AArch64 Remove shuffle pattern for rounding variant.
Commit Message
Hi All,
This removed the patterns to optimize the rounding shift and narrow.
The optimization is valid only for the truncating rounding shift and narrow,
for the rounding shift and narrow we need a different pattern that I will submit
separately.
This wasn't noticed before as the benchmarks did not run conformance as part of
the run, which we now do and this now passes again.
Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
Ok for master?
Thanks,
Tamar
gcc/ChangeLog:
* config/aarch64/aarch64-simd.md (*aarch64_topbits_shuffle<mode>_le
,*aarch64_topbits_shuffle<mode>_be): Remove.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/shrn-combine-8.c: Update.
* gcc.target/aarch64/shrn-combine-9.c: Update.
--- inline copy of patch --
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index bff76e4b6e97db2613ab0ce1d721bf1828f0671b..c71658e2bf52b26bf9fc9fa702dd5446447f4d43 100644
--
Comments
> -----Original Message-----
> From: Tamar Christina <Tamar.Christina@arm.com>
> Sent: Wednesday, November 10, 2021 12:09 PM
> To: gcc-patches@gcc.gnu.org
> Cc: nd <nd@arm.com>; Richard Earnshaw <Richard.Earnshaw@arm.com>;
> Marcus Shawcroft <Marcus.Shawcroft@arm.com>; Kyrylo Tkachov
> <Kyrylo.Tkachov@arm.com>; Richard Sandiford
> <Richard.Sandiford@arm.com>
> Subject: [PATCH]AArch64 Remove shuffle pattern for rounding variant.
>
> Hi All,
>
> This removed the patterns to optimize the rounding shift and narrow.
> The optimization is valid only for the truncating rounding shift and narrow,
> for the rounding shift and narrow we need a different pattern that I will
> submit
> separately.
>
> This wasn't noticed before as the benchmarks did not run conformance as
> part of
> the run, which we now do and this now passes again.
>
> Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
>
> Ok for master?
Ok.
Thanks,
Kyrill
>
> Thanks,
> Tamar
>
> gcc/ChangeLog:
>
> * config/aarch64/aarch64-simd.md
> (*aarch64_topbits_shuffle<mode>_le
> ,*aarch64_topbits_shuffle<mode>_be): Remove.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/aarch64/shrn-combine-8.c: Update.
> * gcc.target/aarch64/shrn-combine-9.c: Update.
>
> --- inline copy of patch --
> diff --git a/gcc/config/aarch64/aarch64-simd.md
> b/gcc/config/aarch64/aarch64-simd.md
> index
> bff76e4b6e97db2613ab0ce1d721bf1828f0671b..c71658e2bf52b26bf9fc9fa70
> 2dd5446447f4d43 100644
> --- a/gcc/config/aarch64/aarch64-simd.md
> +++ b/gcc/config/aarch64/aarch64-simd.md
> @@ -1887,22 +1887,6 @@ (define_insn
> "*aarch64_<srn_op>topbits_shuffle<mode>_le"
> [(set_attr "type" "neon_permute<q>")]
> )
>
> -(define_insn "*aarch64_topbits_shuffle<mode>_le"
> - [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
> - (vec_concat:<VNARROWQ2>
> - (unspec:<VNARROWQ> [
> - (match_operand:VQN 1 "register_operand" "w")
> - (match_operand:VQN 2
> "aarch64_simd_shift_imm_vec_exact_top")
> - ] UNSPEC_RSHRN)
> - (unspec:<VNARROWQ> [
> - (match_operand:VQN 3 "register_operand" "w")
> - (match_dup 2)
> - ] UNSPEC_RSHRN)))]
> - "TARGET_SIMD && !BYTES_BIG_ENDIAN"
> - "uzp2\\t%0.<V2ntype>, %1.<V2ntype>, %3.<V2ntype>"
> - [(set_attr "type" "neon_permute<q>")]
> -)
> -
> (define_insn "*aarch64_<srn_op>topbits_shuffle<mode>_be"
> [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
> (vec_concat:<VNARROWQ2>
> @@ -1917,22 +1901,6 @@ (define_insn
> "*aarch64_<srn_op>topbits_shuffle<mode>_be"
> [(set_attr "type" "neon_permute<q>")]
> )
>
> -(define_insn "*aarch64_topbits_shuffle<mode>_be"
> - [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
> - (vec_concat:<VNARROWQ2>
> - (unspec:<VNARROWQ> [
> - (match_operand:VQN 3 "register_operand" "w")
> - (match_operand:VQN 2
> "aarch64_simd_shift_imm_vec_exact_top")
> - ] UNSPEC_RSHRN)
> - (unspec:<VNARROWQ> [
> - (match_operand:VQN 1 "register_operand" "w")
> - (match_dup 2)
> - ] UNSPEC_RSHRN)))]
> - "TARGET_SIMD && BYTES_BIG_ENDIAN"
> - "uzp2\\t%0.<V2ntype>, %1.<V2ntype>, %3.<V2ntype>"
> - [(set_attr "type" "neon_permute<q>")]
> -)
> -
> (define_expand "aarch64_shrn<mode>"
> [(set (match_operand:<VNARROWQ> 0 "register_operand")
> (truncate:<VNARROWQ>
> diff --git a/gcc/testsuite/gcc.target/aarch64/shrn-combine-8.c
> b/gcc/testsuite/gcc.target/aarch64/shrn-combine-8.c
> index
> 6a47f3cdaee399e603c57a1c6a0c09c6cfd21abb..c93c179632156c07f05e6067e
> 63804db35cc436b 100644
> --- a/gcc/testsuite/gcc.target/aarch64/shrn-combine-8.c
> +++ b/gcc/testsuite/gcc.target/aarch64/shrn-combine-8.c
> @@ -6,7 +6,7 @@
>
> uint8x16_t foo (uint16x8_t a, uint16x8_t b)
> {
> - return vrshrn_high_n_u16 (vrshrn_n_u16 (a, 8), b, 8);
> + return vshrn_high_n_u16 (vshrn_n_u16 (a, 8), b, 8);
> }
>
> /* { dg-final { scan-assembler-times {\tuzp2\t} 1 } } */
> diff --git a/gcc/testsuite/gcc.target/aarch64/shrn-combine-9.c
> b/gcc/testsuite/gcc.target/aarch64/shrn-combine-9.c
> index
> 929a55c5c338844e6a5c5ad249af482286ab9c61..bdb3c13e5a2f89d62b6a24c2
> abe3535656399cac 100644
> --- a/gcc/testsuite/gcc.target/aarch64/shrn-combine-9.c
> +++ b/gcc/testsuite/gcc.target/aarch64/shrn-combine-9.c
> @@ -6,7 +6,7 @@
>
> uint16x8_t foo (uint32x4_t a, uint32x4_t b)
> {
> - return vrshrn_high_n_u32 (vrshrn_n_u32 (a, 16), b, 16);
> + return vshrn_high_n_u32 (vshrn_n_u32 (a, 16), b, 16);
> }
>
> /* { dg-final { scan-assembler-times {\tuzp2\t} 1 } } */
>
>
> --
@@ -1887,22 +1887,6 @@ (define_insn "*aarch64_<srn_op>topbits_shuffle<mode>_le"
[(set_attr "type" "neon_permute<q>")]
)
-(define_insn "*aarch64_topbits_shuffle<mode>_le"
- [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
- (vec_concat:<VNARROWQ2>
- (unspec:<VNARROWQ> [
- (match_operand:VQN 1 "register_operand" "w")
- (match_operand:VQN 2 "aarch64_simd_shift_imm_vec_exact_top")
- ] UNSPEC_RSHRN)
- (unspec:<VNARROWQ> [
- (match_operand:VQN 3 "register_operand" "w")
- (match_dup 2)
- ] UNSPEC_RSHRN)))]
- "TARGET_SIMD && !BYTES_BIG_ENDIAN"
- "uzp2\\t%0.<V2ntype>, %1.<V2ntype>, %3.<V2ntype>"
- [(set_attr "type" "neon_permute<q>")]
-)
-
(define_insn "*aarch64_<srn_op>topbits_shuffle<mode>_be"
[(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
(vec_concat:<VNARROWQ2>
@@ -1917,22 +1901,6 @@ (define_insn "*aarch64_<srn_op>topbits_shuffle<mode>_be"
[(set_attr "type" "neon_permute<q>")]
)
-(define_insn "*aarch64_topbits_shuffle<mode>_be"
- [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
- (vec_concat:<VNARROWQ2>
- (unspec:<VNARROWQ> [
- (match_operand:VQN 3 "register_operand" "w")
- (match_operand:VQN 2 "aarch64_simd_shift_imm_vec_exact_top")
- ] UNSPEC_RSHRN)
- (unspec:<VNARROWQ> [
- (match_operand:VQN 1 "register_operand" "w")
- (match_dup 2)
- ] UNSPEC_RSHRN)))]
- "TARGET_SIMD && BYTES_BIG_ENDIAN"
- "uzp2\\t%0.<V2ntype>, %1.<V2ntype>, %3.<V2ntype>"
- [(set_attr "type" "neon_permute<q>")]
-)
-
(define_expand "aarch64_shrn<mode>"
[(set (match_operand:<VNARROWQ> 0 "register_operand")
(truncate:<VNARROWQ>
@@ -6,7 +6,7 @@
uint8x16_t foo (uint16x8_t a, uint16x8_t b)
{
- return vrshrn_high_n_u16 (vrshrn_n_u16 (a, 8), b, 8);
+ return vshrn_high_n_u16 (vshrn_n_u16 (a, 8), b, 8);
}
/* { dg-final { scan-assembler-times {\tuzp2\t} 1 } } */
@@ -6,7 +6,7 @@
uint16x8_t foo (uint32x4_t a, uint32x4_t b)
{
- return vrshrn_high_n_u32 (vrshrn_n_u32 (a, 16), b, 16);
+ return vshrn_high_n_u32 (vshrn_n_u32 (a, 16), b, 16);
}
/* { dg-final { scan-assembler-times {\tuzp2\t} 1 } } */