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

[Alan Kelly]

This flag is set on Haswell and earlier and all AMD cpus.
---
 Sets this flag on Zen 3 and earlier.
 libavutil/cpu.h     |  1 +
 libavutil/x86/cpu.c | 14 +++++++++++++-
 2 files changed, 14 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..11467ba99d 100644
--- a/libavutil/x86/cpu.c
+++ b/libavutil/x86/cpu.c
@@ -146,8 +146,16 @@ 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(family == 6 && model < 70)
+                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)
@@ -196,6 +204,10 @@ int ff_get_cpu_flags_x86(void)
            used unless explicitly disabled by checking AV_CPU_FLAG_AVXSLOW. */
             if ((family == 0x15 || family == 0x16) && (rval & AV_CPU_FLAG_AVX))
                 rval |= AV_CPU_FLAG_AVXSLOW;
+
+        /* Zen 3 and earlier have slow gather */
+            if((rval & AV_CPU_FLAG_AVX2) & family <= 25)
+                rval |= AV_CPU_FLAG_SLOW_GATHER;
         }
 
         /* XOP and FMA4 use the AVX instruction coding scheme, so they can't be
-- 
2.34.1.173.g76aa8bc2d0-goog