[RFC] X86_64 Avx2 Detection

  From: Sihai Yao <sihai.ysh@alibaba-inc.com>

This patch sets bit_AVX2_Usable of __cpu_features.feature by checking
COMMON_CPUID_INDEX_7 for Haswell. Architecture related assembler file
can use this bit to determine calling path.

---
This version removed the unrelated cpu module branch code and FEATURE_INDEX_7,
which is unusefull for AVX

 ChangeLog                                  | 8 ++++++++
 sysdeps/x86_64/multiarch/ifunc-defines.sym | 1 +
 sysdeps/x86_64/multiarch/init-arch.c       | 3 +++
 sysdeps/x86_64/multiarch/init-arch.h       | 8 ++++++++
 4 files changed, 20 insertions(+)
  

On Mon, Apr 14, 2014 at 5:53 AM,  <ling.ma.program@gmail.com> wrote:
> From: Sihai Yao <sihai.ysh@alibaba-inc.com>
>
> This patch sets bit_AVX2_Usable of __cpu_features.feature by checking
> COMMON_CPUID_INDEX_7 for Haswell. Architecture related assembler file
> can use this bit to determine calling path.
>
> ---
> This version removed the unrelated cpu module branch code and FEATURE_INDEX_7,
> which is unusefull for AVX
>
>  ChangeLog                                  | 8 ++++++++
>  sysdeps/x86_64/multiarch/ifunc-defines.sym | 1 +
>  sysdeps/x86_64/multiarch/init-arch.c       | 3 +++
>  sysdeps/x86_64/multiarch/init-arch.h       | 8 ++++++++
>  4 files changed, 20 insertions(+)
>
> diff --git a/ChangeLog b/ChangeLog
> index fb0177d..ba8980c 100644
> --- a/ChangeLog
> +++ b/ChangeLog
> @@ -1,3 +1,11 @@
> +2014-04-04  Sihai Yao  <sihai.ysh@alibaba-inc.com>

Need a blank line here.

> +       * sysdeps/x86_64/multiarch/ifunc-defines.sym: Add COMMON_CPU_INDEX_7 and
> +       FEATURE_INDEX_7.
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^  FEATURE_INDEX_7 has been removed.

> +       * sysdeps/x86_64/multiarch/init-arch.c: Add AVX2 detection from cpu
> +       features word of COMMON_CPUID_INDEX_7.
> +       * sysdeps/x86_64/multiarch/init-arch.h: Add bit_AVX2_Usable and
> +       index_AVX2_Usable for future assembly code to determing calling path.
> +

It looks good to me, except for ChangeLog.

>  2014-04-10 Torvald Riegel  <triegel@redhat.com>
>
>         * benchtests/pthread_once-inputs: New file.
> diff --git a/sysdeps/x86_64/multiarch/ifunc-defines.sym b/sysdeps/x86_64/multiarch/ifunc-defines.sym
> index eb1538a..a410d88 100644
> --- a/sysdeps/x86_64/multiarch/ifunc-defines.sym
> +++ b/sysdeps/x86_64/multiarch/ifunc-defines.sym
> @@ -17,4 +17,5 @@ FEATURE_OFFSET                offsetof (struct cpu_features, feature)
>  FEATURE_SIZE           sizeof (unsigned int)
>
>  COMMON_CPUID_INDEX_1
> +COMMON_CPUID_INDEX_7
>  FEATURE_INDEX_1
> diff --git a/sysdeps/x86_64/multiarch/init-arch.c b/sysdeps/x86_64/multiarch/init-arch.c
> index db74d97..2a6dcb7 100644
> --- a/sysdeps/x86_64/multiarch/init-arch.c
> +++ b/sysdeps/x86_64/multiarch/init-arch.c
> @@ -167,6 +167,9 @@ __init_cpu_features (void)
>           /* Determine if AVX is usable.  */
>           if (CPUID_AVX)
>             __cpu_features.feature[index_AVX_Usable] |= bit_AVX_Usable;
> +         /* Determine if AVX2 is usable.  */
> +         if (CPUID_AVX2)
> +           __cpu_features.feature[index_AVX2_Usable] |= bit_AVX2_Usable;
>           /* Determine if FMA is usable.  */
>           if (CPUID_FMA)
>             __cpu_features.feature[index_FMA_Usable] |= bit_FMA_Usable;
> diff --git a/sysdeps/x86_64/multiarch/init-arch.h b/sysdeps/x86_64/multiarch/init-arch.h
> index 793707a..813b6de 100644
> --- a/sysdeps/x86_64/multiarch/init-arch.h
> +++ b/sysdeps/x86_64/multiarch/init-arch.h
> @@ -24,6 +24,7 @@
>  #define bit_FMA_Usable                 (1 << 7)
>  #define bit_FMA4_Usable                        (1 << 8)
>  #define bit_Slow_SSE4_2                        (1 << 9)
> +#define bit_AVX2_Usable                        (1 << 10)
>
>  /* CPUID Feature flags.  */
>
> @@ -40,6 +41,7 @@
>
>  /* COMMON_CPUID_INDEX_7.  */
>  #define bit_RTM                (1 << 11)
> +#define bit_AVX2       (1 << 5)
>
>  /* XCR0 Feature flags.  */
>  #define bit_XMM_state  (1 << 1)
> @@ -54,6 +56,7 @@
>  # define index_SSE4_1  COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
>  # define index_SSE4_2  COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
>  # define index_AVX     COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
> +# define index_AVX2    COMMON_CPUID_INDEX_7*CPUID_SIZE+CPUID_EBX_OFFSET
>
>  # define index_Fast_Rep_String         FEATURE_INDEX_1*FEATURE_SIZE
>  # define index_Fast_Copy_Backward      FEATURE_INDEX_1*FEATURE_SIZE
> @@ -64,6 +67,7 @@
>  # define index_FMA_Usable              FEATURE_INDEX_1*FEATURE_SIZE
>  # define index_FMA4_Usable             FEATURE_INDEX_1*FEATURE_SIZE
>  # define index_Slow_SSE4_2             FEATURE_INDEX_1*FEATURE_SIZE
> +# define index_AVX2_Usable             FEATURE_INDEX_1*FEATURE_SIZE
>
>  #else  /* __ASSEMBLER__ */
>
> @@ -145,6 +149,8 @@ extern const struct cpu_features *__get_cpu_features (void)
>    HAS_CPUID_FLAG (COMMON_CPUID_INDEX_80000001, ecx, bit_FMA4)
>  # define CPUID_RTM \
>    HAS_CPUID_FLAG (COMMON_CPUID_INDEX_7, ebx, bit_RTM)
> +# define CPUID_AVX2 \
> +  HAS_CPUID_FLAG (COMMON_CPUID_INDEX_7, ebx, bit_AVX2)
>
>  /* HAS_* evaluates to true if we may use the feature at runtime.  */
>  # define HAS_SSE2      HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, edx, bit_SSE2)
> @@ -153,6 +159,7 @@ extern const struct cpu_features *__get_cpu_features (void)
>  # define HAS_SSE4_1    HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, ecx, bit_SSE4_1)
>  # define HAS_SSE4_2    HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, ecx, bit_SSE4_2)
>  # define HAS_RTM       HAS_CPU_FEATURE (COMMON_CPUID_INDEX_7, ebx, bit_RTM)
> +# define HAS_AVX2      HAS_CPU_FEATURE (COMMON_CPUID_INDEX_7, ebx, bit_AVX2)
>
>  # define index_Fast_Rep_String         FEATURE_INDEX_1
>  # define index_Fast_Copy_Backward      FEATURE_INDEX_1
> @@ -163,6 +170,7 @@ extern const struct cpu_features *__get_cpu_features (void)
>  # define index_FMA_Usable              FEATURE_INDEX_1
>  # define index_FMA4_Usable             FEATURE_INDEX_1
>  # define index_Slow_SSE4_2             FEATURE_INDEX_1
> +# define index_AVX2_Usable             FEATURE_INDEX_1
>
>  # define HAS_ARCH_FEATURE(name) \
>    ((__get_cpu_features ()->feature[index_##name] & (bit_##name)) != 0)
> --
> 1.8.1.4
>