin_ia32_vrndscaleph_v8hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v8hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vrndscaleph_v16hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v16hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, 123, D, E, 8)
> > > +#define __builtin_ia32_addph512_mask_round(A, B, C, D, E) __builtin_ia32_addph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_subph512_mask_round(A, B, C, D, E) __builtin_ia32_subph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_mulph512_mask_round(A, B, C, D, E) __builtin_ia32_mulph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_divph512_mask_round(A, B, C, D, E) __builtin_ia32_divph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_addsh_mask_round(A, B, C, D, E) __builtin_ia32_addsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_subsh_mask_round(A, B, C, D, E) __builtin_ia32_subsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_mulsh_mask_round(A, B, C, D, E) __builtin_ia32_mulsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_divsh_mask_round(A, B, C, D, E) __builtin_ia32_divsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_maxph512_mask_round(A, B, C, D, E) __builtin_ia32_maxph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_minph512_mask_round(A, B, C, D, E) __builtin_ia32_minph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_maxsh_mask_round(A, B, C, D, E) __builtin_ia32_maxsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_minsh_mask_round(A, B, C, D, E) __builtin_ia32_minsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_cmpph512_mask(A, B, C, D) __builtin_ia32_cmpph512_mask(A, B, 1, D)
> > > +#define __builtin_ia32_cmpph512_mask_round(A, B, C, D, E) __builtin_ia32_cmpph512_mask_round(A, B, 1, D, 8)
> > > +#define __builtin_ia32_cmpsh_mask_round(A, B, C, D, E) __builtin_ia32_cmpsh_mask_round(A, B, 1, D, 8)
> > > +#define __builtin_ia32_sqrtph512_mask_round(C, A, B, D) __builtin_ia32_sqrtph512_mask_round(C, A, B, 8)
> > > +#define __builtin_ia32_sqrtsh_mask_round(D, C, A, B, E) __builtin_ia32_sqrtsh_mask_round(D, C, A, B, 8)
> > > +#define __builtin_ia32_scalefph512_mask_round(A, B, C, D, E) __builtin_ia32_scalefph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_scalefsh_mask_round(A, B, C, D, E) __builtin_ia32_scalefsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_reduceph512_mask_round(A, B, C, D, E) __builtin_ia32_reduceph512_mask_round(A, 123, C, D, 8)
> > > +#define __builtin_ia32_reduceph128_mask(A, B, C, D) __builtin_ia32_reduceph128_mask(A, 123, C, D)
> > > +#define __builtin_ia32_reduceph256_mask(A, B, C, D) __builtin_ia32_reduceph256_mask(A, 123, C, D)
> > > +#define __builtin_ia32_reducesh_mask_round(A, B, C, D, E, F) __builtin_ia32_reducesh_mask_round(A, B, 123, D, E, 8)
> > > +#define __builtin_ia32_rndscaleph512_mask_round(A, B, C, D, E) __builtin_ia32_rndscaleph512_mask_round(A, 123, C, D, 8)
> > > +#define __builtin_ia32_rndscaleph128_mask(A, B, C, D) __builtin_ia32_rndscaleph128_mask(A, 123, C, D)
> > > +#define __builtin_ia32_rndscaleph256_mask(A, B, C, D) __builtin_ia32_rndscaleph256_mask(A, 123, C, D)
> > > +#define __builtin_ia32_rndscalesh_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesh_mask_round(A, B, 123, D, E, 8)
> > > #define __builtin_ia32_fpclassph512_mask(A, D, C) __builtin_ia32_fpclassph512_mask(A, 1, C)
> > > #define __builtin_ia32_fpclasssh_mask(A, D, U) __builtin_ia32_fpclasssh_mask(A, 1, U)
> > > #define __builtin_ia32_getexpph512_mask(A, B, C, D) __builtin_ia32_getexpph512_mask(A, B, C, 8)
> > > @@ -721,8 +721,8 @@
> > > #define __builtin_ia32_getmantsh_mask_round(A, B, C, W, U, D) __builtin_ia32_getmantsh_mask_round(A, B, 1, W, U, 4)
> > >
> > > /* avx512fp16vlintrin.h */
> > > -#define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
> > > -#define __builtin_ia32_vcmpph_v16hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v16hf_mask(A, B, 1, D)
> > > +#define __builtin_ia32_cmpph128_mask(A, B, C, D) __builtin_ia32_cmpph128_mask(A, B, 1, D)
> > > +#define __builtin_ia32_cmpph256_mask(A, B, C, D) __builtin_ia32_cmpph256_mask(A, B, 1, D)
> > > #define __builtin_ia32_fpclassph256_mask(A, D, C) __builtin_ia32_fpclassph256_mask(A, 1, C)
> > > #define __builtin_ia32_fpclassph128_mask(A, D, C) __builtin_ia32_fpclassph128_mask(A, 1, C)
> > > #define __builtin_ia32_getmantph256_mask(A, E, C, D) __builtin_ia32_getmantph256_mask(A, 1, C, D)
> > > diff --git a/gcc/testsuite/gcc.target/i386/sse-13.c b/gcc/testsuite/gcc.target/i386/sse-13.c
> > > index 67ef567e437..aafcd414530 100644
> > > --- a/gcc/testsuite/gcc.target/i386/sse-13.c
> > > +++ b/gcc/testsuite/gcc.target/i386/sse-13.c
> > > @@ -703,33 +703,33 @@
> > > #define __builtin_ia32_vpshld_v2di_mask(A, B, C, D, E) __builtin_ia32_vpshld_v2di_mask(A, B, 1, D, E)
> > >
> > > /* avx512fp16intrin.h */
> > > -#define __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vcmpph_v32hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v32hf_mask(A, B, 1, D)
> > > -#define __builtin_ia32_vcmpph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpph_v32hf_mask_round(A, B, 1, D, 8)
> > > -#define __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, 1, D, 8)
> > > -#define __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, D) __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, 8)
> > > -#define __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, E) __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, 8)
> > > -#define __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vreduceph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vreduceph_v32hf_mask_round(A, 123, C, D, 8)
> > > -#define __builtin_ia32_vreduceph_v8hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v8hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vreduceph_v16hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v16hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vreducesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vreducesh_v8hf_mask_round(A, B, 123, D, E, 8)
> > > -#define __builtin_ia32_vrndscaleph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vrndscaleph_v32hf_mask_round(A, 123, C, D, 8)
> > > -#define __builtin_ia32_vrndscaleph_v8hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v8hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vrndscaleph_v16hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v16hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, 123, D, E, 8)
> > > +#define __builtin_ia32_addph512_mask_round(A, B, C, D, E) __builtin_ia32_addph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_subph512_mask_round(A, B, C, D, E) __builtin_ia32_subph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_mulph512_mask_round(A, B, C, D, E) __builtin_ia32_mulph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_divph512_mask_round(A, B, C, D, E) __builtin_ia32_divph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_addsh_mask_round(A, B, C, D, E) __builtin_ia32_addsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_subsh_mask_round(A, B, C, D, E) __builtin_ia32_subsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_mulsh_mask_round(A, B, C, D, E) __builtin_ia32_mulsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_divsh_mask_round(A, B, C, D, E) __builtin_ia32_divsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_maxph512_mask_round(A, B, C, D, E) __builtin_ia32_maxph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_minph512_mask_round(A, B, C, D, E) __builtin_ia32_minph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_maxsh_mask_round(A, B, C, D, E) __builtin_ia32_maxsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_minsh_mask_round(A, B, C, D, E) __builtin_ia32_minsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_cmpph512_mask(A, B, C, D) __builtin_ia32_cmpph512_mask(A, B, 1, D)
> > > +#define __builtin_ia32_cmpph512_mask_round(A, B, C, D, E) __builtin_ia32_cmpph512_mask_round(A, B, 1, D, 8)
> > > +#define __builtin_ia32_cmpsh_mask_round(A, B, C, D, E) __builtin_ia32_cmpsh_mask_round(A, B, 1, D, 8)
> > > +#define __builtin_ia32_sqrtph512_mask_round(C, A, B, D) __builtin_ia32_sqrtph512_mask_round(C, A, B, 8)
> > > +#define __builtin_ia32_sqrtsh_mask_round(D, C, A, B, E) __builtin_ia32_sqrtsh_mask_round(D, C, A, B, 8)
> > > +#define __builtin_ia32_scalefph512_mask_round(A, B, C, D, E) __builtin_ia32_scalefph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_scalefsh_mask_round(A, B, C, D, E) __builtin_ia32_scalefsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_reduceph512_mask_round(A, B, C, D, E) __builtin_ia32_reduceph512_mask_round(A, 123, C, D, 8)
> > > +#define __builtin_ia32_reduceph128_mask(A, B, C, D) __builtin_ia32_reduceph128_mask(A, 123, C, D)
> > > +#define __builtin_ia32_reduceph256_mask(A, B, C, D) __builtin_ia32_reduceph256_mask(A, 123, C, D)
> > > +#define __builtin_ia32_reducesh_mask_round(A, B, C, D, E, F) __builtin_ia32_reducesh_mask_round(A, B, 123, D, E, 8)
> > > +#define __builtin_ia32_rndscaleph512_mask_round(A, B, C, D, E) __builtin_ia32_rndscaleph512_mask_round(A, 123, C, D, 8)
> > > +#define __builtin_ia32_rndscaleph128_mask(A, B, C, D) __builtin_ia32_rndscaleph128_mask(A, 123, C, D)
> > > +#define __builtin_ia32_rndscaleph256_mask(A, B, C, D) __builtin_ia32_rndscaleph256_mask(A, 123, C, D)
> > > +#define __builtin_ia32_rndscalesh_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesh_mask_round(A, B, 123, D, E, 8)
> > > #define __builtin_ia32_fpclassph512_mask(A, D, C) __builtin_ia32_fpclassph512_mask(A, 1, C)
> > > #define __builtin_ia32_fpclasssh_mask(A, D, U) __builtin_ia32_fpclasssh_mask(A, 1, U)
> > > #define __builtin_ia32_getexpph512_mask(A, B, C, D) __builtin_ia32_getexpph512_mask(A, B, C, 8)
> > > @@ -738,8 +738,8 @@
> > > #define __builtin_ia32_getmantsh_mask_round(A, B, C, W, U, D) __builtin_ia32_getmantsh_mask_round(A, B, 1, W, U, 4)
> > >
> > > /* avx512fp16vlintrin.h */
> > > -#define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
> > > -#define __builtin_ia32_vcmpph_v16hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v16hf_mask(A, B, 1, D)
> > > +#define __builtin_ia32_cmpph128_mask(A, B, C, D) __builtin_ia32_cmpph128_mask(A, B, 1, D)
> > > +#define __builtin_ia32_cmpph256_mask(A, B, C, D) __builtin_ia32_cmpph256_mask(A, B, 1, D)
> > > #define __builtin_ia32_fpclassph256_mask(A, D, C) __builtin_ia32_fpclassph256_mask(A, 1, C)
> > > #define __builtin_ia32_fpclassph128_mask(A, D, C) __builtin_ia32_fpclassph128_mask(A, 1, C)
> > > #define __builtin_ia32_getmantph256_mask(A, E, C, D) __builtin_ia32_getmantph256_mask(A, 1, C, D)
> > > diff --git a/gcc/testsuite/gcc.target/i386/sse-23.c b/gcc/testsuite/gcc.target/i386/sse-23.c
> > > index b3f07587acb..8b600282c67 100644
> > > --- a/gcc/testsuite/gcc.target/i386/sse-23.c
> > > +++ b/gcc/testsuite/gcc.target/i386/sse-23.c
> > > @@ -704,33 +704,33 @@
> > > #define __builtin_ia32_vpshld_v2di_mask(A, B, C, D, E) __builtin_ia32_vpshld_v2di_mask(A, B, 1, D, E)
> > >
> > > /* avx512fp16intrin.h */
> > > -#define __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vcmpph_v32hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v32hf_mask(A, B, 1, D)
> > > -#define __builtin_ia32_vcmpph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpph_v32hf_mask_round(A, B, 1, D, 8)
> > > -#define __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, 1, D, 8)
> > > -#define __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, D) __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, 8)
> > > -#define __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, E) __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, 8)
> > > -#define __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, 8)
> > > -#define __builtin_ia32_vreduceph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vreduceph_v32hf_mask_round(A, 123, C, D, 8)
> > > -#define __builtin_ia32_vreduceph_v8hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v8hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vreduceph_v16hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v16hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vreducesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vreducesh_v8hf_mask_round(A, B, 123, D, E, 8)
> > > -#define __builtin_ia32_vrndscaleph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vrndscaleph_v32hf_mask_round(A, 123, C, D, 8)
> > > -#define __builtin_ia32_vrndscaleph_v8hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v8hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vrndscaleph_v16hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v16hf_mask(A, 123, C, D)
> > > -#define __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, 123, D, E, 8)
> > > +#define __builtin_ia32_addph512_mask_round(A, B, C, D, E) __builtin_ia32_addph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_subph512_mask_round(A, B, C, D, E) __builtin_ia32_subph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_mulph512_mask_round(A, B, C, D, E) __builtin_ia32_mulph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_divph512_mask_round(A, B, C, D, E) __builtin_ia32_divph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_addsh_mask_round(A, B, C, D, E) __builtin_ia32_addsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_subsh_mask_round(A, B, C, D, E) __builtin_ia32_subsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_mulsh_mask_round(A, B, C, D, E) __builtin_ia32_mulsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_divsh_mask_round(A, B, C, D, E) __builtin_ia32_divsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_maxph512_mask_round(A, B, C, D, E) __builtin_ia32_maxph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_minph512_mask_round(A, B, C, D, E) __builtin_ia32_minph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_maxsh_mask_round(A, B, C, D, E) __builtin_ia32_maxsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_minsh_mask_round(A, B, C, D, E) __builtin_ia32_minsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_cmpph512_mask(A, B, C, D) __builtin_ia32_cmpph512_mask(A, B, 1, D)
> > > +#define __builtin_ia32_cmpph512_mask_round(A, B, C, D, E) __builtin_ia32_cmpph512_mask_round(A, B, 1, D, 8)
> > > +#define __builtin_ia32_cmpsh_mask_round(A, B, C, D, E) __builtin_ia32_cmpsh_mask_round(A, B, 1, D, 8)
> > > +#define __builtin_ia32_sqrtph512_mask_round(C, A, B, D) __builtin_ia32_sqrtph512_mask_round(C, A, B, 8)
> > > +#define __builtin_ia32_sqrtsh_mask_round(D, C, A, B, E) __builtin_ia32_sqrtsh_mask_round(D, C, A, B, 8)
> > > +#define __builtin_ia32_scalefph512_mask_round(A, B, C, D, E) __builtin_ia32_scalefph512_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_scalefsh_mask_round(A, B, C, D, E) __builtin_ia32_scalefsh_mask_round(A, B, C, D, 8)
> > > +#define __builtin_ia32_reduceph512_mask_round(A, B, C, D, E) __builtin_ia32_reduceph512_mask_round(A, 123, C, D, 8)
> > > +#define __builtin_ia32_reduceph128_mask(A, B, C, D) __builtin_ia32_reduceph128_mask(A, 123, C, D)
> > > +#define __builtin_ia32_reduceph256_mask(A, B, C, D) __builtin_ia32_reduceph256_mask(A, 123, C, D)
> > > +#define __builtin_ia32_reducesh_mask_round(A, B, C, D, E, F) __builtin_ia32_reducesh_mask_round(A, B, 123, D, E, 8)
> > > +#define __builtin_ia32_rndscaleph512_mask_round(A, B, C, D, E) __builtin_ia32_rndscaleph512_mask_round(A, 123, C, D, 8)
> > > +#define __builtin_ia32_rndscaleph128_mask(A, B, C, D) __builtin_ia32_rndscaleph128_mask(A, 123, C, D)
> > > +#define __builtin_ia32_rndscaleph256_mask(A, B, C, D) __builtin_ia32_rndscaleph256_mask(A, 123, C, D)
> > > +#define __builtin_ia32_rndscalesh_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesh_mask_round(A, B, 123, D, E, 8)
> > > #define __builtin_ia32_fpclassph512_mask(A, D, C) __builtin_ia32_fpclassph512_mask(A, 1, C)
> > > #define __builtin_ia32_fpclasssh_mask(A, D, U) __builtin_ia32_fpclasssh_mask(A, 1, U)
> > > #define __builtin_ia32_getexpph512_mask(A, B, C, D) __builtin_ia32_getexpph512_mask(A, B, C, 8)
> > > @@ -739,8 +739,8 @@
> > > #define __builtin_ia32_getmantsh_mask_round(A, B, C, W, U, D) __builtin_ia32_getmantsh_mask_round(A, B, 1, W, U, 4)
> > >
> > > /* avx512fp16vlintrin.h */
> > > -#define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
> > > -#define __builtin_ia32_vcmpph_v16hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v16hf_mask(A, B, 1, D)
> > > +#define __builtin_ia32_cmpph128_mask(A, B, C, D) __builtin_ia32_cmpph128_mask(A, B, 1, D)
> > > +#define __builtin_ia32_cmpph256_mask(A, B, C, D) __builtin_ia32_cmpph256_mask(A, B, 1, D)
> > > #define __builtin_ia32_fpclassph256_mask(A, D, C) __builtin_ia32_fpclassph256_mask(A, 1, C)
> > > #define __builtin_ia32_fpclassph128_mask(A, D, C) __builtin_ia32_fpclassph128_mask(A, 1, C)
> > > #define __builtin_ia32_getmantph256_mask(A, E, C, D) __builtin_ia32_getmantph256_mask(A, 1, C, D)
> > > --
> > > 2.18.1
> > >
> >
> >
> > --
> > BR,
> > Hongtao
@@ -229,15 +229,15 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_add_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
{
- return __builtin_ia32_vaddph_v32hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_addph512_mask (__C, __D, __A, __B);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_add_ph (__mmask32 __A, __m512h __B, __m512h __C)
{
- return __builtin_ia32_vaddph_v32hf_mask (__B, __C,
- _mm512_setzero_ph (), __A);
+ return __builtin_ia32_addph512_mask (__B, __C,
+ _mm512_setzero_ph (), __A);
}
extern __inline __m512h
@@ -251,15 +251,15 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_sub_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
{
- return __builtin_ia32_vsubph_v32hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_subph512_mask (__C, __D, __A, __B);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_sub_ph (__mmask32 __A, __m512h __B, __m512h __C)
{
- return __builtin_ia32_vsubph_v32hf_mask (__B, __C,
- _mm512_setzero_ph (), __A);
+ return __builtin_ia32_subph512_mask (__B, __C,
+ _mm512_setzero_ph (), __A);
}
extern __inline __m512h
@@ -273,15 +273,15 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_mul_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
{
- return __builtin_ia32_vmulph_v32hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_mulph512_mask (__C, __D, __A, __B);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_mul_ph (__mmask32 __A, __m512h __B, __m512h __C)
{
- return __builtin_ia32_vmulph_v32hf_mask (__B, __C,
- _mm512_setzero_ph (), __A);
+ return __builtin_ia32_mulph512_mask (__B, __C,
+ _mm512_setzero_ph (), __A);
}
extern __inline __m512h
@@ -295,15 +295,15 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_div_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
{
- return __builtin_ia32_vdivph_v32hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_divph512_mask (__C, __D, __A, __B);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_div_ph (__mmask32 __A, __m512h __B, __m512h __C)
{
- return __builtin_ia32_vdivph_v32hf_mask (__B, __C,
- _mm512_setzero_ph (), __A);
+ return __builtin_ia32_divph512_mask (__B, __C,
+ _mm512_setzero_ph (), __A);
}
#ifdef __OPTIMIZE__
@@ -311,9 +311,9 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_add_round_ph (__m512h __A, __m512h __B, const int __C)
{
- return __builtin_ia32_vaddph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1, __C);
+ return __builtin_ia32_addph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1, __C);
}
extern __inline __m512h
@@ -321,7 +321,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_add_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
__m512h __D, const int __E)
{
- return __builtin_ia32_vaddph_v32hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_addph512_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m512h
@@ -329,18 +329,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_add_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
const int __D)
{
- return __builtin_ia32_vaddph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_addph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A, __D);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_sub_round_ph (__m512h __A, __m512h __B, const int __C)
{
- return __builtin_ia32_vsubph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1, __C);
+ return __builtin_ia32_subph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1, __C);
}
extern __inline __m512h
@@ -348,7 +348,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_sub_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
__m512h __D, const int __E)
{
- return __builtin_ia32_vsubph_v32hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_subph512_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m512h
@@ -356,18 +356,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_sub_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
const int __D)
{
- return __builtin_ia32_vsubph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_subph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A, __D);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mul_round_ph (__m512h __A, __m512h __B, const int __C)
{
- return __builtin_ia32_vmulph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1, __C);
+ return __builtin_ia32_mulph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1, __C);
}
extern __inline __m512h
@@ -375,7 +375,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_mul_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
__m512h __D, const int __E)
{
- return __builtin_ia32_vmulph_v32hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_mulph512_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m512h
@@ -383,18 +383,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_mul_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
const int __D)
{
- return __builtin_ia32_vmulph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_mulph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A, __D);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_div_round_ph (__m512h __A, __m512h __B, const int __C)
{
- return __builtin_ia32_vdivph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1, __C);
+ return __builtin_ia32_divph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1, __C);
}
extern __inline __m512h
@@ -402,7 +402,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_div_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
__m512h __D, const int __E)
{
- return __builtin_ia32_vdivph_v32hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_divph512_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m512h
@@ -410,67 +410,67 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_div_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
const int __D)
{
- return __builtin_ia32_vdivph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_divph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A, __D);
}
#else
#define _mm512_add_round_ph(A, B, C) \
- ((__m512h)__builtin_ia32_vaddph_v32hf_mask_round((A), (B), \
- _mm512_setzero_ph (),\
- (__mmask32)-1, (C)))
+ ((__m512h)__builtin_ia32_addph512_mask_round((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, (C)))
-#define _mm512_mask_add_round_ph(A, B, C, D, E) \
- ((__m512h)__builtin_ia32_vaddph_v32hf_mask_round((C), (D), (A), (B), (E)))
+#define _mm512_mask_add_round_ph(A, B, C, D, E) \
+ ((__m512h)__builtin_ia32_addph512_mask_round((C), (D), (A), (B), (E)))
#define _mm512_maskz_add_round_ph(A, B, C, D) \
- ((__m512h)__builtin_ia32_vaddph_v32hf_mask_round((B), (C), \
- _mm512_setzero_ph (),\
- (A), (D)))
+ ((__m512h)__builtin_ia32_addph512_mask_round((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), (D)))
#define _mm512_sub_round_ph(A, B, C) \
- ((__m512h)__builtin_ia32_vsubph_v32hf_mask_round((A), (B), \
- _mm512_setzero_ph (),\
- (__mmask32)-1, (C)))
+ ((__m512h)__builtin_ia32_subph512_mask_round((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, (C)))
-#define _mm512_mask_sub_round_ph(A, B, C, D, E) \
- ((__m512h)__builtin_ia32_vsubph_v32hf_mask_round((C), (D), (A), (B), (E)))
+#define _mm512_mask_sub_round_ph(A, B, C, D, E) \
+ ((__m512h)__builtin_ia32_subph512_mask_round((C), (D), (A), (B), (E)))
#define _mm512_maskz_sub_round_ph(A, B, C, D) \
- ((__m512h)__builtin_ia32_vsubph_v32hf_mask_round((B), (C), \
- _mm512_setzero_ph (),\
- (A), (D)))
+ ((__m512h)__builtin_ia32_subph512_mask_round((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), (D)))
#define _mm512_mul_round_ph(A, B, C) \
- ((__m512h)__builtin_ia32_vmulph_v32hf_mask_round((A), (B), \
- _mm512_setzero_ph (),\
- (__mmask32)-1, (C)))
+ ((__m512h)__builtin_ia32_mulph512_mask_round((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, (C)))
-#define _mm512_mask_mul_round_ph(A, B, C, D, E) \
- ((__m512h)__builtin_ia32_vmulph_v32hf_mask_round((C), (D), (A), (B), (E)))
+#define _mm512_mask_mul_round_ph(A, B, C, D, E) \
+ ((__m512h)__builtin_ia32_mulph512_mask_round((C), (D), (A), (B), (E)))
#define _mm512_maskz_mul_round_ph(A, B, C, D) \
- ((__m512h)__builtin_ia32_vmulph_v32hf_mask_round((B), (C), \
- _mm512_setzero_ph (),\
- (A), (D)))
+ ((__m512h)__builtin_ia32_mulph512_mask_round((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), (D)))
#define _mm512_div_round_ph(A, B, C) \
- ((__m512h)__builtin_ia32_vdivph_v32hf_mask_round((A), (B), \
- _mm512_setzero_ph (),\
- (__mmask32)-1, (C)))
+ ((__m512h)__builtin_ia32_divph512_mask_round((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, (C)))
-#define _mm512_mask_div_round_ph(A, B, C, D, E) \
- ((__m512h)__builtin_ia32_vdivph_v32hf_mask_round((C), (D), (A), (B), (E)))
+#define _mm512_mask_div_round_ph(A, B, C, D, E) \
+ ((__m512h)__builtin_ia32_divph512_mask_round((C), (D), (A), (B), (E)))
#define _mm512_maskz_div_round_ph(A, B, C, D) \
- ((__m512h)__builtin_ia32_vdivph_v32hf_mask_round((B), (C), \
- _mm512_setzero_ph (),\
- (A), (D)))
+ ((__m512h)__builtin_ia32_divph512_mask_round((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), (D)))
#endif /* __OPTIMIZE__ */
/* Intrinsics of v[add,sub,mul,div]sh. */
extern __inline __m128h
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_sh (__m128h __A, __m128h __B)
{
__A[0] += __B[0];
@@ -481,15 +481,15 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_add_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vaddsh_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_addsh_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_add_sh (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vaddsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_addsh_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
extern __inline __m128h
@@ -504,15 +504,15 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_sub_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vsubsh_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_subsh_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_sub_sh (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vsubsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_subsh_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
extern __inline __m128h
@@ -527,14 +527,14 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_mul_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vmulsh_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_mulsh_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_mul_sh (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vmulsh_v8hf_mask (__B, __C, _mm_setzero_ph (), __A);
+ return __builtin_ia32_mulsh_mask (__B, __C, _mm_setzero_ph (), __A);
}
extern __inline __m128h
@@ -549,15 +549,15 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_div_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vdivsh_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_divsh_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_div_sh (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vdivsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_divsh_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
#ifdef __OPTIMIZE__
@@ -565,9 +565,9 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_add_round_sh (__m128h __A, __m128h __B, const int __C)
{
- return __builtin_ia32_vaddsh_v8hf_mask_round (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1, __C);
+ return __builtin_ia32_addsh_mask_round (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1, __C);
}
extern __inline __m128h
@@ -575,7 +575,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_add_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, const int __E)
{
- return __builtin_ia32_vaddsh_v8hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_addsh_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m128h
@@ -583,18 +583,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_add_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
const int __D)
{
- return __builtin_ia32_vaddsh_v8hf_mask_round (__B, __C,
- _mm_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_addsh_mask_round (__B, __C,
+ _mm_setzero_ph (),
+ __A, __D);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_sub_round_sh (__m128h __A, __m128h __B, const int __C)
{
- return __builtin_ia32_vsubsh_v8hf_mask_round (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1, __C);
+ return __builtin_ia32_subsh_mask_round (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1, __C);
}
extern __inline __m128h
@@ -602,7 +602,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_sub_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, const int __E)
{
- return __builtin_ia32_vsubsh_v8hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_subsh_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m128h
@@ -610,18 +610,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_sub_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
const int __D)
{
- return __builtin_ia32_vsubsh_v8hf_mask_round (__B, __C,
- _mm_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_subsh_mask_round (__B, __C,
+ _mm_setzero_ph (),
+ __A, __D);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mul_round_sh (__m128h __A, __m128h __B, const int __C)
{
- return __builtin_ia32_vmulsh_v8hf_mask_round (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1, __C);
+ return __builtin_ia32_mulsh_mask_round (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1, __C);
}
extern __inline __m128h
@@ -629,7 +629,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_mul_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, const int __E)
{
- return __builtin_ia32_vmulsh_v8hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_mulsh_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m128h
@@ -637,18 +637,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_mul_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
const int __D)
{
- return __builtin_ia32_vmulsh_v8hf_mask_round (__B, __C,
- _mm_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_mulsh_mask_round (__B, __C,
+ _mm_setzero_ph (),
+ __A, __D);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_div_round_sh (__m128h __A, __m128h __B, const int __C)
{
- return __builtin_ia32_vdivsh_v8hf_mask_round (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1, __C);
+ return __builtin_ia32_divsh_mask_round (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1, __C);
}
extern __inline __m128h
@@ -656,7 +656,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_div_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, const int __E)
{
- return __builtin_ia32_vdivsh_v8hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_divsh_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m128h
@@ -664,62 +664,62 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_div_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
const int __D)
{
- return __builtin_ia32_vdivsh_v8hf_mask_round (__B, __C,
- _mm_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_divsh_mask_round (__B, __C,
+ _mm_setzero_ph (),
+ __A, __D);
}
#else
#define _mm_add_round_sh(A, B, C) \
- ((__m128h)__builtin_ia32_vaddsh_v8hf_mask_round ((A), (B), \
- _mm_setzero_ph (), \
- (__mmask8)-1, (C)))
+ ((__m128h)__builtin_ia32_addsh_mask_round ((A), (B), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, (C)))
#define _mm_mask_add_round_sh(A, B, C, D, E) \
- ((__m128h)__builtin_ia32_vaddsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
+ ((__m128h)__builtin_ia32_addsh_mask_round ((C), (D), (A), (B), (E)))
-#define _mm_maskz_add_round_sh(A, B, C, D) \
- ((__m128h)__builtin_ia32_vaddsh_v8hf_mask_round ((B), (C), \
- _mm_setzero_ph (), \
- (A), (D)))
+#define _mm_maskz_add_round_sh(A, B, C, D) \
+ ((__m128h)__builtin_ia32_addsh_mask_round ((B), (C), \
+ _mm_setzero_ph (), \
+ (A), (D)))
#define _mm_sub_round_sh(A, B, C) \
- ((__m128h)__builtin_ia32_vsubsh_v8hf_mask_round ((A), (B), \
- _mm_setzero_ph (), \
- (__mmask8)-1, (C)))
+ ((__m128h)__builtin_ia32_subsh_mask_round ((A), (B), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, (C)))
#define _mm_mask_sub_round_sh(A, B, C, D, E) \
- ((__m128h)__builtin_ia32_vsubsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
+ ((__m128h)__builtin_ia32_subsh_mask_round ((C), (D), (A), (B), (E)))
-#define _mm_maskz_sub_round_sh(A, B, C, D) \
- ((__m128h)__builtin_ia32_vsubsh_v8hf_mask_round ((B), (C), \
- _mm_setzero_ph (), \
- (A), (D)))
+#define _mm_maskz_sub_round_sh(A, B, C, D) \
+ ((__m128h)__builtin_ia32_subsh_mask_round ((B), (C), \
+ _mm_setzero_ph (), \
+ (A), (D)))
#define _mm_mul_round_sh(A, B, C) \
- ((__m128h)__builtin_ia32_vmulsh_v8hf_mask_round ((A), (B), \
- _mm_setzero_ph (), \
- (__mmask8)-1, (C)))
+ ((__m128h)__builtin_ia32_mulsh_mask_round ((A), (B), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, (C)))
#define _mm_mask_mul_round_sh(A, B, C, D, E) \
- ((__m128h)__builtin_ia32_vmulsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
+ ((__m128h)__builtin_ia32_mulsh_mask_round ((C), (D), (A), (B), (E)))
-#define _mm_maskz_mul_round_sh(A, B, C, D) \
- ((__m128h)__builtin_ia32_vmulsh_v8hf_mask_round ((B), (C), \
- _mm_setzero_ph (), \
- (A), (D)))
+#define _mm_maskz_mul_round_sh(A, B, C, D) \
+ ((__m128h)__builtin_ia32_mulsh_mask_round ((B), (C), \
+ _mm_setzero_ph (), \
+ (A), (D)))
#define _mm_div_round_sh(A, B, C) \
- ((__m128h)__builtin_ia32_vdivsh_v8hf_mask_round ((A), (B), \
- _mm_setzero_ph (), \
- (__mmask8)-1, (C)))
+ ((__m128h)__builtin_ia32_divsh_mask_round ((A), (B), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, (C)))
#define _mm_mask_div_round_sh(A, B, C, D, E) \
- ((__m128h)__builtin_ia32_vdivsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
+ ((__m128h)__builtin_ia32_divsh_mask_round ((C), (D), (A), (B), (E)))
-#define _mm_maskz_div_round_sh(A, B, C, D) \
- ((__m128h)__builtin_ia32_vdivsh_v8hf_mask_round ((B), (C), \
- _mm_setzero_ph (), \
- (A), (D)))
+#define _mm_maskz_div_round_sh(A, B, C, D) \
+ ((__m128h)__builtin_ia32_divsh_mask_round ((B), (C), \
+ _mm_setzero_ph (), \
+ (A), (D)))
#endif /* __OPTIMIZE__ */
/* Intrinsic vmaxph vminph. */
@@ -727,48 +727,48 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_max_ph (__m512h __A, __m512h __B)
{
- return __builtin_ia32_vmaxph_v32hf_mask (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1);
+ return __builtin_ia32_maxph512_mask (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_max_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
{
- return __builtin_ia32_vmaxph_v32hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_maxph512_mask (__C, __D, __A, __B);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_max_ph (__mmask32 __A, __m512h __B, __m512h __C)
{
- return __builtin_ia32_vmaxph_v32hf_mask (__B, __C,
- _mm512_setzero_ph (), __A);
+ return __builtin_ia32_maxph512_mask (__B, __C,
+ _mm512_setzero_ph (), __A);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_min_ph (__m512h __A, __m512h __B)
{
- return __builtin_ia32_vminph_v32hf_mask (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1);
+ return __builtin_ia32_minph512_mask (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_min_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
{
- return __builtin_ia32_vminph_v32hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_minph512_mask (__C, __D, __A, __B);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_min_ph (__mmask32 __A, __m512h __B, __m512h __C)
{
- return __builtin_ia32_vminph_v32hf_mask (__B, __C,
- _mm512_setzero_ph (), __A);
+ return __builtin_ia32_minph512_mask (__B, __C,
+ _mm512_setzero_ph (), __A);
}
#ifdef __OPTIMIZE__
@@ -776,9 +776,9 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_max_round_ph (__m512h __A, __m512h __B, const int __C)
{
- return __builtin_ia32_vmaxph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1, __C);
+ return __builtin_ia32_maxph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1, __C);
}
extern __inline __m512h
@@ -786,7 +786,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_max_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
__m512h __D, const int __E)
{
- return __builtin_ia32_vmaxph_v32hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_maxph512_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m512h
@@ -794,18 +794,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_max_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
const int __D)
{
- return __builtin_ia32_vmaxph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_maxph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A, __D);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_min_round_ph (__m512h __A, __m512h __B, const int __C)
{
- return __builtin_ia32_vminph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1, __C);
+ return __builtin_ia32_minph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1, __C);
}
extern __inline __m512h
@@ -813,7 +813,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_min_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
__m512h __D, const int __E)
{
- return __builtin_ia32_vminph_v32hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_minph512_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m512h
@@ -821,37 +821,37 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_min_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
const int __D)
{
- return __builtin_ia32_vminph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_minph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A, __D);
}
#else
-#define _mm512_max_round_ph(A, B, C) \
- (__builtin_ia32_vmaxph_v32hf_mask_round ((A), (B), \
- _mm512_setzero_ph (), \
- (__mmask32)-1, (C)))
+#define _mm512_max_round_ph(A, B, C) \
+ (__builtin_ia32_maxph512_mask_round ((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, (C)))
#define _mm512_mask_max_round_ph(A, B, C, D, E) \
- (__builtin_ia32_vmaxph_v32hf_mask_round ((C), (D), (A), (B), (E)))
+ (__builtin_ia32_maxph512_mask_round ((C), (D), (A), (B), (E)))
-#define _mm512_maskz_max_round_ph(A, B, C, D) \
- (__builtin_ia32_vmaxph_v32hf_mask_round ((B), (C), \
- _mm512_setzero_ph (), \
- (A), (D)))
+#define _mm512_maskz_max_round_ph(A, B, C, D) \
+ (__builtin_ia32_maxph512_mask_round ((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), (D)))
-#define _mm512_min_round_ph(A, B, C) \
- (__builtin_ia32_vminph_v32hf_mask_round ((A), (B), \
- _mm512_setzero_ph (), \
- (__mmask32)-1, (C)))
+#define _mm512_min_round_ph(A, B, C) \
+ (__builtin_ia32_minph512_mask_round ((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, (C)))
#define _mm512_mask_min_round_ph(A, B, C, D, E) \
- (__builtin_ia32_vminph_v32hf_mask_round ((C), (D), (A), (B), (E)))
+ (__builtin_ia32_minph512_mask_round ((C), (D), (A), (B), (E)))
-#define _mm512_maskz_min_round_ph(A, B, C, D) \
- (__builtin_ia32_vminph_v32hf_mask_round ((B), (C), \
- _mm512_setzero_ph (), \
- (A), (D)))
+#define _mm512_maskz_min_round_ph(A, B, C, D) \
+ (__builtin_ia32_minph512_mask_round ((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), (D)))
#endif /* __OPTIMIZE__ */
/* Intrinsic vmaxsh vminsh. */
@@ -867,15 +867,15 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_max_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vmaxsh_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_maxsh_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_max_sh (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vmaxsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_maxsh_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
extern __inline __m128h
@@ -890,15 +890,15 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_min_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vminsh_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_minsh_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_min_sh (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vminsh_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_minsh_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
#ifdef __OPTIMIZE__
@@ -906,9 +906,9 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_round_sh (__m128h __A, __m128h __B, const int __C)
{
- return __builtin_ia32_vmaxsh_v8hf_mask_round (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1, __C);
+ return __builtin_ia32_maxsh_mask_round (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1, __C);
}
extern __inline __m128h
@@ -916,7 +916,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_max_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, const int __E)
{
- return __builtin_ia32_vmaxsh_v8hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_maxsh_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m128h
@@ -924,18 +924,18 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_max_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
const int __D)
{
- return __builtin_ia32_vmaxsh_v8hf_mask_round (__B, __C,
- _mm_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_maxsh_mask_round (__B, __C,
+ _mm_setzero_ph (),
+ __A, __D);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_round_sh (__m128h __A, __m128h __B, const int __C)
{
- return __builtin_ia32_vminsh_v8hf_mask_round (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1, __C);
+ return __builtin_ia32_minsh_mask_round (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1, __C);
}
extern __inline __m128h
@@ -943,7 +943,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_min_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, const int __E)
{
- return __builtin_ia32_vminsh_v8hf_mask_round (__C, __D, __A, __B, __E);
+ return __builtin_ia32_minsh_mask_round (__C, __D, __A, __B, __E);
}
extern __inline __m128h
@@ -951,37 +951,37 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_min_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
const int __D)
{
- return __builtin_ia32_vminsh_v8hf_mask_round (__B, __C,
- _mm_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_minsh_mask_round (__B, __C,
+ _mm_setzero_ph (),
+ __A, __D);
}
#else
-#define _mm_max_round_sh(A, B, C) \
- (__builtin_ia32_vmaxsh_v8hf_mask_round ((A), (B), \
- _mm_setzero_ph (), \
- (__mmask8)-1, (C)))
+#define _mm_max_round_sh(A, B, C) \
+ (__builtin_ia32_maxsh_mask_round ((A), (B), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, (C)))
-#define _mm_mask_max_round_sh(A, B, C, D, E) \
- (__builtin_ia32_vmaxsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
+#define _mm_mask_max_round_sh(A, B, C, D, E) \
+ (__builtin_ia32_maxsh_mask_round ((C), (D), (A), (B), (E)))
-#define _mm_maskz_max_round_sh(A, B, C, D) \
- (__builtin_ia32_vmaxsh_v8hf_mask_round ((B), (C), \
- _mm_setzero_ph (), \
- (A), (D)))
+#define _mm_maskz_max_round_sh(A, B, C, D) \
+ (__builtin_ia32_maxsh_mask_round ((B), (C), \
+ _mm_setzero_ph (), \
+ (A), (D)))
-#define _mm_min_round_sh(A, B, C) \
- (__builtin_ia32_vminsh_v8hf_mask_round ((A), (B), \
- _mm_setzero_ph (), \
- (__mmask8)-1, (C)))
+#define _mm_min_round_sh(A, B, C) \
+ (__builtin_ia32_minsh_mask_round ((A), (B), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, (C)))
-#define _mm_mask_min_round_sh(A, B, C, D, E) \
- (__builtin_ia32_vminsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
+#define _mm_mask_min_round_sh(A, B, C, D, E) \
+ (__builtin_ia32_minsh_mask_round ((C), (D), (A), (B), (E)))
-#define _mm_maskz_min_round_sh(A, B, C, D) \
- (__builtin_ia32_vminsh_v8hf_mask_round ((B), (C), \
- _mm_setzero_ph (), \
- (A), (D)))
+#define _mm_maskz_min_round_sh(A, B, C, D) \
+ (__builtin_ia32_minsh_mask_round ((B), (C), \
+ _mm_setzero_ph (), \
+ (A), (D)))
#endif /* __OPTIMIZE__ */
@@ -991,8 +991,8 @@ extern __inline __mmask32
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_cmp_ph_mask (__m512h __A, __m512h __B, const int __C)
{
- return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask (__A, __B, __C,
- (__mmask32) -1);
+ return (__mmask32) __builtin_ia32_cmpph512_mask (__A, __B, __C,
+ (__mmask32) -1);
}
extern __inline __mmask32
@@ -1000,8 +1000,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_cmp_ph_mask (__mmask32 __A, __m512h __B, __m512h __C,
const int __D)
{
- return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask (__B, __C, __D,
- __A);
+ return (__mmask32) __builtin_ia32_cmpph512_mask (__B, __C, __D,
+ __A);
}
extern __inline __mmask32
@@ -1009,9 +1009,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_cmp_round_ph_mask (__m512h __A, __m512h __B, const int __C,
const int __D)
{
- return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask_round (__A, __B,
- __C, (__mmask32) -1,
- __D);
+ return (__mmask32) __builtin_ia32_cmpph512_mask_round (__A, __B,
+ __C, (__mmask32) -1,
+ __D);
}
extern __inline __mmask32
@@ -1019,23 +1019,23 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_cmp_round_ph_mask (__mmask32 __A, __m512h __B, __m512h __C,
const int __D, const int __E)
{
- return (__mmask32) __builtin_ia32_vcmpph_v32hf_mask_round (__B, __C,
- __D, __A,
- __E);
+ return (__mmask32) __builtin_ia32_cmpph512_mask_round (__B, __C,
+ __D, __A,
+ __E);
}
#else
#define _mm512_cmp_ph_mask(A, B, C) \
- (__builtin_ia32_vcmpph_v32hf_mask ((A), (B), (C), (-1)))
+ (__builtin_ia32_cmpph512_mask ((A), (B), (C), (-1)))
#define _mm512_mask_cmp_ph_mask(A, B, C, D) \
- (__builtin_ia32_vcmpph_v32hf_mask ((B), (C), (D), (A)))
+ (__builtin_ia32_cmpph512_mask ((B), (C), (D), (A)))
-#define _mm512_cmp_round_ph_mask(A, B, C, D) \
- (__builtin_ia32_vcmpph_v32hf_mask_round ((A), (B), (C), (-1), (D)))
+#define _mm512_cmp_round_ph_mask(A, B, C, D) \
+ (__builtin_ia32_cmpph512_mask_round ((A), (B), (C), (-1), (D)))
-#define _mm512_mask_cmp_round_ph_mask(A, B, C, D, E) \
- (__builtin_ia32_vcmpph_v32hf_mask_round ((B), (C), (D), (A), (E)))
+#define _mm512_mask_cmp_round_ph_mask(A, B, C, D, E) \
+ (__builtin_ia32_cmpph512_mask_round ((B), (C), (D), (A), (E)))
#endif /* __OPTIMIZE__ */
@@ -1046,9 +1046,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmp_sh_mask (__m128h __A, __m128h __B, const int __C)
{
return (__mmask8)
- __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B,
- __C, (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ __builtin_ia32_cmpsh_mask_round (__A, __B,
+ __C, (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __mmask8
@@ -1057,9 +1057,9 @@ _mm_mask_cmp_sh_mask (__mmask8 __A, __m128h __B, __m128h __C,
const int __D)
{
return (__mmask8)
- __builtin_ia32_vcmpsh_v8hf_mask_round (__B, __C,
- __D, __A,
- _MM_FROUND_CUR_DIRECTION);
+ __builtin_ia32_cmpsh_mask_round (__B, __C,
+ __D, __A,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __mmask8
@@ -1067,9 +1067,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmp_round_sh_mask (__m128h __A, __m128h __B, const int __C,
const int __D)
{
- return (__mmask8) __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B,
- __C, (__mmask8) -1,
- __D);
+ return (__mmask8) __builtin_ia32_cmpsh_mask_round (__A, __B,
+ __C, (__mmask8) -1,
+ __D);
}
extern __inline __mmask8
@@ -1077,25 +1077,25 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_cmp_round_sh_mask (__mmask8 __A, __m128h __B, __m128h __C,
const int __D, const int __E)
{
- return (__mmask8) __builtin_ia32_vcmpsh_v8hf_mask_round (__B, __C,
- __D, __A,
- __E);
+ return (__mmask8) __builtin_ia32_cmpsh_mask_round (__B, __C,
+ __D, __A,
+ __E);
}
#else
-#define _mm_cmp_sh_mask(A, B, C) \
- (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (C), (-1), \
- (_MM_FROUND_CUR_DIRECTION)))
+#define _mm_cmp_sh_mask(A, B, C) \
+ (__builtin_ia32_cmpsh_mask_round ((A), (B), (C), (-1), \
+ (_MM_FROUND_CUR_DIRECTION)))
-#define _mm_mask_cmp_sh_mask(A, B, C, D) \
- (__builtin_ia32_vcmpsh_v8hf_mask_round ((B), (C), (D), (A), \
- (_MM_FROUND_CUR_DIRECTION)))
+#define _mm_mask_cmp_sh_mask(A, B, C, D) \
+ (__builtin_ia32_cmpsh_mask_round ((B), (C), (D), (A), \
+ (_MM_FROUND_CUR_DIRECTION)))
-#define _mm_cmp_round_sh_mask(A, B, C, D) \
- (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (C), (-1), (D)))
+#define _mm_cmp_round_sh_mask(A, B, C, D) \
+ (__builtin_ia32_cmpsh_mask_round ((A), (B), (C), (-1), (D)))
-#define _mm_mask_cmp_round_sh_mask(A, B, C, D, E) \
- (__builtin_ia32_vcmpsh_v8hf_mask_round ((B), (C), (D), (A), (E)))
+#define _mm_mask_cmp_round_sh_mask(A, B, C, D, E) \
+ (__builtin_ia32_cmpsh_mask_round ((B), (C), (D), (A), (E)))
#endif /* __OPTIMIZE__ */
@@ -1104,134 +1104,134 @@ extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_comieq_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_EQ_OS,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_EQ_OS,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_comilt_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LT_OS,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LT_OS,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_comile_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LE_OS,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LE_OS,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_comigt_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GT_OS,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GT_OS,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_comige_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GE_OS,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GE_OS,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_comineq_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_NEQ_US,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_NEQ_US,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomieq_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_EQ_OQ,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_EQ_OQ,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomilt_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LT_OQ,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LT_OQ,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomile_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_LE_OQ,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_LE_OQ,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomigt_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GT_OQ,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GT_OQ,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomige_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_GE_OQ,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_GE_OQ,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_ucomineq_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, _CMP_NEQ_UQ,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, _CMP_NEQ_UQ,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
#ifdef __OPTIMIZE__
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
- _mm_comi_sh (__m128h __A, __m128h __B, const int __P)
+_mm_comi_sh (__m128h __A, __m128h __B, const int __P)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, __P,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, __P,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline int
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_comi_round_sh (__m128h __A, __m128h __B, const int __P, const int __R)
{
- return __builtin_ia32_vcmpsh_v8hf_mask_round (__A, __B, __P,
- (__mmask8) -1,__R);
+ return __builtin_ia32_cmpsh_mask_round (__A, __B, __P,
+ (__mmask8) -1,__R);
}
#else
-#define _mm_comi_round_sh(A, B, P, R) \
- (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (P), (__mmask8) (-1), (R)))
-#define _mm_comi_sh(A, B, P) \
- (__builtin_ia32_vcmpsh_v8hf_mask_round ((A), (B), (P), (__mmask8) (-1), \
- _MM_FROUND_CUR_DIRECTION))
+#define _mm_comi_round_sh(A, B, P, R) \
+ (__builtin_ia32_cmpsh_mask_round ((A), (B), (P), (__mmask8) (-1), (R)))
+#define _mm_comi_sh(A, B, P) \
+ (__builtin_ia32_cmpsh_mask_round ((A), (B), (P), (__mmask8) (-1), \
+ _MM_FROUND_CUR_DIRECTION))
#endif /* __OPTIMIZE__ */
@@ -1240,28 +1240,28 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_sqrt_ph (__m512h __A)
{
- return __builtin_ia32_vsqrtph_v32hf_mask_round (__A,
- _mm512_setzero_ph(),
- (__mmask32) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_sqrtph512_mask_round (__A,
+ _mm512_setzero_ph(),
+ (__mmask32) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_sqrt_ph (__m512h __A, __mmask32 __B, __m512h __C)
{
- return __builtin_ia32_vsqrtph_v32hf_mask_round (__C, __A, __B,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_sqrtph512_mask_round (__C, __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_sqrt_ph (__mmask32 __A, __m512h __B)
{
- return __builtin_ia32_vsqrtph_v32hf_mask_round (__B,
- _mm512_setzero_ph (),
- __A,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_sqrtph512_mask_round (__B,
+ _mm512_setzero_ph (),
+ __A,
+ _MM_FROUND_CUR_DIRECTION);
}
#ifdef __OPTIMIZE__
@@ -1269,9 +1269,9 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_sqrt_round_ph (__m512h __A, const int __B)
{
- return __builtin_ia32_vsqrtph_v32hf_mask_round (__A,
- _mm512_setzero_ph(),
- (__mmask32) -1, __B);
+ return __builtin_ia32_sqrtph512_mask_round (__A,
+ _mm512_setzero_ph(),
+ (__mmask32) -1, __B);
}
extern __inline __m512h
@@ -1279,31 +1279,31 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_sqrt_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
const int __D)
{
- return __builtin_ia32_vsqrtph_v32hf_mask_round (__C, __A, __B, __D);
+ return __builtin_ia32_sqrtph512_mask_round (__C, __A, __B, __D);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_sqrt_round_ph (__mmask32 __A, __m512h __B, const int __C)
{
- return __builtin_ia32_vsqrtph_v32hf_mask_round (__B,
- _mm512_setzero_ph (),
- __A, __C);
+ return __builtin_ia32_sqrtph512_mask_round (__B,
+ _mm512_setzero_ph (),
+ __A, __C);
}
#else
-#define _mm512_sqrt_round_ph(A, B) \
- (__builtin_ia32_vsqrtph_v32hf_mask_round ((A), \
- _mm512_setzero_ph (), \
- (__mmask32)-1, (B)))
+#define _mm512_sqrt_round_ph(A, B) \
+ (__builtin_ia32_sqrtph512_mask_round ((A), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, (B)))
-#define _mm512_mask_sqrt_round_ph(A, B, C, D) \
- (__builtin_ia32_vsqrtph_v32hf_mask_round ((C), (A), (B), (D)))
+#define _mm512_mask_sqrt_round_ph(A, B, C, D) \
+ (__builtin_ia32_sqrtph512_mask_round ((C), (A), (B), (D)))
-#define _mm512_maskz_sqrt_round_ph(A, B, C) \
- (__builtin_ia32_vsqrtph_v32hf_mask_round ((B), \
- _mm512_setzero_ph (), \
- (A), (C)))
+#define _mm512_maskz_sqrt_round_ph(A, B, C) \
+ (__builtin_ia32_sqrtph512_mask_round ((B), \
+ _mm512_setzero_ph (), \
+ (A), (C)))
#endif /* __OPTIMIZE__ */
@@ -1312,23 +1312,23 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_rsqrt_ph (__m512h __A)
{
- return __builtin_ia32_vrsqrtph_v32hf_mask (__A, _mm512_setzero_ph (),
- (__mmask32) -1);
+ return __builtin_ia32_rsqrtph512_mask (__A, _mm512_setzero_ph (),
+ (__mmask32) -1);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_rsqrt_ph (__m512h __A, __mmask32 __B, __m512h __C)
{
- return __builtin_ia32_vrsqrtph_v32hf_mask (__C, __A, __B);
+ return __builtin_ia32_rsqrtph512_mask (__C, __A, __B);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_rsqrt_ph (__mmask32 __A, __m512h __B)
{
- return __builtin_ia32_vrsqrtph_v32hf_mask (__B, _mm512_setzero_ph (),
- __A);
+ return __builtin_ia32_rsqrtph512_mask (__B, _mm512_setzero_ph (),
+ __A);
}
/* Intrinsics vrsqrtsh. */
@@ -1336,23 +1336,23 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rsqrt_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vrsqrtsh_v8hf_mask (__B, __A, _mm_setzero_ph (),
- (__mmask8) -1);
+ return __builtin_ia32_rsqrtsh_mask (__B, __A, _mm_setzero_ph (),
+ (__mmask8) -1);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_rsqrt_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vrsqrtsh_v8hf_mask (__D, __C, __A, __B);
+ return __builtin_ia32_rsqrtsh_mask (__D, __C, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_rsqrt_sh (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vrsqrtsh_v8hf_mask (__C, __B, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_rsqrtsh_mask (__C, __B, _mm_setzero_ph (),
+ __A);
}
/* Intrinsics vsqrtsh. */
@@ -1360,27 +1360,27 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_sqrt_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vsqrtsh_v8hf_mask_round (__B, __A,
- _mm_setzero_ph (),
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_sqrtsh_mask_round (__B, __A,
+ _mm_setzero_ph (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_sqrt_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vsqrtsh_v8hf_mask_round (__D, __C, __A, __B,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_sqrtsh_mask_round (__D, __C, __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_sqrt_sh (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vsqrtsh_v8hf_mask_round (__C, __B,
- _mm_setzero_ph (),
- __A, _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_sqrtsh_mask_round (__C, __B,
+ _mm_setzero_ph (),
+ __A, _MM_FROUND_CUR_DIRECTION);
}
#ifdef __OPTIMIZE__
@@ -1388,9 +1388,9 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_sqrt_round_sh (__m128h __A, __m128h __B, const int __C)
{
- return __builtin_ia32_vsqrtsh_v8hf_mask_round (__B, __A,
- _mm_setzero_ph (),
- (__mmask8) -1, __C);
+ return __builtin_ia32_sqrtsh_mask_round (__B, __A,
+ _mm_setzero_ph (),
+ (__mmask8) -1, __C);
}
extern __inline __m128h
@@ -1398,8 +1398,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_sqrt_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, const int __E)
{
- return __builtin_ia32_vsqrtsh_v8hf_mask_round (__D, __C, __A, __B,
- __E);
+ return __builtin_ia32_sqrtsh_mask_round (__D, __C, __A, __B,
+ __E);
}
extern __inline __m128h
@@ -1407,24 +1407,24 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_sqrt_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
const int __D)
{
- return __builtin_ia32_vsqrtsh_v8hf_mask_round (__C, __B,
- _mm_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_sqrtsh_mask_round (__C, __B,
+ _mm_setzero_ph (),
+ __A, __D);
}
#else
#define _mm_sqrt_round_sh(A, B, C) \
- (__builtin_ia32_vsqrtsh_v8hf_mask_round ((B), (A), \
- _mm_setzero_ph (), \
- (__mmask8)-1, (C)))
+ (__builtin_ia32_sqrtsh_mask_round ((B), (A), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, (C)))
#define _mm_mask_sqrt_round_sh(A, B, C, D, E) \
- (__builtin_ia32_vsqrtsh_v8hf_mask_round ((D), (C), (A), (B), (E)))
+ (__builtin_ia32_sqrtsh_mask_round ((D), (C), (A), (B), (E)))
-#define _mm_maskz_sqrt_round_sh(A, B, C, D) \
- (__builtin_ia32_vsqrtsh_v8hf_mask_round ((C), (B), \
- _mm_setzero_ph (), \
- (A), (D)))
+#define _mm_maskz_sqrt_round_sh(A, B, C, D) \
+ (__builtin_ia32_sqrtsh_mask_round ((C), (B), \
+ _mm_setzero_ph (), \
+ (A), (D)))
#endif /* __OPTIMIZE__ */
@@ -1433,23 +1433,23 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_rcp_ph (__m512h __A)
{
- return __builtin_ia32_vrcpph_v32hf_mask (__A, _mm512_setzero_ph (),
- (__mmask32) -1);
+ return __builtin_ia32_rcpph512_mask (__A, _mm512_setzero_ph (),
+ (__mmask32) -1);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_rcp_ph (__m512h __A, __mmask32 __B, __m512h __C)
{
- return __builtin_ia32_vrcpph_v32hf_mask (__C, __A, __B);
+ return __builtin_ia32_rcpph512_mask (__C, __A, __B);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_rcp_ph (__mmask32 __A, __m512h __B)
{
- return __builtin_ia32_vrcpph_v32hf_mask (__B, _mm512_setzero_ph (),
- __A);
+ return __builtin_ia32_rcpph512_mask (__B, _mm512_setzero_ph (),
+ __A);
}
/* Intrinsics vrcpsh. */
@@ -1457,23 +1457,23 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rcp_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vrcpsh_v8hf_mask (__B, __A, _mm_setzero_ph (),
- (__mmask8) -1);
+ return __builtin_ia32_rcpsh_mask (__B, __A, _mm_setzero_ph (),
+ (__mmask8) -1);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_rcp_sh (__m128h __A, __mmask32 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vrcpsh_v8hf_mask (__D, __C, __A, __B);
+ return __builtin_ia32_rcpsh_mask (__D, __C, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_rcp_sh (__mmask32 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vrcpsh_v8hf_mask (__C, __B, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_rcpsh_mask (__C, __B, _mm_setzero_ph (),
+ __A);
}
/* Intrinsics vscalefph. */
@@ -1481,28 +1481,28 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_scalef_ph (__m512h __A, __m512h __B)
{
- return __builtin_ia32_vscalefph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_scalefph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_scalef_ph (__m512h __A, __mmask32 __B, __m512h __C, __m512h __D)
{
- return __builtin_ia32_vscalefph_v32hf_mask_round (__C, __D, __A, __B,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_scalefph512_mask_round (__C, __D, __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_scalef_ph (__mmask32 __A, __m512h __B, __m512h __C)
{
- return __builtin_ia32_vscalefph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_scalefph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A,
+ _MM_FROUND_CUR_DIRECTION);
}
#ifdef __OPTIMIZE__
@@ -1510,9 +1510,9 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_scalef_round_ph (__m512h __A, __m512h __B, const int __C)
{
- return __builtin_ia32_vscalefph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1, __C);
+ return __builtin_ia32_scalefph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1, __C);
}
extern __inline __m512h
@@ -1520,8 +1520,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_scalef_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
__m512h __D, const int __E)
{
- return __builtin_ia32_vscalefph_v32hf_mask_round (__C, __D, __A, __B,
- __E);
+ return __builtin_ia32_scalefph512_mask_round (__C, __D, __A, __B,
+ __E);
}
extern __inline __m512h
@@ -1529,24 +1529,24 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_scalef_round_ph (__mmask32 __A, __m512h __B, __m512h __C,
const int __D)
{
- return __builtin_ia32_vscalefph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_scalefph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A, __D);
}
#else
-#define _mm512_scalef_round_ph(A, B, C) \
- (__builtin_ia32_vscalefph_v32hf_mask_round ((A), (B), \
- _mm512_setzero_ph (), \
- (__mmask32)-1, (C)))
+#define _mm512_scalef_round_ph(A, B, C) \
+ (__builtin_ia32_scalefph512_mask_round ((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, (C)))
#define _mm512_mask_scalef_round_ph(A, B, C, D, E) \
- (__builtin_ia32_vscalefph_v32hf_mask_round ((C), (D), (A), (B), (E)))
+ (__builtin_ia32_scalefph512_mask_round ((C), (D), (A), (B), (E)))
-#define _mm512_maskz_scalef_round_ph(A, B, C, D) \
- (__builtin_ia32_vscalefph_v32hf_mask_round ((B), (C), \
- _mm512_setzero_ph (), \
- (A), (D)))
+#define _mm512_maskz_scalef_round_ph(A, B, C, D) \
+ (__builtin_ia32_scalefph512_mask_round ((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), (D)))
#endif /* __OPTIMIZE__ */
@@ -1555,28 +1555,28 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_scalef_sh (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vscalefsh_v8hf_mask_round (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_scalefsh_mask_round (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_scalef_sh (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vscalefsh_v8hf_mask_round (__C, __D, __A, __B,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_scalefsh_mask_round (__C, __D, __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_scalef_sh (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vscalefsh_v8hf_mask_round (__B, __C,
- _mm_setzero_ph (),
- __A,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_scalefsh_mask_round (__B, __C,
+ _mm_setzero_ph (),
+ __A,
+ _MM_FROUND_CUR_DIRECTION);
}
#ifdef __OPTIMIZE__
@@ -1584,9 +1584,9 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_scalef_round_sh (__m128h __A, __m128h __B, const int __C)
{
- return __builtin_ia32_vscalefsh_v8hf_mask_round (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1, __C);
+ return __builtin_ia32_scalefsh_mask_round (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1, __C);
}
extern __inline __m128h
@@ -1594,8 +1594,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_scalef_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, const int __E)
{
- return __builtin_ia32_vscalefsh_v8hf_mask_round (__C, __D, __A, __B,
- __E);
+ return __builtin_ia32_scalefsh_mask_round (__C, __D, __A, __B,
+ __E);
}
extern __inline __m128h
@@ -1603,23 +1603,23 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_scalef_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
const int __D)
{
- return __builtin_ia32_vscalefsh_v8hf_mask_round (__B, __C,
- _mm_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_scalefsh_mask_round (__B, __C,
+ _mm_setzero_ph (),
+ __A, __D);
}
#else
-#define _mm_scalef_round_sh(A, B, C) \
- (__builtin_ia32_vscalefsh_v8hf_mask_round ((A), (B), \
- _mm_setzero_ph (), \
- (__mmask8)-1, (C)))
+#define _mm_scalef_round_sh(A, B, C) \
+ (__builtin_ia32_scalefsh_mask_round ((A), (B), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, (C)))
-#define _mm_mask_scalef_round_sh(A, B, C, D, E) \
- (__builtin_ia32_vscalefsh_v8hf_mask_round ((C), (D), (A), (B), (E)))
+#define _mm_mask_scalef_round_sh(A, B, C, D, E) \
+ (__builtin_ia32_scalefsh_mask_round ((C), (D), (A), (B), (E)))
-#define _mm_maskz_scalef_round_sh(A, B, C, D) \
- (__builtin_ia32_vscalefsh_v8hf_mask_round ((B), (C), _mm_setzero_ph (), \
- (A), (D)))
+#define _mm_maskz_scalef_round_sh(A, B, C, D) \
+ (__builtin_ia32_scalefsh_mask_round ((B), (C), _mm_setzero_ph (), \
+ (A), (D)))
#endif /* __OPTIMIZE__ */
@@ -1629,37 +1629,37 @@ extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_reduce_ph (__m512h __A, int __B)
{
- return __builtin_ia32_vreduceph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_reduceph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_reduce_ph (__m512h __A, __mmask32 __B, __m512h __C, int __D)
{
- return __builtin_ia32_vreduceph_v32hf_mask_round (__C, __D, __A, __B,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_reduceph512_mask_round (__C, __D, __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_reduce_ph (__mmask32 __A, __m512h __B, int __C)
{
- return __builtin_ia32_vreduceph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_reduceph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_reduce_round_ph (__m512h __A, int __B, const int __C)
{
- return __builtin_ia32_vreduceph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1, __C);
+ return __builtin_ia32_reduceph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1, __C);
}
extern __inline __m512h
@@ -1667,8 +1667,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_reduce_round_ph (__m512h __A, __mmask32 __B, __m512h __C,
int __D, const int __E)
{
- return __builtin_ia32_vreduceph_v32hf_mask_round (__C, __D, __A, __B,
- __E);
+ return __builtin_ia32_reduceph512_mask_round (__C, __D, __A, __B,
+ __E);
}
extern __inline __m512h
@@ -1676,39 +1676,39 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_reduce_round_ph (__mmask32 __A, __m512h __B, int __C,
const int __D)
{
- return __builtin_ia32_vreduceph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_reduceph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A, __D);
}
#else
#define _mm512_reduce_ph(A, B) \
- (__builtin_ia32_vreduceph_v32hf_mask_round ((A), (B), \
- _mm512_setzero_ph (), \
- (__mmask32)-1, \
- _MM_FROUND_CUR_DIRECTION))
+ (__builtin_ia32_reduceph512_mask_round ((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, \
+ _MM_FROUND_CUR_DIRECTION))
#define _mm512_mask_reduce_ph(A, B, C, D) \
- (__builtin_ia32_vreduceph_v32hf_mask_round ((C), (D), (A), (B), \
- _MM_FROUND_CUR_DIRECTION))
+ (__builtin_ia32_reduceph512_mask_round ((C), (D), (A), (B), \
+ _MM_FROUND_CUR_DIRECTION))
#define _mm512_maskz_reduce_ph(A, B, C) \
- (__builtin_ia32_vreduceph_v32hf_mask_round ((B), (C), \
- _mm512_setzero_ph (), \
- (A), _MM_FROUND_CUR_DIRECTION))
+ (__builtin_ia32_reduceph512_mask_round ((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), _MM_FROUND_CUR_DIRECTION))
-#define _mm512_reduce_round_ph(A, B, C) \
- (__builtin_ia32_vreduceph_v32hf_mask_round ((A), (B), \
- _mm512_setzero_ph (), \
- (__mmask32)-1, (C)))
+#define _mm512_reduce_round_ph(A, B, C) \
+ (__builtin_ia32_reduceph512_mask_round ((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, (C)))
#define _mm512_mask_reduce_round_ph(A, B, C, D, E) \
- (__builtin_ia32_vreduceph_v32hf_mask_round ((C), (D), (A), (B), (E)))
+ (__builtin_ia32_reduceph512_mask_round ((C), (D), (A), (B), (E)))
-#define _mm512_maskz_reduce_round_ph(A, B, C, D) \
- (__builtin_ia32_vreduceph_v32hf_mask_round ((B), (C), \
- _mm512_setzero_ph (), \
- (A), (D)))
+#define _mm512_maskz_reduce_round_ph(A, B, C, D) \
+ (__builtin_ia32_reduceph512_mask_round ((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), (D)))
#endif /* __OPTIMIZE__ */
@@ -1718,10 +1718,10 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_reduce_sh (__m128h __A, __m128h __B, int __C)
{
- return __builtin_ia32_vreducesh_v8hf_mask_round (__A, __B, __C,
- _mm_setzero_ph (),
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_reducesh_mask_round (__A, __B, __C,
+ _mm_setzero_ph (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128h
@@ -1729,26 +1729,26 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_reduce_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, int __E)
{
- return __builtin_ia32_vreducesh_v8hf_mask_round (__C, __D, __E, __A, __B,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_reducesh_mask_round (__C, __D, __E, __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_reduce_sh (__mmask8 __A, __m128h __B, __m128h __C, int __D)
{
- return __builtin_ia32_vreducesh_v8hf_mask_round (__B, __C, __D,
- _mm_setzero_ph (), __A,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_reducesh_mask_round (__B, __C, __D,
+ _mm_setzero_ph (), __A,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_reduce_round_sh (__m128h __A, __m128h __B, int __C, const int __D)
{
- return __builtin_ia32_vreducesh_v8hf_mask_round (__A, __B, __C,
- _mm_setzero_ph (),
- (__mmask8) -1, __D);
+ return __builtin_ia32_reducesh_mask_round (__A, __B, __C,
+ _mm_setzero_ph (),
+ (__mmask8) -1, __D);
}
extern __inline __m128h
@@ -1756,8 +1756,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_reduce_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, int __E, const int __F)
{
- return __builtin_ia32_vreducesh_v8hf_mask_round (__C, __D, __E, __A,
- __B, __F);
+ return __builtin_ia32_reducesh_mask_round (__C, __D, __E, __A,
+ __B, __F);
}
extern __inline __m128h
@@ -1765,81 +1765,81 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_reduce_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
int __D, const int __E)
{
- return __builtin_ia32_vreducesh_v8hf_mask_round (__B, __C, __D,
- _mm_setzero_ph (),
- __A, __E);
+ return __builtin_ia32_reducesh_mask_round (__B, __C, __D,
+ _mm_setzero_ph (),
+ __A, __E);
}
#else
#define _mm_reduce_sh(A, B, C) \
- (__builtin_ia32_vreducesh_v8hf_mask_round ((A), (B), (C), \
- _mm_setzero_ph (), \
- (__mmask8)-1, \
- _MM_FROUND_CUR_DIRECTION))
+ (__builtin_ia32_reducesh_mask_round ((A), (B), (C), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, \
+ _MM_FROUND_CUR_DIRECTION))
#define _mm_mask_reduce_sh(A, B, C, D, E) \
- (__builtin_ia32_vreducesh_v8hf_mask_round ((C), (D), (E), (A), (B), \
- _MM_FROUND_CUR_DIRECTION))
+ (__builtin_ia32_reducesh_mask_round ((C), (D), (E), (A), (B), \
+ _MM_FROUND_CUR_DIRECTION))
#define _mm_maskz_reduce_sh(A, B, C, D) \
- (__builtin_ia32_vreducesh_v8hf_mask_round ((B), (C), (D), \
- _mm_setzero_ph (), \
- (A), _MM_FROUND_CUR_DIRECTION))
+ (__builtin_ia32_reducesh_mask_round ((B), (C), (D), \
+ _mm_setzero_ph (), \
+ (A), _MM_FROUND_CUR_DIRECTION))
#define _mm_reduce_round_sh(A, B, C, D) \
- (__builtin_ia32_vreducesh_v8hf_mask_round ((A), (B), (C), \
- _mm_setzero_ph (), \
- (__mmask8)-1, (D)))
+ (__builtin_ia32_reducesh_mask_round ((A), (B), (C), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, (D)))
#define _mm_mask_reduce_round_sh(A, B, C, D, E, F) \
- (__builtin_ia32_vreducesh_v8hf_mask_round ((C), (D), (E), (A), (B), (F)))
+ (__builtin_ia32_reducesh_mask_round ((C), (D), (E), (A), (B), (F)))
#define _mm_maskz_reduce_round_sh(A, B, C, D, E) \
- (__builtin_ia32_vreducesh_v8hf_mask_round ((B), (C), (D), \
- _mm_setzero_ph (), \
- (A), (E)))
+ (__builtin_ia32_reducesh_mask_round ((B), (C), (D), \
+ _mm_setzero_ph (), \
+ (A), (E)))
#endif /* __OPTIMIZE__ */
/* Intrinsics vrndscaleph. */
#ifdef __OPTIMIZE__
extern __inline __m512h
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_roundscale_ph (__m512h __A, int __B)
{
- return __builtin_ia32_vrndscaleph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_rndscaleph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_roundscale_ph (__m512h __A, __mmask32 __B,
- __m512h __C, int __D)
+ __m512h __C, int __D)
{
- return __builtin_ia32_vrndscaleph_v32hf_mask_round (__C, __D, __A, __B,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_rndscaleph512_mask_round (__C, __D, __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_roundscale_ph (__mmask32 __A, __m512h __B, int __C)
{
- return __builtin_ia32_vrndscaleph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_rndscaleph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m512h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_roundscale_round_ph (__m512h __A, int __B, const int __C)
{
- return __builtin_ia32_vrndscaleph_v32hf_mask_round (__A, __B,
- _mm512_setzero_ph (),
- (__mmask32) -1,
- __C);
+ return __builtin_ia32_rndscaleph512_mask_round (__A, __B,
+ _mm512_setzero_ph (),
+ (__mmask32) -1,
+ __C);
}
extern __inline __m512h
@@ -1847,8 +1847,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_roundscale_round_ph (__m512h __A, __mmask32 __B,
__m512h __C, int __D, const int __E)
{
- return __builtin_ia32_vrndscaleph_v32hf_mask_round (__C, __D, __A,
- __B, __E);
+ return __builtin_ia32_rndscaleph512_mask_round (__C, __D, __A,
+ __B, __E);
}
extern __inline __m512h
@@ -1856,52 +1856,52 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_roundscale_round_ph (__mmask32 __A, __m512h __B, int __C,
const int __D)
{
- return __builtin_ia32_vrndscaleph_v32hf_mask_round (__B, __C,
- _mm512_setzero_ph (),
- __A, __D);
+ return __builtin_ia32_rndscaleph512_mask_round (__B, __C,
+ _mm512_setzero_ph (),
+ __A, __D);
}
#else
-#define _mm512_roundscale_ph(A, B) \
- (__builtin_ia32_vrndscaleph_v32hf_mask_round ((A), (B), \
- _mm512_setzero_ph (), \
- (__mmask32)-1, \
- _MM_FROUND_CUR_DIRECTION))
-
-#define _mm512_mask_roundscale_ph(A, B, C, D) \
- (__builtin_ia32_vrndscaleph_v32hf_mask_round ((C), (D), (A), (B), \
- _MM_FROUND_CUR_DIRECTION))
-
-#define _mm512_maskz_roundscale_ph(A, B, C) \
- (__builtin_ia32_vrndscaleph_v32hf_mask_round ((B), (C), \
- _mm512_setzero_ph (), \
- (A), \
- _MM_FROUND_CUR_DIRECTION))
-#define _mm512_roundscale_round_ph(A, B, C) \
- (__builtin_ia32_vrndscaleph_v32hf_mask_round ((A), (B), \
- _mm512_setzero_ph (), \
- (__mmask32)-1, (C)))
+#define _mm512_roundscale_ph(A, B) \
+ (__builtin_ia32_rndscaleph512_mask_round ((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, \
+ _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_roundscale_ph(A, B, C, D) \
+ (__builtin_ia32_rndscaleph512_mask_round ((C), (D), (A), (B), \
+ _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_maskz_roundscale_ph(A, B, C) \
+ (__builtin_ia32_rndscaleph512_mask_round ((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), \
+ _MM_FROUND_CUR_DIRECTION))
+#define _mm512_roundscale_round_ph(A, B, C) \
+ (__builtin_ia32_rndscaleph512_mask_round ((A), (B), \
+ _mm512_setzero_ph (), \
+ (__mmask32)-1, (C)))
#define _mm512_mask_roundscale_round_ph(A, B, C, D, E) \
- (__builtin_ia32_vrndscaleph_v32hf_mask_round ((C), (D), (A), (B), (E)))
+ (__builtin_ia32_rndscaleph512_mask_round ((C), (D), (A), (B), (E)))
-#define _mm512_maskz_roundscale_round_ph(A, B, C, D) \
- (__builtin_ia32_vrndscaleph_v32hf_mask_round ((B), (C), \
- _mm512_setzero_ph (), \
- (A), (D)))
+#define _mm512_maskz_roundscale_round_ph(A, B, C, D) \
+ (__builtin_ia32_rndscaleph512_mask_round ((B), (C), \
+ _mm512_setzero_ph (), \
+ (A), (D)))
#endif /* __OPTIMIZE__ */
/* Intrinsics vrndscalesh. */
#ifdef __OPTIMIZE__
extern __inline __m128h
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_roundscale_sh (__m128h __A, __m128h __B, int __C)
{
- return __builtin_ia32_vrndscalesh_v8hf_mask_round (__A, __B, __C,
- _mm_setzero_ph (),
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_rndscalesh_mask_round (__A, __B, __C,
+ _mm_setzero_ph (),
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128h
@@ -1909,27 +1909,27 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_roundscale_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, int __E)
{
- return __builtin_ia32_vrndscalesh_v8hf_mask_round (__C, __D, __E, __A, __B,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_rndscalesh_mask_round (__C, __D, __E, __A, __B,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_roundscale_sh (__mmask8 __A, __m128h __B, __m128h __C, int __D)
{
- return __builtin_ia32_vrndscalesh_v8hf_mask_round (__B, __C, __D,
- _mm_setzero_ph (), __A,
- _MM_FROUND_CUR_DIRECTION);
+ return __builtin_ia32_rndscalesh_mask_round (__B, __C, __D,
+ _mm_setzero_ph (), __A,
+ _MM_FROUND_CUR_DIRECTION);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_roundscale_round_sh (__m128h __A, __m128h __B, int __C, const int __D)
{
- return __builtin_ia32_vrndscalesh_v8hf_mask_round (__A, __B, __C,
- _mm_setzero_ph (),
- (__mmask8) -1,
- __D);
+ return __builtin_ia32_rndscalesh_mask_round (__A, __B, __C,
+ _mm_setzero_ph (),
+ (__mmask8) -1,
+ __D);
}
extern __inline __m128h
@@ -1937,8 +1937,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_roundscale_round_sh (__m128h __A, __mmask8 __B, __m128h __C,
__m128h __D, int __E, const int __F)
{
- return __builtin_ia32_vrndscalesh_v8hf_mask_round (__C, __D, __E,
- __A, __B, __F);
+ return __builtin_ia32_rndscalesh_mask_round (__C, __D, __E,
+ __A, __B, __F);
}
extern __inline __m128h
@@ -1946,46 +1946,46 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_roundscale_round_sh (__mmask8 __A, __m128h __B, __m128h __C,
int __D, const int __E)
{
- return __builtin_ia32_vrndscalesh_v8hf_mask_round (__B, __C, __D,
- _mm_setzero_ph (),
- __A, __E);
+ return __builtin_ia32_rndscalesh_mask_round (__B, __C, __D,
+ _mm_setzero_ph (),
+ __A, __E);
}
#else
#define _mm_roundscale_sh(A, B, C) \
- (__builtin_ia32_vrndscalesh_v8hf_mask_round ((A), (B), (C), \
- _mm_setzero_ph (), \
- (__mmask8)-1, \
- _MM_FROUND_CUR_DIRECTION))
+ (__builtin_ia32_rndscalesh_mask_round ((A), (B), (C), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, \
+ _MM_FROUND_CUR_DIRECTION))
#define _mm_mask_roundscale_sh(A, B, C, D, E) \
- (__builtin_ia32_vrndscalesh_v8hf_mask_round ((C), (D), (E), (A), (B), \
- _MM_FROUND_CUR_DIRECTION))
+ (__builtin_ia32_rndscalesh_mask_round ((C), (D), (E), (A), (B), \
+ _MM_FROUND_CUR_DIRECTION))
#define _mm_maskz_roundscale_sh(A, B, C, D) \
- (__builtin_ia32_vrndscalesh_v8hf_mask_round ((B), (C), (D), \
- _mm_setzero_ph (), \
- (A), _MM_FROUND_CUR_DIRECTION))
+ (__builtin_ia32_rndscalesh_mask_round ((B), (C), (D), \
+ _mm_setzero_ph (), \
+ (A), _MM_FROUND_CUR_DIRECTION))
-#define _mm_roundscale_round_sh(A, B, C, D) \
- (__builtin_ia32_vrndscalesh_v8hf_mask_round ((A), (B), (C), \
- _mm_setzero_ph (), \
- (__mmask8)-1, (D)))
+#define _mm_roundscale_round_sh(A, B, C, D) \
+ (__builtin_ia32_rndscalesh_mask_round ((A), (B), (C), \
+ _mm_setzero_ph (), \
+ (__mmask8)-1, (D)))
#define _mm_mask_roundscale_round_sh(A, B, C, D, E, F) \
- (__builtin_ia32_vrndscalesh_v8hf_mask_round ((C), (D), (E), (A), (B), (F)))
+ (__builtin_ia32_rndscalesh_mask_round ((C), (D), (E), (A), (B), (F)))
-#define _mm_maskz_roundscale_round_sh(A, B, C, D, E) \
- (__builtin_ia32_vrndscalesh_v8hf_mask_round ((B), (C), (D), \
- _mm_setzero_ph (), \
- (A), (E)))
+#define _mm_maskz_roundscale_round_sh(A, B, C, D, E) \
+ (__builtin_ia32_rndscalesh_mask_round ((B), (C), (D), \
+ _mm_setzero_ph (), \
+ (A), (E)))
#endif /* __OPTIMIZE__ */
/* Intrinsics vfpclasssh. */
#ifdef __OPTIMIZE__
extern __inline __mmask8
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_fpclass_sh_mask (__m128h __A, const int __imm)
{
return (__mmask8) __builtin_ia32_fpclasssh_mask ((__v8hf) __A, __imm,
@@ -2031,11 +2031,11 @@ _mm512_fpclass_ph_mask (__m512h __A, const int __imm)
#else
#define _mm512_mask_fpclass_ph_mask(u, x, c) \
- ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x),\
+ ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x), \
(int) (c),(__mmask8)(u)))
#define _mm512_fpclass_ph_mask(x, c) \
- ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x),\
+ ((__mmask32) __builtin_ia32_fpclassph512_mask ((__v32hf) (__m512h) (x), \
(int) (c),(__mmask8)-1))
#endif /* __OPIMTIZE__ */
@@ -2141,9 +2141,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_getexp_round_ph (__m512h __A, const int __R)
{
return (__m512h) __builtin_ia32_getexpph512_mask ((__v32hf) __A,
- (__v32hf)
- _mm512_setzero_ph (),
- (__mmask32) -1, __R);
+ (__v32hf)
+ _mm512_setzero_ph (),
+ (__mmask32) -1, __R);
}
extern __inline __m512h
@@ -2152,8 +2152,8 @@ _mm512_mask_getexp_round_ph (__m512h __W, __mmask32 __U, __m512h __A,
const int __R)
{
return (__m512h) __builtin_ia32_getexpph512_mask ((__v32hf) __A,
- (__v32hf) __W,
- (__mmask32) __U, __R);
+ (__v32hf) __W,
+ (__mmask32) __U, __R);
}
extern __inline __m512h
@@ -2161,37 +2161,37 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_getexp_round_ph (__mmask32 __U, __m512h __A, const int __R)
{
return (__m512h) __builtin_ia32_getexpph512_mask ((__v32hf) __A,
- (__v32hf)
- _mm512_setzero_ph (),
- (__mmask32) __U, __R);
+ (__v32hf)
+ _mm512_setzero_ph (),
+ (__mmask32) __U, __R);
}
#else
-#define _mm_getexp_round_sh(A, B, R) \
- ((__m128h)__builtin_ia32_getexpsh_mask_round((__v8hf)(__m128h)(A), \
- (__v8hf)(__m128h)(B), \
- (__v8hf)_mm_setzero_ph(), \
+#define _mm_getexp_round_sh(A, B, R) \
+ ((__m128h)__builtin_ia32_getexpsh_mask_round((__v8hf)(__m128h)(A), \
+ (__v8hf)(__m128h)(B), \
+ (__v8hf)_mm_setzero_ph(), \
(__mmask8)-1, R))
-#define _mm_mask_getexp_round_sh(W, U, A, B, C) \
+#define _mm_mask_getexp_round_sh(W, U, A, B, C) \
(__m128h)__builtin_ia32_getexpsh_mask_round(A, B, W, U, C)
-#define _mm_maskz_getexp_round_sh(U, A, B, C) \
- (__m128h)__builtin_ia32_getexpsh_mask_round(A, B, \
- (__v8hf)_mm_setzero_ph(), \
+#define _mm_maskz_getexp_round_sh(U, A, B, C) \
+ (__m128h)__builtin_ia32_getexpsh_mask_round(A, B, \
+ (__v8hf)_mm_setzero_ph(), \
U, C)
-#define _mm512_getexp_round_ph(A, R) \
- ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
- (__v32hf)_mm512_setzero_ph(), (__mmask32)-1, R))
+#define _mm512_getexp_round_ph(A, R) \
+ ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
+ (__v32hf)_mm512_setzero_ph(), (__mmask32)-1, R))
-#define _mm512_mask_getexp_round_ph(W, U, A, R) \
- ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
- (__v32hf)(__m512h)(W), (__mmask32)(U), R))
+#define _mm512_mask_getexp_round_ph(W, U, A, R) \
+ ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
+ (__v32hf)(__m512h)(W), (__mmask32)(U), R))
-#define _mm512_maskz_getexp_round_ph(U, A, R) \
- ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
- (__v32hf)_mm512_setzero_ph(), (__mmask32)(U), R))
+#define _mm512_maskz_getexp_round_ph(U, A, R) \
+ ((__m512h)__builtin_ia32_getexpph512_mask((__v32hf)(__m512h)(A), \
+ (__v32hf)_mm512_setzero_ph(), (__mmask32)(U), R))
#endif /* __OPTIMIZE__ */
@@ -53,30 +53,30 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_add_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vaddph_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_addph128_mask (__C, __D, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_add_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
{
- return __builtin_ia32_vaddph_v16hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_addph256_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_add_ph (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vaddph_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_addph128_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_add_ph (__mmask16 __A, __m256h __B, __m256h __C)
{
- return __builtin_ia32_vaddph_v16hf_mask (__B, __C,
- _mm256_setzero_ph (), __A);
+ return __builtin_ia32_addph256_mask (__B, __C,
+ _mm256_setzero_ph (), __A);
}
extern __inline __m128h
@@ -97,30 +97,30 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_sub_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vsubph_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_subph128_mask (__C, __D, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_sub_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
{
- return __builtin_ia32_vsubph_v16hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_subph256_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_sub_ph (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vsubph_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_subph128_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_sub_ph (__mmask16 __A, __m256h __B, __m256h __C)
{
- return __builtin_ia32_vsubph_v16hf_mask (__B, __C,
- _mm256_setzero_ph (), __A);
+ return __builtin_ia32_subph256_mask (__B, __C,
+ _mm256_setzero_ph (), __A);
}
extern __inline __m128h
@@ -141,30 +141,30 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_mul_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vmulph_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_mulph128_mask (__C, __D, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_mul_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
{
- return __builtin_ia32_vmulph_v16hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_mulph256_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_mul_ph (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vmulph_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_mulph128_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_mul_ph (__mmask16 __A, __m256h __B, __m256h __C)
{
- return __builtin_ia32_vmulph_v16hf_mask (__B, __C,
- _mm256_setzero_ph (), __A);
+ return __builtin_ia32_mulph256_mask (__B, __C,
+ _mm256_setzero_ph (), __A);
}
extern __inline __m128h
@@ -185,30 +185,30 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_div_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vdivph_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_divph128_mask (__C, __D, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_div_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
{
- return __builtin_ia32_vdivph_v16hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_divph256_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_div_ph (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vdivph_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_divph128_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_div_ph (__mmask16 __A, __m256h __B, __m256h __C)
{
- return __builtin_ia32_vdivph_v16hf_mask (__B, __C,
- _mm256_setzero_ph (), __A);
+ return __builtin_ia32_divph256_mask (__B, __C,
+ _mm256_setzero_ph (), __A);
}
/* Intrinsics v[max,min]ph. */
@@ -216,96 +216,96 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_max_ph (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vmaxph_v8hf_mask (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1);
+ return __builtin_ia32_maxph128_mask (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_max_ph (__m256h __A, __m256h __B)
{
- return __builtin_ia32_vmaxph_v16hf_mask (__A, __B,
- _mm256_setzero_ph (),
- (__mmask16) -1);
+ return __builtin_ia32_maxph256_mask (__A, __B,
+ _mm256_setzero_ph (),
+ (__mmask16) -1);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_max_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vmaxph_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_maxph128_mask (__C, __D, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_max_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
{
- return __builtin_ia32_vmaxph_v16hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_maxph256_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_max_ph (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vmaxph_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_maxph128_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_max_ph (__mmask16 __A, __m256h __B, __m256h __C)
{
- return __builtin_ia32_vmaxph_v16hf_mask (__B, __C,
- _mm256_setzero_ph (), __A);
+ return __builtin_ia32_maxph256_mask (__B, __C,
+ _mm256_setzero_ph (), __A);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_min_ph (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vminph_v8hf_mask (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1);
+ return __builtin_ia32_minph128_mask (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_min_ph (__m256h __A, __m256h __B)
{
- return __builtin_ia32_vminph_v16hf_mask (__A, __B,
- _mm256_setzero_ph (),
- (__mmask16) -1);
+ return __builtin_ia32_minph256_mask (__A, __B,
+ _mm256_setzero_ph (),
+ (__mmask16) -1);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_min_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vminph_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_minph128_mask (__C, __D, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_min_ph (__m256h __A, __mmask16 __B, __m256h __C, __m256h __D)
{
- return __builtin_ia32_vminph_v16hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_minph256_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_min_ph (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vminph_v8hf_mask (__B, __C, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_minph128_mask (__B, __C, _mm_setzero_ph (),
+ __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_min_ph (__mmask16 __A, __m256h __B, __m256h __C)
{
- return __builtin_ia32_vminph_v16hf_mask (__B, __C,
- _mm256_setzero_ph (), __A);
+ return __builtin_ia32_minph256_mask (__B, __C,
+ _mm256_setzero_ph (), __A);
}
/* vcmpph */
@@ -314,8 +314,8 @@ extern __inline __mmask8
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmp_ph_mask (__m128h __A, __m128h __B, const int __C)
{
- return (__mmask8) __builtin_ia32_vcmpph_v8hf_mask (__A, __B, __C,
- (__mmask8) -1);
+ return (__mmask8) __builtin_ia32_cmpph128_mask (__A, __B, __C,
+ (__mmask8) -1);
}
extern __inline __mmask8
@@ -323,15 +323,15 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_cmp_ph_mask (__mmask8 __A, __m128h __B, __m128h __C,
const int __D)
{
- return (__mmask8) __builtin_ia32_vcmpph_v8hf_mask (__B, __C, __D, __A);
+ return (__mmask8) __builtin_ia32_cmpph128_mask (__B, __C, __D, __A);
}
extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_cmp_ph_mask (__m256h __A, __m256h __B, const int __C)
{
- return (__mmask16) __builtin_ia32_vcmpph_v16hf_mask (__A, __B, __C,
- (__mmask16) -1);
+ return (__mmask16) __builtin_ia32_cmpph256_mask (__A, __B, __C,
+ (__mmask16) -1);
}
extern __inline __mmask16
@@ -339,22 +339,22 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_cmp_ph_mask (__mmask16 __A, __m256h __B, __m256h __C,
const int __D)
{
- return (__mmask16) __builtin_ia32_vcmpph_v16hf_mask (__B, __C, __D,
- __A);
+ return (__mmask16) __builtin_ia32_cmpph256_mask (__B, __C, __D,
+ __A);
}
#else
-#define _mm_cmp_ph_mask(A, B, C) \
- (__builtin_ia32_vcmpph_v8hf_mask ((A), (B), (C), (-1)))
+#define _mm_cmp_ph_mask(A, B, C) \
+ (__builtin_ia32_cmpph128_mask ((A), (B), (C), (-1)))
-#define _mm_mask_cmp_ph_mask(A, B, C, D) \
- (__builtin_ia32_vcmpph_v8hf_mask ((B), (C), (D), (A)))
+#define _mm_mask_cmp_ph_mask(A, B, C, D) \
+ (__builtin_ia32_cmpph128_mask ((B), (C), (D), (A)))
-#define _mm256_cmp_ph_mask(A, B, C) \
- (__builtin_ia32_vcmpph_v16hf_mask ((A), (B), (C), (-1)))
+#define _mm256_cmp_ph_mask(A, B, C) \
+ (__builtin_ia32_cmpph256_mask ((A), (B), (C), (-1)))
-#define _mm256_mask_cmp_ph_mask(A, B, C, D) \
- (__builtin_ia32_vcmpph_v16hf_mask ((B), (C), (D), (A)))
+#define _mm256_mask_cmp_ph_mask(A, B, C, D) \
+ (__builtin_ia32_cmpph256_mask ((B), (C), (D), (A)))
#endif /* __OPTIMIZE__ */
@@ -363,46 +363,46 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_sqrt_ph (__m128h __A)
{
- return __builtin_ia32_vsqrtph_v8hf_mask (__A, _mm_setzero_ph (),
- (__mmask8) -1);
+ return __builtin_ia32_sqrtph128_mask (__A, _mm_setzero_ph (),
+ (__mmask8) -1);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_sqrt_ph (__m256h __A)
{
- return __builtin_ia32_vsqrtph_v16hf_mask (__A, _mm256_setzero_ph (),
- (__mmask16) -1);
+ return __builtin_ia32_sqrtph256_mask (__A, _mm256_setzero_ph (),
+ (__mmask16) -1);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_sqrt_ph (__m128h __A, __mmask8 __B, __m128h __C)
{
- return __builtin_ia32_vsqrtph_v8hf_mask (__C, __A, __B);
+ return __builtin_ia32_sqrtph128_mask (__C, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_sqrt_ph (__m256h __A, __mmask16 __B, __m256h __C)
{
- return __builtin_ia32_vsqrtph_v16hf_mask (__C, __A, __B);
+ return __builtin_ia32_sqrtph256_mask (__C, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_sqrt_ph (__mmask8 __A, __m128h __B)
{
- return __builtin_ia32_vsqrtph_v8hf_mask (__B, _mm_setzero_ph (),
- __A);
+ return __builtin_ia32_sqrtph128_mask (__B, _mm_setzero_ph (),
+ __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_sqrt_ph (__mmask16 __A, __m256h __B)
{
- return __builtin_ia32_vsqrtph_v16hf_mask (__B, _mm256_setzero_ph (),
- __A);
+ return __builtin_ia32_sqrtph256_mask (__B, _mm256_setzero_ph (),
+ __A);
}
/* Intrinsics vrsqrtph. */
@@ -410,45 +410,45 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rsqrt_ph (__m128h __A)
{
- return __builtin_ia32_vrsqrtph_v8hf_mask (__A, _mm_setzero_ph (),
- (__mmask8) -1);
+ return __builtin_ia32_rsqrtph128_mask (__A, _mm_setzero_ph (),
+ (__mmask8) -1);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_rsqrt_ph (__m256h __A)
{
- return __builtin_ia32_vrsqrtph_v16hf_mask (__A, _mm256_setzero_ph (),
- (__mmask16) -1);
+ return __builtin_ia32_rsqrtph256_mask (__A, _mm256_setzero_ph (),
+ (__mmask16) -1);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_rsqrt_ph (__m128h __A, __mmask8 __B, __m128h __C)
{
- return __builtin_ia32_vrsqrtph_v8hf_mask (__C, __A, __B);
+ return __builtin_ia32_rsqrtph128_mask (__C, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_rsqrt_ph (__m256h __A, __mmask16 __B, __m256h __C)
{
- return __builtin_ia32_vrsqrtph_v16hf_mask (__C, __A, __B);
+ return __builtin_ia32_rsqrtph256_mask (__C, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_rsqrt_ph (__mmask8 __A, __m128h __B)
{
- return __builtin_ia32_vrsqrtph_v8hf_mask (__B, _mm_setzero_ph (), __A);
+ return __builtin_ia32_rsqrtph128_mask (__B, _mm_setzero_ph (), __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_rsqrt_ph (__mmask16 __A, __m256h __B)
{
- return __builtin_ia32_vrsqrtph_v16hf_mask (__B, _mm256_setzero_ph (),
- __A);
+ return __builtin_ia32_rsqrtph256_mask (__B, _mm256_setzero_ph (),
+ __A);
}
/* Intrinsics vrcpph. */
@@ -456,45 +456,45 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rcp_ph (__m128h __A)
{
- return __builtin_ia32_vrcpph_v8hf_mask (__A, _mm_setzero_ph (),
- (__mmask8) -1);
+ return __builtin_ia32_rcpph128_mask (__A, _mm_setzero_ph (),
+ (__mmask8) -1);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_rcp_ph (__m256h __A)
{
- return __builtin_ia32_vrcpph_v16hf_mask (__A, _mm256_setzero_ph (),
- (__mmask16) -1);
+ return __builtin_ia32_rcpph256_mask (__A, _mm256_setzero_ph (),
+ (__mmask16) -1);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_rcp_ph (__m128h __A, __mmask8 __B, __m128h __C)
{
- return __builtin_ia32_vrcpph_v8hf_mask (__C, __A, __B);
+ return __builtin_ia32_rcpph128_mask (__C, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_rcp_ph (__m256h __A, __mmask16 __B, __m256h __C)
{
- return __builtin_ia32_vrcpph_v16hf_mask (__C, __A, __B);
+ return __builtin_ia32_rcpph256_mask (__C, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_rcp_ph (__mmask8 __A, __m128h __B)
{
- return __builtin_ia32_vrcpph_v8hf_mask (__B, _mm_setzero_ph (), __A);
+ return __builtin_ia32_rcpph128_mask (__B, _mm_setzero_ph (), __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_rcp_ph (__mmask16 __A, __m256h __B)
{
- return __builtin_ia32_vrcpph_v16hf_mask (__B, _mm256_setzero_ph (),
- __A);
+ return __builtin_ia32_rcpph256_mask (__B, _mm256_setzero_ph (),
+ __A);
}
/* Intrinsics vscalefph. */
@@ -502,25 +502,25 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_scalef_ph (__m128h __A, __m128h __B)
{
- return __builtin_ia32_vscalefph_v8hf_mask (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1);
+ return __builtin_ia32_scalefph128_mask (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_scalef_ph (__m256h __A, __m256h __B)
{
- return __builtin_ia32_vscalefph_v16hf_mask (__A, __B,
- _mm256_setzero_ph (),
- (__mmask16) -1);
+ return __builtin_ia32_scalefph256_mask (__A, __B,
+ _mm256_setzero_ph (),
+ (__mmask16) -1);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_scalef_ph (__m128h __A, __mmask8 __B, __m128h __C, __m128h __D)
{
- return __builtin_ia32_vscalefph_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_scalefph128_mask (__C, __D, __A, __B);
}
extern __inline __m256h
@@ -528,24 +528,24 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_scalef_ph (__m256h __A, __mmask16 __B, __m256h __C,
__m256h __D)
{
- return __builtin_ia32_vscalefph_v16hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_scalefph256_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_scalef_ph (__mmask8 __A, __m128h __B, __m128h __C)
{
- return __builtin_ia32_vscalefph_v8hf_mask (__B, __C,
- _mm_setzero_ph (), __A);
+ return __builtin_ia32_scalefph128_mask (__B, __C,
+ _mm_setzero_ph (), __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_scalef_ph (__mmask16 __A, __m256h __B, __m256h __C)
{
- return __builtin_ia32_vscalefph_v16hf_mask (__B, __C,
- _mm256_setzero_ph (),
- __A);
+ return __builtin_ia32_scalefph256_mask (__B, __C,
+ _mm256_setzero_ph (),
+ __A);
}
/* Intrinsics vreduceph. */
@@ -554,109 +554,109 @@ extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_reduce_ph (__m128h __A, int __B)
{
- return __builtin_ia32_vreduceph_v8hf_mask (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1);
+ return __builtin_ia32_reduceph128_mask (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_reduce_ph (__m128h __A, __mmask8 __B, __m128h __C, int __D)
{
- return __builtin_ia32_vreduceph_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_reduceph128_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_reduce_ph (__mmask8 __A, __m128h __B, int __C)
{
- return __builtin_ia32_vreduceph_v8hf_mask (__B, __C,
- _mm_setzero_ph (), __A);
+ return __builtin_ia32_reduceph128_mask (__B, __C,
+ _mm_setzero_ph (), __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_reduce_ph (__m256h __A, int __B)
{
- return __builtin_ia32_vreduceph_v16hf_mask (__A, __B,
- _mm256_setzero_ph (),
- (__mmask16) -1);
+ return __builtin_ia32_reduceph256_mask (__A, __B,
+ _mm256_setzero_ph (),
+ (__mmask16) -1);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_reduce_ph (__m256h __A, __mmask16 __B, __m256h __C, int __D)
{
- return __builtin_ia32_vreduceph_v16hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_reduceph256_mask (__C, __D, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_reduce_ph (__mmask16 __A, __m256h __B, int __C)
{
- return __builtin_ia32_vreduceph_v16hf_mask (__B, __C,
- _mm256_setzero_ph (),
- __A);
+ return __builtin_ia32_reduceph256_mask (__B, __C,
+ _mm256_setzero_ph (),
+ __A);
}
#else
-#define _mm_reduce_ph(A, B) \
- (__builtin_ia32_vreduceph_v8hf_mask ((A), (B),\
- _mm_setzero_ph (), \
- ((__mmask8)-1)))
+#define _mm_reduce_ph(A, B) \
+ (__builtin_ia32_reduceph128_mask ((A), (B), \
+ _mm_setzero_ph (), \
+ ((__mmask8)-1)))
-#define _mm_mask_reduce_ph(A, B, C, D) \
- (__builtin_ia32_vreduceph_v8hf_mask ((C), (D), (A), (B)))
+#define _mm_mask_reduce_ph(A, B, C, D) \
+ (__builtin_ia32_reduceph128_mask ((C), (D), (A), (B)))
-#define _mm_maskz_reduce_ph(A, B, C) \
- (__builtin_ia32_vreduceph_v8hf_mask ((B), (C), _mm_setzero_ph (), (A)))
+#define _mm_maskz_reduce_ph(A, B, C) \
+ (__builtin_ia32_reduceph128_mask ((B), (C), _mm_setzero_ph (), (A)))
#define _mm256_reduce_ph(A, B) \
- (__builtin_ia32_vreduceph_v16hf_mask ((A), (B),\
- _mm256_setzero_ph (), \
- ((__mmask16)-1)))
+ (__builtin_ia32_reduceph256_mask ((A), (B), \
+ _mm256_setzero_ph (), \
+ ((__mmask16)-1)))
-#define _mm256_mask_reduce_ph(A, B, C, D) \
- (__builtin_ia32_vreduceph_v16hf_mask ((C), (D), (A), (B)))
+#define _mm256_mask_reduce_ph(A, B, C, D) \
+ (__builtin_ia32_reduceph256_mask ((C), (D), (A), (B)))
-#define _mm256_maskz_reduce_ph(A, B, C) \
- (__builtin_ia32_vreduceph_v16hf_mask ((B), (C), _mm256_setzero_ph (), (A)))
+#define _mm256_maskz_reduce_ph(A, B, C) \
+ (__builtin_ia32_reduceph256_mask ((B), (C), _mm256_setzero_ph (), (A)))
#endif /* __OPTIMIZE__ */
/* Intrinsics vrndscaleph. */
#ifdef __OPTIMIZE__
-extern __inline __m128h
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_roundscale_ph (__m128h __A, int __B)
-{
- return __builtin_ia32_vrndscaleph_v8hf_mask (__A, __B,
- _mm_setzero_ph (),
- (__mmask8) -1);
-}
+ extern __inline __m128h
+ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+ _mm_roundscale_ph (__m128h __A, int __B)
+ {
+ return __builtin_ia32_rndscaleph128_mask (__A, __B,
+ _mm_setzero_ph (),
+ (__mmask8) -1);
+ }
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_roundscale_ph (__m128h __A, __mmask8 __B, __m128h __C, int __D)
{
- return __builtin_ia32_vrndscaleph_v8hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_rndscaleph128_mask (__C, __D, __A, __B);
}
extern __inline __m128h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_roundscale_ph (__mmask8 __A, __m128h __B, int __C)
{
- return __builtin_ia32_vrndscaleph_v8hf_mask (__B, __C,
- _mm_setzero_ph (), __A);
+ return __builtin_ia32_rndscaleph128_mask (__B, __C,
+ _mm_setzero_ph (), __A);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_roundscale_ph (__m256h __A, int __B)
{
- return __builtin_ia32_vrndscaleph_v16hf_mask (__A, __B,
- _mm256_setzero_ph (),
- (__mmask16) -1);
+ return __builtin_ia32_rndscaleph256_mask (__A, __B,
+ _mm256_setzero_ph (),
+ (__mmask16) -1);
}
extern __inline __m256h
@@ -664,40 +664,40 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_roundscale_ph (__m256h __A, __mmask16 __B, __m256h __C,
int __D)
{
- return __builtin_ia32_vrndscaleph_v16hf_mask (__C, __D, __A, __B);
+ return __builtin_ia32_rndscaleph256_mask (__C, __D, __A, __B);
}
extern __inline __m256h
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_roundscale_ph (__mmask16 __A, __m256h __B, int __C)
{
- return __builtin_ia32_vrndscaleph_v16hf_mask (__B, __C,
- _mm256_setzero_ph (),
- __A);
+ return __builtin_ia32_rndscaleph256_mask (__B, __C,
+ _mm256_setzero_ph (),
+ __A);
}
#else
-#define _mm_roundscale_ph(A, B) \
- (__builtin_ia32_vrndscaleph_v8hf_mask ((A), (B), _mm_setzero_ph (), \
- ((__mmask8)-1)))
+#define _mm_roundscale_ph(A, B) \
+ (__builtin_ia32_rndscaleph128_mask ((A), (B), _mm_setzero_ph (), \
+ ((__mmask8)-1)))
-#define _mm_mask_roundscale_ph(A, B, C, D) \
- (__builtin_ia32_vrndscaleph_v8hf_mask ((C), (D), (A), (B)))
+#define _mm_mask_roundscale_ph(A, B, C, D) \
+ (__builtin_ia32_rndscaleph128_mask ((C), (D), (A), (B)))
-#define _mm_maskz_roundscale_ph(A, B, C) \
- (__builtin_ia32_vrndscaleph_v8hf_mask ((B), (C), _mm_setzero_ph (), (A)))
+#define _mm_maskz_roundscale_ph(A, B, C) \
+ (__builtin_ia32_rndscaleph128_mask ((B), (C), _mm_setzero_ph (), (A)))
-#define _mm256_roundscale_ph(A, B) \
- (__builtin_ia32_vrndscaleph_v16hf_mask ((A), (B), \
- _mm256_setzero_ph(), \
- ((__mmask16)-1)))
+#define _mm256_roundscale_ph(A, B) \
+ (__builtin_ia32_rndscaleph256_mask ((A), (B), \
+ _mm256_setzero_ph(), \
+ ((__mmask16)-1)))
-#define _mm256_mask_roundscale_ph(A, B, C, D) \
- (__builtin_ia32_vrndscaleph_v16hf_mask ((C), (D), (A), (B)))
+#define _mm256_mask_roundscale_ph(A, B, C, D) \
+ (__builtin_ia32_rndscaleph256_mask ((C), (D), (A), (B)))
-#define _mm256_maskz_roundscale_ph(A, B, C) \
- (__builtin_ia32_vrndscaleph_v16hf_mask ((B), (C), \
- _mm256_setzero_ph (), (A)))
+#define _mm256_maskz_roundscale_ph(A, B, C) \
+ (__builtin_ia32_rndscaleph256_mask ((B), (C), \
+ _mm256_setzero_ph (), (A)))
#endif /* __OPTIMIZE__ */
@@ -705,7 +705,7 @@ _mm256_maskz_roundscale_ph (__mmask16 __A, __m256h __B, int __C)
#ifdef __OPTIMIZE__
extern __inline __mmask8
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_fpclass_ph_mask (__mmask8 __U, __m128h __A, const int __imm)
+ _mm_mask_fpclass_ph_mask (__mmask8 __U, __m128h __A, const int __imm)
{
return (__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) __A,
__imm, __U);
@@ -725,7 +725,7 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_fpclass_ph_mask (__mmask16 __U, __m256h __A, const int __imm)
{
return (__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) __A,
- __imm, __U);
+ __imm, __U);
}
extern __inline __mmask16
@@ -733,26 +733,26 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_fpclass_ph_mask (__m256h __A, const int __imm)
{
return (__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) __A,
- __imm,
- (__mmask16) -1);
+ __imm,
+ (__mmask16) -1);
}
#else
#define _mm_fpclass_ph_mask(X, C) \
- ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
+ ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
(int) (C),(__mmask8)-1))
#define _mm_mask_fpclass_ph_mask(u, X, C) \
- ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
+ ((__mmask8) __builtin_ia32_fpclassph128_mask ((__v8hf) (__m128h) (X), \
(int) (C),(__mmask8)(u)))
#define _mm256_fpclass_ph_mask(X, C) \
- ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
- (int) (C),(__mmask16)-1))
+ ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
+ (int) (C),(__mmask16)-1))
#define _mm256_mask_fpclass_ph_mask(u, X, C) \
- ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
- (int) (C),(__mmask16)(u)))
+ ((__mmask16) __builtin_ia32_fpclassph256_mask ((__v16hf) (__m256h) (X), \
+ (int) (C),(__mmask16)(u)))
#endif /* __OPTIMIZE__ */
/* Intrinsics vgetexpph, vgetexpsh. */
@@ -761,9 +761,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_getexp_ph (__m256h __A)
{
return (__m256h) __builtin_ia32_getexpph256_mask ((__v16hf) __A,
- (__v16hf)
- _mm256_setzero_ph (),
- (__mmask16) -1);
+ (__v16hf)
+ _mm256_setzero_ph (),
+ (__mmask16) -1);
}
extern __inline __m256h
@@ -771,8 +771,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_getexp_ph (__m256h __W, __mmask16 __U, __m256h __A)
{
return (__m256h) __builtin_ia32_getexpph256_mask ((__v16hf) __A,
- (__v16hf) __W,
- (__mmask16) __U);
+ (__v16hf) __W,
+ (__mmask16) __U);
}
extern __inline __m256h
@@ -780,9 +780,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_getexp_ph (__mmask16 __U, __m256h __A)
{
return (__m256h) __builtin_ia32_getexpph256_mask ((__v16hf) __A,
- (__v16hf)
- _mm256_setzero_ph (),
- (__mmask16) __U);
+ (__v16hf)
+ _mm256_setzero_ph (),
+ (__mmask16) __U);
}
extern __inline __m128h
@@ -790,9 +790,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_getexp_ph (__m128h __A)
{
return (__m128h) __builtin_ia32_getexpph128_mask ((__v8hf) __A,
- (__v8hf)
- _mm_setzero_ph (),
- (__mmask8) -1);
+ (__v8hf)
+ _mm_setzero_ph (),
+ (__mmask8) -1);
}
extern __inline __m128h
@@ -800,8 +800,8 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_getexp_ph (__m128h __W, __mmask8 __U, __m128h __A)
{
return (__m128h) __builtin_ia32_getexpph128_mask ((__v8hf) __A,
- (__v8hf) __W,
- (__mmask8) __U);
+ (__v8hf) __W,
+ (__mmask8) __U);
}
extern __inline __m128h
@@ -809,9 +809,9 @@ __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_getexp_ph (__mmask8 __U, __m128h __A)
{
return (__m128h) __builtin_ia32_getexpph128_mask ((__v8hf) __A,
- (__v8hf)
- _mm_setzero_ph (),
- (__mmask8) __U);
+ (__v8hf)
+ _mm_setzero_ph (),
+ (__mmask8) __U);
}
@@ -892,41 +892,41 @@ _mm_maskz_getmant_ph (__mmask8 __U, __m128h __A,
}
#else
-#define _mm256_getmant_ph(X, B, C) \
- ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
- (int)(((C)<<2) | (B)), \
- (__v16hf)(__m256h)_mm256_setzero_ph (),\
- (__mmask16)-1))
-
-#define _mm256_mask_getmant_ph(W, U, X, B, C) \
- ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
- (int)(((C)<<2) | (B)), \
- (__v16hf)(__m256h)(W), \
- (__mmask16)(U)))
-
-#define _mm256_maskz_getmant_ph(U, X, B, C) \
- ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
- (int)(((C)<<2) | (B)), \
- (__v16hf)(__m256h)_mm256_setzero_ph (),\
- (__mmask16)(U)))
-
-#define _mm_getmant_ph(X, B, C) \
- ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
- (int)(((C)<<2) | (B)), \
- (__v8hf)(__m128h)_mm_setzero_ph (), \
- (__mmask8)-1))
-
-#define _mm_mask_getmant_ph(W, U, X, B, C) \
- ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
- (int)(((C)<<2) | (B)), \
- (__v8hf)(__m128h)(W), \
- (__mmask8)(U)))
-
-#define _mm_maskz_getmant_ph(U, X, B, C) \
- ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
- (int)(((C)<<2) | (B)), \
- (__v8hf)(__m128h)_mm_setzero_ph (), \
- (__mmask8)(U)))
+#define _mm256_getmant_ph(X, B, C) \
+ ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
+ (int)(((C)<<2) | (B)), \
+ (__v16hf)(__m256h)_mm256_setzero_ph (), \
+ (__mmask16)-1))
+
+#define _mm256_mask_getmant_ph(W, U, X, B, C) \
+ ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
+ (int)(((C)<<2) | (B)), \
+ (__v16hf)(__m256h)(W), \
+ (__mmask16)(U)))
+
+#define _mm256_maskz_getmant_ph(U, X, B, C) \
+ ((__m256h) __builtin_ia32_getmantph256_mask ((__v16hf)(__m256h) (X), \
+ (int)(((C)<<2) | (B)), \
+ (__v16hf)(__m256h)_mm256_setzero_ph (), \
+ (__mmask16)(U)))
+
+#define _mm_getmant_ph(X, B, C) \
+ ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
+ (int)(((C)<<2) | (B)), \
+ (__v8hf)(__m128h)_mm_setzero_ph (), \
+ (__mmask8)-1))
+
+#define _mm_mask_getmant_ph(W, U, X, B, C) \
+ ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
+ (int)(((C)<<2) | (B)), \
+ (__v8hf)(__m128h)(W), \
+ (__mmask8)(U)))
+
+#define _mm_maskz_getmant_ph(U, X, B, C) \
+ ((__m128h) __builtin_ia32_getmantph128_mask ((__v8hf)(__m128h) (X), \
+ (int)(((C)<<2) | (B)), \
+ (__v8hf)(__m128h)_mm_setzero_ph (), \
+ (__mmask8)(U)))
#endif /* __OPTIMIZE__ */
@@ -2775,49 +2775,49 @@ BDESC (0, OPTION_MASK_ISA2_AVX512BF16, CODE_FOR_avx512f_dpbf16ps_v4sf_mask, "__b
BDESC (0, OPTION_MASK_ISA2_AVX512BF16, CODE_FOR_avx512f_dpbf16ps_v4sf_maskz, "__builtin_ia32_dpbf16ps_v4sf_maskz", IX86_BUILTIN_DPHI16PS_V4SF_MASKZ, UNKNOWN, (int) V4SF_FTYPE_V4SF_V8HI_V8HI_UQI)
/* AVX512FP16. */
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv8hf3_mask, "__builtin_ia32_vaddph_v8hf_mask", IX86_BUILTIN_VADDPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv16hf3_mask, "__builtin_ia32_vaddph_v16hf_mask", IX86_BUILTIN_VADDPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask, "__builtin_ia32_vaddph_v32hf_mask", IX86_BUILTIN_VADDPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv8hf3_mask, "__builtin_ia32_vsubph_v8hf_mask", IX86_BUILTIN_VSUBPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv16hf3_mask, "__builtin_ia32_vsubph_v16hf_mask", IX86_BUILTIN_VSUBPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask, "__builtin_ia32_vsubph_v32hf_mask", IX86_BUILTIN_VSUBPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv8hf3_mask, "__builtin_ia32_vmulph_v8hf_mask", IX86_BUILTIN_VMULPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv16hf3_mask, "__builtin_ia32_vmulph_v16hf_mask", IX86_BUILTIN_VMULPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask, "__builtin_ia32_vmulph_v32hf_mask", IX86_BUILTIN_VMULPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv8hf3_mask, "__builtin_ia32_vdivph_v8hf_mask", IX86_BUILTIN_VDIVPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv16hf3_mask, "__builtin_ia32_vdivph_v16hf_mask", IX86_BUILTIN_VDIVPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask, "__builtin_ia32_vdivph_v32hf_mask", IX86_BUILTIN_VDIVPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask, "__builtin_ia32_vaddsh_v8hf_mask", IX86_BUILTIN_VADDSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask, "__builtin_ia32_vsubsh_v8hf_mask", IX86_BUILTIN_VSUBSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask, "__builtin_ia32_vmulsh_v8hf_mask", IX86_BUILTIN_VMULSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask, "__builtin_ia32_vdivsh_v8hf_mask", IX86_BUILTIN_VDIVSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv8hf3_mask, "__builtin_ia32_vmaxph_v8hf_mask", IX86_BUILTIN_VMAXPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv16hf3_mask, "__builtin_ia32_vmaxph_v16hf_mask", IX86_BUILTIN_VMAXPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask, "__builtin_ia32_vmaxph_v32hf_mask", IX86_BUILTIN_VMAXPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv8hf3_mask, "__builtin_ia32_vminph_v8hf_mask", IX86_BUILTIN_VMINPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv16hf3_mask, "__builtin_ia32_vminph_v16hf_mask", IX86_BUILTIN_VMINPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask, "__builtin_ia32_vminph_v32hf_mask", IX86_BUILTIN_VMINPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask, "__builtin_ia32_vmaxsh_v8hf_mask", IX86_BUILTIN_VMAXSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask, "__builtin_ia32_vminsh_v8hf_mask", IX86_BUILTIN_VMINSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_cmpv8hf3_mask, "__builtin_ia32_vcmpph_v8hf_mask", IX86_BUILTIN_VCMPPH_V8HF_MASK, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_cmpv16hf3_mask, "__builtin_ia32_vcmpph_v16hf_mask", IX86_BUILTIN_VCMPPH_V16HF_MASK, UNKNOWN, (int) UHI_FTYPE_V16HF_V16HF_INT_UHI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask, "__builtin_ia32_vcmpph_v32hf_mask", IX86_BUILTIN_VCMPPH_V32HF_MASK, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv8hf2_mask, "__builtin_ia32_vsqrtph_v8hf_mask", IX86_BUILTIN_VSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv16hf2_mask, "__builtin_ia32_vsqrtph_v16hf_mask", IX86_BUILTIN_VSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv8hf2_mask, "__builtin_ia32_vrsqrtph_v8hf_mask", IX86_BUILTIN_VRSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv16hf2_mask, "__builtin_ia32_vrsqrtph_v16hf_mask", IX86_BUILTIN_VRSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv32hf2_mask, "__builtin_ia32_vrsqrtph_v32hf_mask", IX86_BUILTIN_VRSQRTPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrsqrtv8hf2_mask, "__builtin_ia32_vrsqrtsh_v8hf_mask", IX86_BUILTIN_VRSQRTSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv8hf2_mask, "__builtin_ia32_vrcpph_v8hf_mask", IX86_BUILTIN_VRCPPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv16hf2_mask, "__builtin_ia32_vrcpph_v16hf_mask", IX86_BUILTIN_VRCPPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv32hf2_mask, "__builtin_ia32_vrcpph_v32hf_mask", IX86_BUILTIN_VRCPPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrcpv8hf2_mask, "__builtin_ia32_vrcpsh_v8hf_mask", IX86_BUILTIN_VRCPSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_scalefv8hf_mask, "__builtin_ia32_vscalefph_v8hf_mask", IX86_BUILTIN_VSCALEFPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_scalefv16hf_mask, "__builtin_ia32_vscalefph_v16hf_mask", IX86_BUILTIN_VSCALEFPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv8hf_mask, "__builtin_ia32_vreduceph_v8hf_mask", IX86_BUILTIN_VREDUCEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv16hf_mask, "__builtin_ia32_vreduceph_v16hf_mask", IX86_BUILTIN_VREDUCEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rndscalev8hf_mask, "__builtin_ia32_vrndscaleph_v8hf_mask", IX86_BUILTIN_VRNDSCALEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
-BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_rndscalev16hf_mask, "__builtin_ia32_vrndscaleph_v16hf_mask", IX86_BUILTIN_VRNDSCALEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv8hf3_mask, "__builtin_ia32_addph128_mask", IX86_BUILTIN_VADDPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv16hf3_mask, "__builtin_ia32_addph256_mask", IX86_BUILTIN_VADDPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask, "__builtin_ia32_addph512_mask", IX86_BUILTIN_VADDPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv8hf3_mask, "__builtin_ia32_subph128_mask", IX86_BUILTIN_VSUBPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv16hf3_mask, "__builtin_ia32_subph256_mask", IX86_BUILTIN_VSUBPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask, "__builtin_ia32_subph512_mask", IX86_BUILTIN_VSUBPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv8hf3_mask, "__builtin_ia32_mulph128_mask", IX86_BUILTIN_VMULPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv16hf3_mask, "__builtin_ia32_mulph256_mask", IX86_BUILTIN_VMULPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask, "__builtin_ia32_mulph512_mask", IX86_BUILTIN_VMULPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv8hf3_mask, "__builtin_ia32_divph128_mask", IX86_BUILTIN_VDIVPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv16hf3_mask, "__builtin_ia32_divph256_mask", IX86_BUILTIN_VDIVPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask, "__builtin_ia32_divph512_mask", IX86_BUILTIN_VDIVPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask, "__builtin_ia32_addsh_mask", IX86_BUILTIN_VADDSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask, "__builtin_ia32_subsh_mask", IX86_BUILTIN_VSUBSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask, "__builtin_ia32_mulsh_mask", IX86_BUILTIN_VMULSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask, "__builtin_ia32_divsh_mask", IX86_BUILTIN_VDIVSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv8hf3_mask, "__builtin_ia32_maxph128_mask", IX86_BUILTIN_VMAXPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv16hf3_mask, "__builtin_ia32_maxph256_mask", IX86_BUILTIN_VMAXPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask, "__builtin_ia32_maxph512_mask", IX86_BUILTIN_VMAXPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv8hf3_mask, "__builtin_ia32_minph128_mask", IX86_BUILTIN_VMINPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv16hf3_mask, "__builtin_ia32_minph256_mask", IX86_BUILTIN_VMINPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask, "__builtin_ia32_minph512_mask", IX86_BUILTIN_VMINPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask, "__builtin_ia32_maxsh_mask", IX86_BUILTIN_VMAXSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask, "__builtin_ia32_minsh_mask", IX86_BUILTIN_VMINSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_cmpv8hf3_mask, "__builtin_ia32_cmpph128_mask", IX86_BUILTIN_VCMPPH_V8HF_MASK, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_cmpv16hf3_mask, "__builtin_ia32_cmpph256_mask", IX86_BUILTIN_VCMPPH_V16HF_MASK, UNKNOWN, (int) UHI_FTYPE_V16HF_V16HF_INT_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask, "__builtin_ia32_cmpph512_mask", IX86_BUILTIN_VCMPPH_V32HF_MASK, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv8hf2_mask, "__builtin_ia32_sqrtph128_mask", IX86_BUILTIN_VSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv16hf2_mask, "__builtin_ia32_sqrtph256_mask", IX86_BUILTIN_VSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv8hf2_mask, "__builtin_ia32_rsqrtph128_mask", IX86_BUILTIN_VRSQRTPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv16hf2_mask, "__builtin_ia32_rsqrtph256_mask", IX86_BUILTIN_VRSQRTPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rsqrtv32hf2_mask, "__builtin_ia32_rsqrtph512_mask", IX86_BUILTIN_VRSQRTPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrsqrtv8hf2_mask, "__builtin_ia32_rsqrtsh_mask", IX86_BUILTIN_VRSQRTSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv8hf2_mask, "__builtin_ia32_rcpph128_mask", IX86_BUILTIN_VRCPPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv16hf2_mask, "__builtin_ia32_rcpph256_mask", IX86_BUILTIN_VRCPPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_UHI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rcpv32hf2_mask, "__builtin_ia32_rcpph512_mask", IX86_BUILTIN_VRCPPH_V32HF_MASK, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmrcpv8hf2_mask, "__builtin_ia32_rcpsh_mask", IX86_BUILTIN_VRCPSH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_scalefv8hf_mask, "__builtin_ia32_scalefph128_mask", IX86_BUILTIN_VSCALEFPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_scalefv16hf_mask, "__builtin_ia32_scalefph256_mask", IX86_BUILTIN_VSCALEFPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_V16HF_V16HF_UHI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv8hf_mask, "__builtin_ia32_reduceph128_mask", IX86_BUILTIN_VREDUCEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv16hf_mask, "__builtin_ia32_reduceph256_mask", IX86_BUILTIN_VREDUCEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_rndscalev8hf_mask, "__builtin_ia32_rndscaleph128_mask", IX86_BUILTIN_VRNDSCALEPH_V8HF_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HF_INT_V8HF_UQI)
+BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512vl_rndscalev16hf_mask, "__builtin_ia32_rndscaleph256_mask", IX86_BUILTIN_VRNDSCALEPH_V16HF_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HF_INT_V16HF_UHI)
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512dq_fpclassv16hf_mask, "__builtin_ia32_fpclassph256_mask", IX86_BUILTIN_FPCLASSPH256, UNKNOWN, (int) HI_FTYPE_V16HF_INT_UHI)
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512dq_fpclassv8hf_mask, "__builtin_ia32_fpclassph128_mask", IX86_BUILTIN_FPCLASSPH128, UNKNOWN, (int) QI_FTYPE_V8HF_INT_UQI)
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512dq_fpclassv32hf_mask, "__builtin_ia32_fpclassph512_mask", IX86_BUILTIN_FPCLASSPH512, UNKNOWN, (int) SI_FTYPE_V32HF_INT_USI)
@@ -3027,28 +3027,28 @@ BDESC (OPTION_MASK_ISA_AVX512DQ, 0, CODE_FOR_avx512dq_rangepv16sf_mask_round, "_
BDESC (OPTION_MASK_ISA_AVX512DQ, 0, CODE_FOR_avx512dq_rangepv8df_mask_round, "__builtin_ia32_rangepd512_mask", IX86_BUILTIN_RANGEPD512, UNKNOWN, (int) V8DF_FTYPE_V8DF_V8DF_INT_V8DF_QI_INT)
/* AVX512FP16. */
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask_round, "__builtin_ia32_vaddph_v32hf_mask_round", IX86_BUILTIN_VADDPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask_round, "__builtin_ia32_vsubph_v32hf_mask_round", IX86_BUILTIN_VSUBPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask_round, "__builtin_ia32_vmulph_v32hf_mask_round", IX86_BUILTIN_VMULPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask_round, "__builtin_ia32_vdivph_v32hf_mask_round", IX86_BUILTIN_VDIVPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask_round, "__builtin_ia32_vaddsh_v8hf_mask_round", IX86_BUILTIN_VADDSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask_round, "__builtin_ia32_vsubsh_v8hf_mask_round", IX86_BUILTIN_VSUBSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask_round, "__builtin_ia32_vmulsh_v8hf_mask_round", IX86_BUILTIN_VMULSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask_round, "__builtin_ia32_vdivsh_v8hf_mask_round", IX86_BUILTIN_VDIVSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask_round, "__builtin_ia32_vmaxph_v32hf_mask_round", IX86_BUILTIN_VMAXPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask_round, "__builtin_ia32_vminph_v32hf_mask_round", IX86_BUILTIN_VMINPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask_round, "__builtin_ia32_vmaxsh_v8hf_mask_round", IX86_BUILTIN_VMAXSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask_round, "__builtin_ia32_vminsh_v8hf_mask_round", IX86_BUILTIN_VMINSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask_round, "__builtin_ia32_vcmpph_v32hf_mask_round", IX86_BUILTIN_VCMPPH_V32HF_MASK_ROUND, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmcmpv8hf3_mask_round, "__builtin_ia32_vcmpsh_v8hf_mask_round", IX86_BUILTIN_VCMPSH_V8HF_MASK_ROUND, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv32hf2_mask_round, "__builtin_ia32_vsqrtph_v32hf_mask_round", IX86_BUILTIN_VSQRTPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsqrtv8hf2_mask_round, "__builtin_ia32_vsqrtsh_v8hf_mask_round", IX86_BUILTIN_VSQRTSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_scalefv32hf_mask_round, "__builtin_ia32_vscalefph_v32hf_mask_round", IX86_BUILTIN_VSCALEFPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmscalefv8hf_mask_round, "__builtin_ia32_vscalefsh_v8hf_mask_round", IX86_BUILTIN_VSCALEFSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv32hf_mask_round, "__builtin_ia32_vreduceph_v32hf_mask_round", IX86_BUILTIN_VREDUCEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducesv8hf_mask_round, "__builtin_ia32_vreducesh_v8hf_mask_round", IX86_BUILTIN_VREDUCESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_rndscalev32hf_mask_round, "__builtin_ia32_vrndscaleph_v32hf_mask_round", IX86_BUILTIN_VRNDSCALEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
-BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_rndscalev8hf_mask_round, "__builtin_ia32_vrndscalesh_v8hf_mask_round", IX86_BUILTIN_VRNDSCALESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_addv32hf3_mask_round, "__builtin_ia32_addph512_mask_round", IX86_BUILTIN_VADDPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_subv32hf3_mask_round, "__builtin_ia32_subph512_mask_round", IX86_BUILTIN_VSUBPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_mulv32hf3_mask_round, "__builtin_ia32_mulph512_mask_round", IX86_BUILTIN_VMULPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_divv32hf3_mask_round, "__builtin_ia32_divph512_mask_round", IX86_BUILTIN_VDIVPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmaddv8hf3_mask_round, "__builtin_ia32_addsh_mask_round", IX86_BUILTIN_VADDSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsubv8hf3_mask_round, "__builtin_ia32_subsh_mask_round", IX86_BUILTIN_VSUBSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmmulv8hf3_mask_round, "__builtin_ia32_mulsh_mask_round", IX86_BUILTIN_VMULSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmdivv8hf3_mask_round, "__builtin_ia32_divsh_mask_round", IX86_BUILTIN_VDIVSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_smaxv32hf3_mask_round, "__builtin_ia32_maxph512_mask_round", IX86_BUILTIN_VMAXPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_sminv32hf3_mask_round, "__builtin_ia32_minph512_mask_round", IX86_BUILTIN_VMINPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsmaxv8hf3_mask_round, "__builtin_ia32_maxsh_mask_round", IX86_BUILTIN_VMAXSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsminv8hf3_mask_round, "__builtin_ia32_minsh_mask_round", IX86_BUILTIN_VMINSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_cmpv32hf3_mask_round, "__builtin_ia32_cmpph512_mask_round", IX86_BUILTIN_VCMPPH_V32HF_MASK_ROUND, UNKNOWN, (int) USI_FTYPE_V32HF_V32HF_INT_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmcmpv8hf3_mask_round, "__builtin_ia32_cmpsh_mask_round", IX86_BUILTIN_VCMPSH_V8HF_MASK_ROUND, UNKNOWN, (int) UQI_FTYPE_V8HF_V8HF_INT_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_sqrtv32hf2_mask_round, "__builtin_ia32_sqrtph512_mask_round", IX86_BUILTIN_VSQRTPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vmsqrtv8hf2_mask_round, "__builtin_ia32_sqrtsh_mask_round", IX86_BUILTIN_VSQRTSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_scalefv32hf_mask_round, "__builtin_ia32_scalefph512_mask_round", IX86_BUILTIN_VSCALEFPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vmscalefv8hf_mask_round, "__builtin_ia32_scalefsh_mask_round", IX86_BUILTIN_VSCALEFSH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducepv32hf_mask_round, "__builtin_ia32_reduceph512_mask_round", IX86_BUILTIN_VREDUCEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_reducesv8hf_mask_round, "__builtin_ia32_reducesh_mask_round", IX86_BUILTIN_VREDUCESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_rndscalev32hf_mask_round, "__builtin_ia32_rndscaleph512_mask_round", IX86_BUILTIN_VRNDSCALEPH_V32HF_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
+BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_rndscalev8hf_mask_round, "__builtin_ia32_rndscalesh_mask_round", IX86_BUILTIN_VRNDSCALESH_V8HF_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_getexpv32hf_mask_round, "__builtin_ia32_getexpph512_mask", IX86_BUILTIN_GETEXPPH512, UNKNOWN, (int) V32HF_FTYPE_V32HF_V32HF_USI_INT)
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_sgetexpv8hf_mask_round, "__builtin_ia32_getexpsh_mask_round", IX86_BUILTIN_GETEXPSH_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_V8HF_UQI_INT)
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_getmantv32hf_mask_round, "__builtin_ia32_getmantph512_mask", IX86_BUILTIN_GETMANTPH512, UNKNOWN, (int) V32HF_FTYPE_V32HF_INT_V32HF_USI_INT)
@@ -686,33 +686,33 @@
#define __builtin_ia32_vpshld_v2di_mask(A, B, C, D, E) __builtin_ia32_vpshld_v2di_mask(A, B, 1, D, E)
/* avx512fp16intrin.h */
-#define __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vcmpph_v32hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v32hf_mask(A, B, 1, D)
-#define __builtin_ia32_vcmpph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpph_v32hf_mask_round(A, B, 1, D, 8)
-#define __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, 1, D, 8)
-#define __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, D) __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, 8)
-#define __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, E) __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, 8)
-#define __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vreduceph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vreduceph_v32hf_mask_round(A, 123, C, D, 8)
-#define __builtin_ia32_vreduceph_v8hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v8hf_mask(A, 123, C, D)
-#define __builtin_ia32_vreduceph_v16hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v16hf_mask(A, 123, C, D)
-#define __builtin_ia32_vreducesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vreducesh_v8hf_mask_round(A, B, 123, D, E, 8)
-#define __builtin_ia32_vrndscaleph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vrndscaleph_v32hf_mask_round(A, 123, C, D, 8)
-#define __builtin_ia32_vrndscaleph_v8hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v8hf_mask(A, 123, C, D)
-#define __builtin_ia32_vrndscaleph_v16hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v16hf_mask(A, 123, C, D)
-#define __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, 123, D, E, 8)
+#define __builtin_ia32_addph512_mask_round(A, B, C, D, E) __builtin_ia32_addph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subph512_mask_round(A, B, C, D, E) __builtin_ia32_subph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_mulph512_mask_round(A, B, C, D, E) __builtin_ia32_mulph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_divph512_mask_round(A, B, C, D, E) __builtin_ia32_divph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_addsh_mask_round(A, B, C, D, E) __builtin_ia32_addsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subsh_mask_round(A, B, C, D, E) __builtin_ia32_subsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_mulsh_mask_round(A, B, C, D, E) __builtin_ia32_mulsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_divsh_mask_round(A, B, C, D, E) __builtin_ia32_divsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_maxph512_mask_round(A, B, C, D, E) __builtin_ia32_maxph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_minph512_mask_round(A, B, C, D, E) __builtin_ia32_minph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_maxsh_mask_round(A, B, C, D, E) __builtin_ia32_maxsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_minsh_mask_round(A, B, C, D, E) __builtin_ia32_minsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_cmpph512_mask(A, B, C, D) __builtin_ia32_cmpph512_mask(A, B, 1, D)
+#define __builtin_ia32_cmpph512_mask_round(A, B, C, D, E) __builtin_ia32_cmpph512_mask_round(A, B, 1, D, 8)
+#define __builtin_ia32_cmpsh_mask_round(A, B, C, D, E) __builtin_ia32_cmpsh_mask_round(A, B, 1, D, 8)
+#define __builtin_ia32_sqrtph512_mask_round(C, A, B, D) __builtin_ia32_sqrtph512_mask_round(C, A, B, 8)
+#define __builtin_ia32_sqrtsh_mask_round(D, C, A, B, E) __builtin_ia32_sqrtsh_mask_round(D, C, A, B, 8)
+#define __builtin_ia32_scalefph512_mask_round(A, B, C, D, E) __builtin_ia32_scalefph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_scalefsh_mask_round(A, B, C, D, E) __builtin_ia32_scalefsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_reduceph512_mask_round(A, B, C, D, E) __builtin_ia32_reduceph512_mask_round(A, 123, C, D, 8)
+#define __builtin_ia32_reduceph128_mask(A, B, C, D) __builtin_ia32_reduceph128_mask(A, 123, C, D)
+#define __builtin_ia32_reduceph256_mask(A, B, C, D) __builtin_ia32_reduceph256_mask(A, 123, C, D)
+#define __builtin_ia32_reducesh_mask_round(A, B, C, D, E, F) __builtin_ia32_reducesh_mask_round(A, B, 123, D, E, 8)
+#define __builtin_ia32_rndscaleph512_mask_round(A, B, C, D, E) __builtin_ia32_rndscaleph512_mask_round(A, 123, C, D, 8)
+#define __builtin_ia32_rndscaleph128_mask(A, B, C, D) __builtin_ia32_rndscaleph128_mask(A, 123, C, D)
+#define __builtin_ia32_rndscaleph256_mask(A, B, C, D) __builtin_ia32_rndscaleph256_mask(A, 123, C, D)
+#define __builtin_ia32_rndscalesh_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesh_mask_round(A, B, 123, D, E, 8)
#define __builtin_ia32_fpclassph512_mask(A, D, C) __builtin_ia32_fpclassph512_mask(A, 1, C)
#define __builtin_ia32_fpclasssh_mask(A, D, U) __builtin_ia32_fpclasssh_mask(A, 1, U)
#define __builtin_ia32_getexpph512_mask(A, B, C, D) __builtin_ia32_getexpph512_mask(A, B, C, 8)
@@ -721,8 +721,8 @@
#define __builtin_ia32_getmantsh_mask_round(A, B, C, W, U, D) __builtin_ia32_getmantsh_mask_round(A, B, 1, W, U, 4)
/* avx512fp16vlintrin.h */
-#define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
-#define __builtin_ia32_vcmpph_v16hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v16hf_mask(A, B, 1, D)
+#define __builtin_ia32_cmpph128_mask(A, B, C, D) __builtin_ia32_cmpph128_mask(A, B, 1, D)
+#define __builtin_ia32_cmpph256_mask(A, B, C, D) __builtin_ia32_cmpph256_mask(A, B, 1, D)
#define __builtin_ia32_fpclassph256_mask(A, D, C) __builtin_ia32_fpclassph256_mask(A, 1, C)
#define __builtin_ia32_fpclassph128_mask(A, D, C) __builtin_ia32_fpclassph128_mask(A, 1, C)
#define __builtin_ia32_getmantph256_mask(A, E, C, D) __builtin_ia32_getmantph256_mask(A, 1, C, D)
@@ -703,33 +703,33 @@
#define __builtin_ia32_vpshld_v2di_mask(A, B, C, D, E) __builtin_ia32_vpshld_v2di_mask(A, B, 1, D, E)
/* avx512fp16intrin.h */
-#define __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vcmpph_v32hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v32hf_mask(A, B, 1, D)
-#define __builtin_ia32_vcmpph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpph_v32hf_mask_round(A, B, 1, D, 8)
-#define __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, 1, D, 8)
-#define __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, D) __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, 8)
-#define __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, E) __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, 8)
-#define __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vreduceph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vreduceph_v32hf_mask_round(A, 123, C, D, 8)
-#define __builtin_ia32_vreduceph_v8hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v8hf_mask(A, 123, C, D)
-#define __builtin_ia32_vreduceph_v16hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v16hf_mask(A, 123, C, D)
-#define __builtin_ia32_vreducesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vreducesh_v8hf_mask_round(A, B, 123, D, E, 8)
-#define __builtin_ia32_vrndscaleph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vrndscaleph_v32hf_mask_round(A, 123, C, D, 8)
-#define __builtin_ia32_vrndscaleph_v8hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v8hf_mask(A, 123, C, D)
-#define __builtin_ia32_vrndscaleph_v16hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v16hf_mask(A, 123, C, D)
-#define __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, 123, D, E, 8)
+#define __builtin_ia32_addph512_mask_round(A, B, C, D, E) __builtin_ia32_addph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subph512_mask_round(A, B, C, D, E) __builtin_ia32_subph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_mulph512_mask_round(A, B, C, D, E) __builtin_ia32_mulph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_divph512_mask_round(A, B, C, D, E) __builtin_ia32_divph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_addsh_mask_round(A, B, C, D, E) __builtin_ia32_addsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subsh_mask_round(A, B, C, D, E) __builtin_ia32_subsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_mulsh_mask_round(A, B, C, D, E) __builtin_ia32_mulsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_divsh_mask_round(A, B, C, D, E) __builtin_ia32_divsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_maxph512_mask_round(A, B, C, D, E) __builtin_ia32_maxph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_minph512_mask_round(A, B, C, D, E) __builtin_ia32_minph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_maxsh_mask_round(A, B, C, D, E) __builtin_ia32_maxsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_minsh_mask_round(A, B, C, D, E) __builtin_ia32_minsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_cmpph512_mask(A, B, C, D) __builtin_ia32_cmpph512_mask(A, B, 1, D)
+#define __builtin_ia32_cmpph512_mask_round(A, B, C, D, E) __builtin_ia32_cmpph512_mask_round(A, B, 1, D, 8)
+#define __builtin_ia32_cmpsh_mask_round(A, B, C, D, E) __builtin_ia32_cmpsh_mask_round(A, B, 1, D, 8)
+#define __builtin_ia32_sqrtph512_mask_round(C, A, B, D) __builtin_ia32_sqrtph512_mask_round(C, A, B, 8)
+#define __builtin_ia32_sqrtsh_mask_round(D, C, A, B, E) __builtin_ia32_sqrtsh_mask_round(D, C, A, B, 8)
+#define __builtin_ia32_scalefph512_mask_round(A, B, C, D, E) __builtin_ia32_scalefph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_scalefsh_mask_round(A, B, C, D, E) __builtin_ia32_scalefsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_reduceph512_mask_round(A, B, C, D, E) __builtin_ia32_reduceph512_mask_round(A, 123, C, D, 8)
+#define __builtin_ia32_reduceph128_mask(A, B, C, D) __builtin_ia32_reduceph128_mask(A, 123, C, D)
+#define __builtin_ia32_reduceph256_mask(A, B, C, D) __builtin_ia32_reduceph256_mask(A, 123, C, D)
+#define __builtin_ia32_reducesh_mask_round(A, B, C, D, E, F) __builtin_ia32_reducesh_mask_round(A, B, 123, D, E, 8)
+#define __builtin_ia32_rndscaleph512_mask_round(A, B, C, D, E) __builtin_ia32_rndscaleph512_mask_round(A, 123, C, D, 8)
+#define __builtin_ia32_rndscaleph128_mask(A, B, C, D) __builtin_ia32_rndscaleph128_mask(A, 123, C, D)
+#define __builtin_ia32_rndscaleph256_mask(A, B, C, D) __builtin_ia32_rndscaleph256_mask(A, 123, C, D)
+#define __builtin_ia32_rndscalesh_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesh_mask_round(A, B, 123, D, E, 8)
#define __builtin_ia32_fpclassph512_mask(A, D, C) __builtin_ia32_fpclassph512_mask(A, 1, C)
#define __builtin_ia32_fpclasssh_mask(A, D, U) __builtin_ia32_fpclasssh_mask(A, 1, U)
#define __builtin_ia32_getexpph512_mask(A, B, C, D) __builtin_ia32_getexpph512_mask(A, B, C, 8)
@@ -738,8 +738,8 @@
#define __builtin_ia32_getmantsh_mask_round(A, B, C, W, U, D) __builtin_ia32_getmantsh_mask_round(A, B, 1, W, U, 4)
/* avx512fp16vlintrin.h */
-#define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
-#define __builtin_ia32_vcmpph_v16hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v16hf_mask(A, B, 1, D)
+#define __builtin_ia32_cmpph128_mask(A, B, C, D) __builtin_ia32_cmpph128_mask(A, B, 1, D)
+#define __builtin_ia32_cmpph256_mask(A, B, C, D) __builtin_ia32_cmpph256_mask(A, B, 1, D)
#define __builtin_ia32_fpclassph256_mask(A, D, C) __builtin_ia32_fpclassph256_mask(A, 1, C)
#define __builtin_ia32_fpclassph128_mask(A, D, C) __builtin_ia32_fpclassph128_mask(A, 1, C)
#define __builtin_ia32_getmantph256_mask(A, E, C, D) __builtin_ia32_getmantph256_mask(A, 1, C, D)
@@ -704,33 +704,33 @@
#define __builtin_ia32_vpshld_v2di_mask(A, B, C, D, E) __builtin_ia32_vpshld_v2di_mask(A, B, 1, D, E)
/* avx512fp16intrin.h */
-#define __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vaddsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vsubsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmulsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vdivsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vminph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vmaxsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vminsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vcmpph_v32hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v32hf_mask(A, B, 1, D)
-#define __builtin_ia32_vcmpph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpph_v32hf_mask_round(A, B, 1, D, 8)
-#define __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vcmpsh_v8hf_mask_round(A, B, 1, D, 8)
-#define __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, D) __builtin_ia32_vsqrtph_v32hf_mask_round(C, A, B, 8)
-#define __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, E) __builtin_ia32_vsqrtsh_v8hf_mask_round(D, C, A, B, 8)
-#define __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefph_v32hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, E) __builtin_ia32_vscalefsh_v8hf_mask_round(A, B, C, D, 8)
-#define __builtin_ia32_vreduceph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vreduceph_v32hf_mask_round(A, 123, C, D, 8)
-#define __builtin_ia32_vreduceph_v8hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v8hf_mask(A, 123, C, D)
-#define __builtin_ia32_vreduceph_v16hf_mask(A, B, C, D) __builtin_ia32_vreduceph_v16hf_mask(A, 123, C, D)
-#define __builtin_ia32_vreducesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vreducesh_v8hf_mask_round(A, B, 123, D, E, 8)
-#define __builtin_ia32_vrndscaleph_v32hf_mask_round(A, B, C, D, E) __builtin_ia32_vrndscaleph_v32hf_mask_round(A, 123, C, D, 8)
-#define __builtin_ia32_vrndscaleph_v8hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v8hf_mask(A, 123, C, D)
-#define __builtin_ia32_vrndscaleph_v16hf_mask(A, B, C, D) __builtin_ia32_vrndscaleph_v16hf_mask(A, 123, C, D)
-#define __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, C, D, E, F) __builtin_ia32_vrndscalesh_v8hf_mask_round(A, B, 123, D, E, 8)
+#define __builtin_ia32_addph512_mask_round(A, B, C, D, E) __builtin_ia32_addph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subph512_mask_round(A, B, C, D, E) __builtin_ia32_subph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_mulph512_mask_round(A, B, C, D, E) __builtin_ia32_mulph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_divph512_mask_round(A, B, C, D, E) __builtin_ia32_divph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_addsh_mask_round(A, B, C, D, E) __builtin_ia32_addsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_subsh_mask_round(A, B, C, D, E) __builtin_ia32_subsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_mulsh_mask_round(A, B, C, D, E) __builtin_ia32_mulsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_divsh_mask_round(A, B, C, D, E) __builtin_ia32_divsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_maxph512_mask_round(A, B, C, D, E) __builtin_ia32_maxph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_minph512_mask_round(A, B, C, D, E) __builtin_ia32_minph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_maxsh_mask_round(A, B, C, D, E) __builtin_ia32_maxsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_minsh_mask_round(A, B, C, D, E) __builtin_ia32_minsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_cmpph512_mask(A, B, C, D) __builtin_ia32_cmpph512_mask(A, B, 1, D)
+#define __builtin_ia32_cmpph512_mask_round(A, B, C, D, E) __builtin_ia32_cmpph512_mask_round(A, B, 1, D, 8)
+#define __builtin_ia32_cmpsh_mask_round(A, B, C, D, E) __builtin_ia32_cmpsh_mask_round(A, B, 1, D, 8)
+#define __builtin_ia32_sqrtph512_mask_round(C, A, B, D) __builtin_ia32_sqrtph512_mask_round(C, A, B, 8)
+#define __builtin_ia32_sqrtsh_mask_round(D, C, A, B, E) __builtin_ia32_sqrtsh_mask_round(D, C, A, B, 8)
+#define __builtin_ia32_scalefph512_mask_round(A, B, C, D, E) __builtin_ia32_scalefph512_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_scalefsh_mask_round(A, B, C, D, E) __builtin_ia32_scalefsh_mask_round(A, B, C, D, 8)
+#define __builtin_ia32_reduceph512_mask_round(A, B, C, D, E) __builtin_ia32_reduceph512_mask_round(A, 123, C, D, 8)
+#define __builtin_ia32_reduceph128_mask(A, B, C, D) __builtin_ia32_reduceph128_mask(A, 123, C, D)
+#define __builtin_ia32_reduceph256_mask(A, B, C, D) __builtin_ia32_reduceph256_mask(A, 123, C, D)
+#define __builtin_ia32_reducesh_mask_round(A, B, C, D, E, F) __builtin_ia32_reducesh_mask_round(A, B, 123, D, E, 8)
+#define __builtin_ia32_rndscaleph512_mask_round(A, B, C, D, E) __builtin_ia32_rndscaleph512_mask_round(A, 123, C, D, 8)
+#define __builtin_ia32_rndscaleph128_mask(A, B, C, D) __builtin_ia32_rndscaleph128_mask(A, 123, C, D)
+#define __builtin_ia32_rndscaleph256_mask(A, B, C, D) __builtin_ia32_rndscaleph256_mask(A, 123, C, D)
+#define __builtin_ia32_rndscalesh_mask_round(A, B, C, D, E, F) __builtin_ia32_rndscalesh_mask_round(A, B, 123, D, E, 8)
#define __builtin_ia32_fpclassph512_mask(A, D, C) __builtin_ia32_fpclassph512_mask(A, 1, C)
#define __builtin_ia32_fpclasssh_mask(A, D, U) __builtin_ia32_fpclasssh_mask(A, 1, U)
#define __builtin_ia32_getexpph512_mask(A, B, C, D) __builtin_ia32_getexpph512_mask(A, B, C, 8)
@@ -739,8 +739,8 @@
#define __builtin_ia32_getmantsh_mask_round(A, B, C, W, U, D) __builtin_ia32_getmantsh_mask_round(A, B, 1, W, U, 4)
/* avx512fp16vlintrin.h */
-#define __builtin_ia32_vcmpph_v8hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v8hf_mask(A, B, 1, D)
-#define __builtin_ia32_vcmpph_v16hf_mask(A, B, C, D) __builtin_ia32_vcmpph_v16hf_mask(A, B, 1, D)
+#define __builtin_ia32_cmpph128_mask(A, B, C, D) __builtin_ia32_cmpph128_mask(A, B, 1, D)
+#define __builtin_ia32_cmpph256_mask(A, B, C, D) __builtin_ia32_cmpph256_mask(A, B, 1, D)
#define __builtin_ia32_fpclassph256_mask(A, D, C) __builtin_ia32_fpclassph256_mask(A, 1, C)
#define __builtin_ia32_fpclassph128_mask(A, D, C) __builtin_ia32_fpclassph128_mask(A, 1, C)
#define __builtin_ia32_getmantph256_mask(A, E, C, D) __builtin_ia32_getmantph256_mask(A, 1, C, D)