[FFmpeg-devel] [PATCH 1/2] libavutil/cpu: Add AV_CPU_FLAG_SLOW_GATHER.

[Lynne]

21 Dec 2021, 20:56 by alankelly-at-google.com at ffmpeg.org:

> This flag is set on Haswell and earlier and all AMD cpus.
> ---
>  Checks for family for Haswell. All checks are done where AVX2 flag is
>  set as this is clearer.
>  libavutil/cpu.h     |  1 +
>  libavutil/x86/cpu.c | 15 ++++++++++++++-
>  2 files changed, 15 insertions(+), 1 deletion(-)
>
> diff --git a/libavutil/cpu.h b/libavutil/cpu.h
> index ae443eccad..ce9bf14bf7 100644
> --- a/libavutil/cpu.h
> +++ b/libavutil/cpu.h
> @@ -54,6 +54,7 @@
>  #define AV_CPU_FLAG_BMI1        0x20000 ///< Bit Manipulation Instruction Set 1
>  #define AV_CPU_FLAG_BMI2        0x40000 ///< Bit Manipulation Instruction Set 2
>  #define AV_CPU_FLAG_AVX512     0x100000 ///< AVX-512 functions: requires OS support even if YMM/ZMM registers aren't used
> +#define AV_CPU_FLAG_SLOW_GATHER  0x2000000 ///< CPU has slow gathers.
>  
>  #define AV_CPU_FLAG_ALTIVEC      0x0001 ///< standard
>  #define AV_CPU_FLAG_VSX          0x0002 ///< ISA 2.06
> diff --git a/libavutil/x86/cpu.c b/libavutil/x86/cpu.c
> index bcd41a50a2..441b4695d5 100644
> --- a/libavutil/x86/cpu.c
> +++ b/libavutil/x86/cpu.c
> @@ -146,8 +146,21 @@ int ff_get_cpu_flags_x86(void)
>  if (max_std_level >= 7) {
>  cpuid(7, eax, ebx, ecx, edx);
>  #if HAVE_AVX2
> -        if ((rval & AV_CPU_FLAG_AVX) && (ebx & 0x00000020))
> +        if ((rval & AV_CPU_FLAG_AVX) && (ebx & 0x00000020)) {
>  rval |= AV_CPU_FLAG_AVX2;
> +            cpuid(1, eax, ebx, ecx, std_caps);
> +            family = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
> +            model  = ((eax >> 4) & 0xf) + ((eax >> 12) & 0xf0);
> +            /* Haswell has slow gather */
> +            if (!strncmp(vendor.c, "GenuineIntel", 12))
> +                if (family == 6 && model < 70)
> +                    rval |= AV_CPU_FLAG_SLOW_GATHER;
> +            /* Zen 3 and earlier have slow gather */
> +            if (!strncmp(vendor.c, "AuthenticAMD", 12))
> +                if (family <= 0x19)
> +                    rval |= AV_CPU_FLAG_SLOW_GATHER;
> +        }
> +
>  #if HAVE_AVX512 /* F, CD, BW, DQ, VL */
>  if ((xcr0_lo & 0xe0) == 0xe0) { /* OPMASK/ZMM state */
>  if ((rval & AV_CPU_FLAG_AVX2) && (ebx & 0xd0030000) == 0xd0030000)
> -- 
> 2.34.1.173.g76aa8bc2d0-goog
>

LGTM, thanks