[FFmpeg-cvslog] libavutil/cpu: Add AV_CPU_FLAG_SLOW_GATHER.

[Alan Kelly]

ffmpeg | branch: master | Alan Kelly <alankelly-at-google.com at ffmpeg.org> | Tue Dec 21 20:56:41 2021 +0100| [ffbab99f2c22be06ef3c564fd38320d40e48a2b5] | committer: James Almer

libavutil/cpu: Add AV_CPU_FLAG_SLOW_GATHER.

This flag is set on Haswell and earlier and all AMD cpus.

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=ffbab99f2c22be06ef3c564fd38320d40e48a2b5
---

 doc/APIchanges      |  3 +++
 libavutil/cpu.h     |  1 +
 libavutil/version.h |  4 ++--
 libavutil/x86/cpu.c | 15 ++++++++++++++-
 4 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/doc/APIchanges b/doc/APIchanges
index 93fc45ced4..ac75040274 100644
--- a/doc/APIchanges
+++ b/doc/APIchanges
@@ -14,6 +14,9 @@ libavutil:     2021-04-27
 
 API changes, most recent first:
 
+2021-12-21 - xxxxxxxxxx - lavu 57.12.100 - cpu.h
+  Add AV_CPU_FLAG_SLOW_GATHER.
+
 2021-12-20 - xxxxxxxxxx - lavu 57.11.101 - display.h
   Modified the documentation of av_display_rotation_set()
   to match its longstanding actual behaviour of treating
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/version.h b/libavutil/version.h
index 678401fcf5..668f9206fe 100644
--- a/libavutil/version.h
+++ b/libavutil/version.h
@@ -79,8 +79,8 @@
  */
 
 #define LIBAVUTIL_VERSION_MAJOR  57
-#define LIBAVUTIL_VERSION_MINOR  11
-#define LIBAVUTIL_VERSION_MICRO 101
+#define LIBAVUTIL_VERSION_MINOR  12
+#define LIBAVUTIL_VERSION_MICRO 100
 
 #define LIBAVUTIL_VERSION_INT   AV_VERSION_INT(LIBAVUTIL_VERSION_MAJOR, \
                                                LIBAVUTIL_VERSION_MINOR, \
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)