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>

9 files changed, 67 insertions, 50 deletions

diff --git a/configure b/configure
index 650b52fcc5..7d22c2a345 100755
--- a/configure
+++ b/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"
@@ -6126,10 +6129,11 @@ EOF
             elf*) enabled debug && append X86ASMFLAGS $x86asm_debug ;;
         esac
 
-        enabled avx512 && check_x86asm avx512_external "vmovdqa32 [eax]{k1}{z}, zmm0"
-        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"
+        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"
         check_x86asm cpunop          "CPU amdnop"
     fi
 
@@ -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}"
diff --git a/doc/APIchanges b/doc/APIchanges
index ea402f6118..ccc4f24b28 100644
--- a/doc/APIchanges
+++ b/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(),
diff --git a/libavutil/cpu.c b/libavutil/cpu.c
index 1368502245..833c220192 100644
--- a/libavutil/cpu.c
+++ b/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
diff --git a/libavutil/cpu.h b/libavutil/cpu.h
index ce9bf14bf7..9711e574c5 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_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
diff --git a/libavutil/version.h b/libavutil/version.h
index c7004601c8..6c5d90507c 100644
--- a/libavutil/version.h
+++ b/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, \
diff --git a/libavutil/x86/cpu.c b/libavutil/x86/cpu.c
index 7b13fcae91..d6cd4fab9c 100644
--- a/libavutil/x86/cpu.c
+++ b/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 */
diff --git a/libavutil/x86/cpu.h b/libavutil/x86/cpu.h
index 937c697fa0..40a1eef0ab 100644
--- a/libavutil/x86/cpu.h
+++ b/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)
diff --git a/libavutil/x86/x86inc.asm b/libavutil/x86/x86inc.asm
index 01c35e3a4b..251ee797de 100644
--- a/libavutil/x86/x86inc.asm
+++ b/libavutil/x86/x86inc.asm
@@ -817,32 +817,33 @@ BRANCH_INSTR jz, je, jnz, jne, jl, jle, jnl, jnle, jg, jge, jng, jnge, ja, jae,
 
 ; cpuflags
 
-%assign cpuflags_mmx      (1<<0)
-%assign cpuflags_mmx2     (1<<1) | cpuflags_mmx
-%assign cpuflags_3dnow    (1<<2) | cpuflags_mmx
-%assign cpuflags_3dnowext (1<<3) | cpuflags_3dnow
-%assign cpuflags_sse      (1<<4) | cpuflags_mmx2
-%assign cpuflags_sse2     (1<<5) | cpuflags_sse
-%assign cpuflags_sse2slow (1<<6) | cpuflags_sse2
-%assign cpuflags_lzcnt    (1<<7) | cpuflags_sse2
-%assign cpuflags_sse3     (1<<8) | cpuflags_sse2
-%assign cpuflags_ssse3    (1<<9) | cpuflags_sse3
-%assign cpuflags_sse4     (1<<10)| cpuflags_ssse3
-%assign cpuflags_sse42    (1<<11)| cpuflags_sse4
-%assign cpuflags_aesni    (1<<12)| cpuflags_sse42
-%assign cpuflags_avx      (1<<13)| cpuflags_sse42
-%assign cpuflags_xop      (1<<14)| cpuflags_avx
-%assign cpuflags_fma4     (1<<15)| cpuflags_avx
-%assign cpuflags_fma3     (1<<16)| cpuflags_avx
-%assign cpuflags_bmi1     (1<<17)| cpuflags_avx|cpuflags_lzcnt
-%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_cache32  (1<<21)
-%assign cpuflags_cache64  (1<<22)
-%assign cpuflags_aligned  (1<<23) ; not a cpu feature, but a function variant
-%assign cpuflags_atom     (1<<24)
+%assign cpuflags_mmx       (1<<0)
+%assign cpuflags_mmx2      (1<<1) | cpuflags_mmx
+%assign cpuflags_3dnow     (1<<2) | cpuflags_mmx
+%assign cpuflags_3dnowext  (1<<3) | cpuflags_3dnow
+%assign cpuflags_sse       (1<<4) | cpuflags_mmx2
+%assign cpuflags_sse2      (1<<5) | cpuflags_sse
+%assign cpuflags_sse2slow  (1<<6) | cpuflags_sse2
+%assign cpuflags_lzcnt     (1<<7) | cpuflags_sse2
+%assign cpuflags_sse3      (1<<8) | cpuflags_sse2
+%assign cpuflags_ssse3     (1<<9) | cpuflags_sse3
+%assign cpuflags_sse4      (1<<10)| cpuflags_ssse3
+%assign cpuflags_sse42     (1<<11)| cpuflags_sse4
+%assign cpuflags_aesni     (1<<12)| cpuflags_sse42
+%assign cpuflags_avx       (1<<13)| cpuflags_sse42
+%assign cpuflags_xop       (1<<14)| cpuflags_avx
+%assign cpuflags_fma4      (1<<15)| cpuflags_avx
+%assign cpuflags_fma3      (1<<16)| cpuflags_avx
+%assign cpuflags_bmi1      (1<<17)| cpuflags_avx|cpuflags_lzcnt
+%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)
+%assign cpuflags_aligned   (1<<23) ; not a cpu feature, but a function variant
+%assign cpuflags_atom      (1<<24)
 
 ; Returns a boolean value expressing whether or not the specified cpuflag is enabled.
 %define    cpuflag(x) (((((cpuflags & (cpuflags_ %+ x)) ^ (cpuflags_ %+ x)) - 1) >> 31) & 1)
diff --git a/tests/checkasm/checkasm.c b/tests/checkasm/checkasm.c
index f74125e810..e77b4ec20f 100644
--- a/tests/checkasm/checkasm.c
+++ b/tests/checkasm/checkasm.c
@@ -220,23 +220,24 @@ static const struct {
     { "MMI",      "mmi",      AV_CPU_FLAG_MMI },
     { "MSA",      "msa",      AV_CPU_FLAG_MSA },
 #elif ARCH_X86
-    { "MMX",      "mmx",      AV_CPU_FLAG_MMX|AV_CPU_FLAG_CMOV },
-    { "MMXEXT",   "mmxext",   AV_CPU_FLAG_MMXEXT },
-    { "3DNOW",    "3dnow",    AV_CPU_FLAG_3DNOW },
-    { "3DNOWEXT", "3dnowext", AV_CPU_FLAG_3DNOWEXT },
-    { "SSE",      "sse",      AV_CPU_FLAG_SSE },
-    { "SSE2",     "sse2",     AV_CPU_FLAG_SSE2|AV_CPU_FLAG_SSE2SLOW },
-    { "SSE3",     "sse3",     AV_CPU_FLAG_SSE3|AV_CPU_FLAG_SSE3SLOW },
-    { "SSSE3",    "ssse3",    AV_CPU_FLAG_SSSE3|AV_CPU_FLAG_ATOM },
-    { "SSE4.1",   "sse4",     AV_CPU_FLAG_SSE4 },
-    { "SSE4.2",   "sse42",    AV_CPU_FLAG_SSE42 },
-    { "AES-NI",   "aesni",    AV_CPU_FLAG_AESNI },
-    { "AVX",      "avx",      AV_CPU_FLAG_AVX },
-    { "XOP",      "xop",      AV_CPU_FLAG_XOP },
-    { "FMA3",     "fma3",     AV_CPU_FLAG_FMA3 },
-    { "FMA4",     "fma4",     AV_CPU_FLAG_FMA4 },
-    { "AVX2",     "avx2",     AV_CPU_FLAG_AVX2 },
-    { "AVX-512",  "avx512",   AV_CPU_FLAG_AVX512 },
+    { "MMX",        "mmx",       AV_CPU_FLAG_MMX|AV_CPU_FLAG_CMOV },
+    { "MMXEXT",     "mmxext",    AV_CPU_FLAG_MMXEXT },
+    { "3DNOW",      "3dnow",     AV_CPU_FLAG_3DNOW },
+    { "3DNOWEXT",   "3dnowext",  AV_CPU_FLAG_3DNOWEXT },
+    { "SSE",        "sse",       AV_CPU_FLAG_SSE },
+    { "SSE2",       "sse2",      AV_CPU_FLAG_SSE2|AV_CPU_FLAG_SSE2SLOW },
+    { "SSE3",       "sse3",      AV_CPU_FLAG_SSE3|AV_CPU_FLAG_SSE3SLOW },
+    { "SSSE3",      "ssse3",     AV_CPU_FLAG_SSSE3|AV_CPU_FLAG_ATOM },
+    { "SSE4.1",     "sse4",      AV_CPU_FLAG_SSE4 },
+    { "SSE4.2",     "sse42",     AV_CPU_FLAG_SSE42 },
+    { "AES-NI",     "aesni",     AV_CPU_FLAG_AESNI },
+    { "AVX",        "avx",       AV_CPU_FLAG_AVX },
+    { "XOP",        "xop",       AV_CPU_FLAG_XOP },
+    { "FMA3",       "fma3",      AV_CPU_FLAG_FMA3 },
+    { "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 },