avutil/cpu: add AVX512 Icelake flag

Signed-off-by: Wu Jianhua <jianhua.wu@intel.com>
Reviewed-by: Henrik Gramner <henrik@gramner.com>
Signed-off-by: James Almer <jamrial@gmail.com>

configure

@@ -443,6 +443,7 @@ Optimization options (experts only):
   --disable-fma4           disable FMA4 optimizations
   --disable-avx2           disable AVX2 optimizations
   --disable-avx512         disable AVX-512 optimizations
+  --disable-avx512icl      disable AVX-512ICL optimizations
   --disable-aesni          disable AESNI optimizations
   --disable-armv5te        disable armv5te optimizations
   --disable-armv6          disable armv6 optimizations
@@ -2096,6 +2097,7 @@ ARCH_EXT_LIST_X86_SIMD="
     avx
     avx2
     avx512
+    avx512icl
     fma3
     fma4
     mmx
@@ -2665,6 +2667,7 @@ fma3_deps="avx"
 fma4_deps="avx"
 avx2_deps="avx"
 avx512_deps="avx2"
+avx512icl_deps="avx512"
 
 mmx_external_deps="x86asm"
 mmx_inline_deps="inline_asm x86"
@@ -6127,6 +6130,7 @@ EOF
         esac
 
         enabled avx512    && check_x86asm avx512_external    "vmovdqa32 [eax]{k1}{z}, zmm0"
+        enabled avx512icl && check_x86asm avx512icl_external "vpdpwssds zmm31{k1}{z}, zmm29, zmm28"
         enabled avx2      && check_x86asm avx2_external      "vextracti128 xmm0, ymm0, 0"
         enabled xop       && check_x86asm xop_external       "vpmacsdd xmm0, xmm1, xmm2, xmm3"
         enabled fma4      && check_x86asm fma4_external      "vfmaddps ymm0, ymm1, ymm2, ymm3"
@@ -7469,6 +7473,7 @@ if enabled x86; then
     echo "AVX enabled               ${avx-no}"
     echo "AVX2 enabled              ${avx2-no}"
     echo "AVX-512 enabled           ${avx512-no}"
+    echo "AVX-512ICL enabled        ${avx512icl-no}"
     echo "XOP enabled               ${xop-no}"
     echo "FMA3 enabled              ${fma3-no}"
     echo "FMA4 enabled              ${fma4-no}"

doc/APIchanges

@@ -14,6 +14,9 @@ libavutil:     2021-04-27
 
 API changes, most recent first:
 
+2022-03-10 - xxxxxxxxxx - lavu 57.23.100 - cpu.h
+  Add AV_CPU_FLAG_AVX512ICL.
+
 2022-02-07 - xxxxxxxxxx - lavu 57.21.100 - fifo.h
   Deprecate AVFifoBuffer and the API around it, namely av_fifo_alloc(),
   av_fifo_alloc_array(), av_fifo_free(), av_fifo_freep(), av_fifo_reset(),

libavutil/cpu.c

@@ -137,6 +137,7 @@ int av_parse_cpu_caps(unsigned *flags, const char *s)
         { "cmov",     NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_CMOV     },    .unit = "flags" },
         { "aesni",    NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_AESNI    },    .unit = "flags" },
         { "avx512"  , NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_AVX512   },    .unit = "flags" },
+        { "avx512icl",  NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_AVX512ICL   }, .unit = "flags" },
         { "slowgather", NULL, 0, AV_OPT_TYPE_CONST, { .i64 = AV_CPU_FLAG_SLOW_GATHER }, .unit = "flags" },
 
 #define CPU_FLAG_P2 AV_CPU_FLAG_CMOV | AV_CPU_FLAG_MMX

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_AVX512ICL  0x200000 ///< F/CD/BW/DQ/VL/VNNI/IFMA/VBMI/VBMI2/VPOPCNTDQ/BITALG/GFNI/VAES/VPCLMULQDQ
 #define AV_CPU_FLAG_SLOW_GATHER  0x2000000 ///< CPU has slow gathers.
 
 #define AV_CPU_FLAG_ALTIVEC      0x0001 ///< standard

libavutil/version.h

@@ -79,7 +79,7 @@
  */
 
 #define LIBAVUTIL_VERSION_MAJOR  57
-#define LIBAVUTIL_VERSION_MINOR  22
+#define LIBAVUTIL_VERSION_MINOR  23
 #define LIBAVUTIL_VERSION_MICRO 100
 
 #define LIBAVUTIL_VERSION_INT   AV_VERSION_INT(LIBAVUTIL_VERSION_MAJOR, \

libavutil/x86/cpu.c

@@ -150,9 +150,13 @@ int ff_get_cpu_flags_x86(void)
             rval |= AV_CPU_FLAG_AVX2;
 #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)
+            if ((rval & AV_CPU_FLAG_AVX2) && (ebx & 0xd0030000) == 0xd0030000) {
                 rval |= AV_CPU_FLAG_AVX512;
-
+#if HAVE_AVX512ICL
+                if ((ebx & 0xd0200000) == 0xd0200000 && (ecx & 0x5f42) == 0x5f42)
+                    rval |= AV_CPU_FLAG_AVX512ICL;
+#endif /* HAVE_AVX512ICL */
+            }
         }
 #endif /* HAVE_AVX512 */
 #endif /* HAVE_AVX2 */

libavutil/x86/cpu.h

@@ -80,6 +80,7 @@
 #define EXTERNAL_AVX2_SLOW(flags)   CPUEXT_SUFFIX_SLOW2(flags, _EXTERNAL, AVX2, AVX)
 #define EXTERNAL_AESNI(flags)       CPUEXT_SUFFIX(flags, _EXTERNAL, AESNI)
 #define EXTERNAL_AVX512(flags)      CPUEXT_SUFFIX(flags, _EXTERNAL, AVX512)
+#define EXTERNAL_AVX512ICL(flags)   CPUEXT_SUFFIX(flags, _EXTERNAL, AVX512ICL)
 
 #define INLINE_AMD3DNOW(flags)      CPUEXT_SUFFIX(flags, _INLINE, AMD3DNOW)
 #define INLINE_AMD3DNOWEXT(flags)   CPUEXT_SUFFIX(flags, _INLINE, AMD3DNOWEXT)

libavutil/x86/x86inc.asm

@@ -838,6 +838,7 @@ BRANCH_INSTR jz, je, jnz, jne, jl, jle, jnl, jnle, jg, jge, jng, jnge, ja, jae,
 %assign cpuflags_bmi2      (1<<18)| cpuflags_bmi1
 %assign cpuflags_avx2      (1<<19)| cpuflags_fma3|cpuflags_bmi2
 %assign cpuflags_avx512    (1<<20)| cpuflags_avx2 ; F, CD, BW, DQ, VL
+%assign cpuflags_avx512icl (1<<25)| cpuflags_avx512
 
 %assign cpuflags_cache32   (1<<21)
 %assign cpuflags_cache64   (1<<22)

tests/checkasm/checkasm.c

@@ -237,6 +237,7 @@ static const struct {
     { "FMA4",       "fma4",      AV_CPU_FLAG_FMA4 },
     { "AVX2",       "avx2",      AV_CPU_FLAG_AVX2 },
     { "AVX-512",    "avx512",    AV_CPU_FLAG_AVX512 },
+    { "AVX-512ICL", "avx512icl", AV_CPU_FLAG_AVX512ICL },
 #elif ARCH_LOONGARCH
     { "LSX",      "lsx",      AV_CPU_FLAG_LSX },
     { "LASX",     "lasx",     AV_CPU_FLAG_LASX },