Merge pull request #14007 from seiko2plus:core_avx512_infa

* core: improve AVX512 infrastructure by adding more CPU features groups

* cmake: use groups for AVX512 optimization flags

* core: remove gap in CPU flags enumeration

* cmake: restore default CPU_DISPATCH

cmake/OpenCVCompilerOptimizations.cmake

@@ -4,6 +4,15 @@
 # SSE4_1 / SSE4_2 / POPCNT
 # AVX / AVX2 / AVX_512F
 # FMA3
+#
+# CPU features groups:
+# AVX512_COMMON (Common instructions AVX-512F/CD for all CPUs that support AVX-512)
+# AVX512_KNL (Knights Landing with AVX-512F/CD/ER/PF)
+# AVX512_KNM (Knights Mill with AVX-512F/CD/ER/PF/4FMAPS/4VNNIW/VPOPCNTDQ)
+# AVX512_SKX (Skylake-X with AVX-512F/CD/BW/DQ/VL)
+# AVX512_CNL (Cannon Lake with AVX-512F/CD/BW/DQ/VL/IFMA/VBMI)
+# AVX512_CEL (Cascade Lake with AVX-512F/CD/BW/DQ/VL/IFMA/VBMI/VNNI)
+# AVX512_ICL (Ice Lake with AVX-512F/CD/BW/DQ/VL/IFMA/VBMI/VNNI/VBMI2/BITALG/VPOPCNTDQ/VPCLMULQDQ*/GFNI*/VAES*)
 
 # ppc64le arch:
 # VSX  (always available on Power8)
@@ -33,7 +42,8 @@
 #
 # CPU_{opt}_ENABLED_DEFAULT=ON/OFF - has compiler support without additional flag (CPU_BASELINE_DETECT=ON only)
 
-set(CPU_ALL_OPTIMIZATIONS "SSE;SSE2;SSE3;SSSE3;SSE4_1;SSE4_2;POPCNT;AVX;FP16;AVX2;FMA3;AVX_512F;AVX512_SKX")
+set(CPU_ALL_OPTIMIZATIONS "SSE;SSE2;SSE3;SSSE3;SSE4_1;SSE4_2;POPCNT;AVX;FP16;AVX2;FMA3;AVX_512F")
+list(APPEND CPU_ALL_OPTIMIZATIONS "AVX512_COMMON;AVX512_KNL;AVX512_KNM;AVX512_SKX;AVX512_CNL;AVX512_CEL;AVX512_ICL")
 list(APPEND CPU_ALL_OPTIMIZATIONS NEON VFPV3 FP16)
 list(APPEND CPU_ALL_OPTIMIZATIONS VSX VSX3)
 list(REMOVE_DUPLICATES CPU_ALL_OPTIMIZATIONS)
@@ -152,9 +162,15 @@ elseif(" ${CMAKE_CXX_FLAGS} " MATCHES " -march=native | -xHost | /QxHost ")
 endif()
 
 if(X86 OR X86_64)
-  ocv_update(CPU_KNOWN_OPTIMIZATIONS "SSE;SSE2;SSE3;SSSE3;SSE4_1;POPCNT;SSE4_2;FP16;FMA3;AVX;AVX2;AVX_512F;AVX512_SKX")
+  ocv_update(CPU_KNOWN_OPTIMIZATIONS "SSE;SSE2;SSE3;SSSE3;SSE4_1;POPCNT;SSE4_2;FP16;FMA3;AVX;AVX2;AVX_512F;AVX512_COMMON;AVX512_KNL;AVX512_KNM;AVX512_SKX;AVX512_CNL;AVX512_CEL;AVX512_ICL")
 
-  ocv_update(CPU_AVX512_SKX_GROUP "AVX_512F;AVX_512CD;AVX_512BW;AVX_512DQ;AVX_512VL")
+  ocv_update(CPU_AVX512_COMMON_GROUP "AVX_512F;AVX_512CD")
+  ocv_update(CPU_AVX512_KNL_GROUP "AVX512_COMMON;AVX512_KNL_EXTRA")
+  ocv_update(CPU_AVX512_KNM_GROUP "AVX512_KNL;AVX512_KNM_EXTRA;AVX_512VPOPCNTDQ")
+  ocv_update(CPU_AVX512_SKX_GROUP "AVX512_COMMON;AVX_512VL;AVX_512BW;AVX_512DQ")
+  ocv_update(CPU_AVX512_CNL_GROUP "AVX512_SKX;AVX_512IFMA;AVX_512VBMI")
+  ocv_update(CPU_AVX512_CEL_GROUP "AVX512_CNL;AVX_512VNNI")
+  ocv_update(CPU_AVX512_ICL_GROUP "AVX512_CEL;AVX_512VBMI2;AVX_512BITALG;AVX_512VPOPCNTDQ") # ? VPCLMULQDQ, GFNI, VAES
 
   ocv_update(CPU_SSE_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_sse.cpp")
   ocv_update(CPU_SSE2_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_sse2.cpp")
@@ -167,9 +183,22 @@ if(X86 OR X86_64)
   ocv_update(CPU_AVX2_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx2.cpp")
   ocv_update(CPU_FP16_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_fp16.cpp")
   ocv_update(CPU_AVX_512F_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512.cpp")
+  ocv_update(CPU_AVX512_COMMON_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512common.cpp")
+  ocv_update(CPU_AVX512_KNL_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512knl.cpp")
+  ocv_update(CPU_AVX512_KNM_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512knm.cpp")
   ocv_update(CPU_AVX512_SKX_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512skx.cpp")
+  ocv_update(CPU_AVX512_CNL_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512cnl.cpp")
+  ocv_update(CPU_AVX512_CEL_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512cel.cpp")
+  ocv_update(CPU_AVX512_ICL_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512icl.cpp")
 
   if(NOT OPENCV_CPU_OPT_IMPLIES_IGNORE)
+    ocv_update(CPU_AVX512_ICL_IMPLIES "AVX512_CEL")
+    ocv_update(CPU_AVX512_CEL_IMPLIES "AVX512_CNL")
+    ocv_update(CPU_AVX512_CNL_IMPLIES "AVX512_SKX")
+    ocv_update(CPU_AVX512_SKX_IMPLIES "AVX512_COMMON")
+    ocv_update(CPU_AVX512_KNM_IMPLIES "AVX512_KNL")
+    ocv_update(CPU_AVX512_KNL_IMPLIES "AVX512_COMMON")
+    ocv_update(CPU_AVX512_COMMON_IMPLIES "AVX_512F")
     ocv_update(CPU_AVX_512F_IMPLIES "AVX2")
     ocv_update(CPU_AVX_512F_FORCE "") # Don't force other optimizations
     ocv_update(CPU_AVX2_IMPLIES "AVX;FMA3;FP16")
@@ -192,10 +221,10 @@ if(X86 OR X86_64)
       ocv_update(CPU_${name}_FLAGS_NAME "${name}")
       if(MSVC)
         set(enable_flags "${msvc_flags}")
-        set(flags_conflict "/arch:[^ ]+")
+        set(flags_conflict "/arch:[^ ]*|/Qx:[^ ]+")
       else()
         set(enable_flags "${unix_flags}")
-        set(flags_conflict "-msse[^ ]*|-mssse3|-mavx[^ ]*|-march[^ ]+")
+        set(flags_conflict "-msse[^ ]*|-mssse3|-mavx[^ ]*|-march[^ ]*|-x[^ ]+")
       endif()
       ocv_update(CPU_${name}_FLAGS_ON "${enable_flags}")
       if(flags_conflict)
@@ -215,8 +244,14 @@ if(X86 OR X86_64)
     if(NOT X86_64) # x64 compiler doesn't support /arch:sse
       ocv_intel_compiler_optimization_option(SSE "-msse" "/arch:SSE")
     endif()
-    ocv_intel_compiler_optimization_option(AVX_512F "-march=common-avx512" "/arch:COMMON-AVX512")
-    ocv_intel_compiler_optimization_option(AVX512_SKX "-march=core-avx512" "/arch:CORE-AVX512")
+    ocv_intel_compiler_optimization_option(AVX_512F "-xCOMMON-AVX512" "/Qx:COMMON-AVX512")
+    ocv_intel_compiler_optimization_option(AVX512_COMMON "-xCOMMON-AVX512" "/Qx:COMMON-AVX512")
+    ocv_intel_compiler_optimization_option(AVX512_KNL "-xKNL" "/Qx:KNL")
+    ocv_intel_compiler_optimization_option(AVX512_KNM "-xKNM" "/Qx:KNM")
+    ocv_intel_compiler_optimization_option(AVX512_SKX "-xSKYLAKE-AVX512" "/Qx:SKYLAKE-AVX512")
+    ocv_intel_compiler_optimization_option(AVX512_CNL "-xCANNONLAKE" "/Qx:CANNONLAKE")
+    ocv_intel_compiler_optimization_option(AVX512_CEL "-xCASCADELAKE" "/Qx:CASCADELAKE")
+    ocv_intel_compiler_optimization_option(AVX512_ICL "-xICELAKE-CLIENT" "/Qx:ICELAKE-CLIENT")
   elseif(CV_GCC OR CV_CLANG)
     ocv_update(CPU_AVX2_FLAGS_ON "-mavx2")
     ocv_update(CPU_FP16_FLAGS_ON "-mf16c")
@@ -230,12 +265,21 @@ if(X86 OR X86_64)
     ocv_update(CPU_SSE2_FLAGS_ON "-msse2")
     ocv_update(CPU_SSE_FLAGS_ON "-msse")
     if(NOT (CV_GCC AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS "5.0"))  # GCC >= 5.0
-      # -mavx512f -mavx512pf -mavx512er -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi
       ocv_update(CPU_AVX_512F_FLAGS_ON "-mavx512f")
-      ocv_update(CPU_AVX512_SKX_FLAGS_ON "-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq")
+      ocv_update(CPU_AVX_512CD_FLAGS_ON "-mavx512cd")
+      ocv_update(CPU_AVX512_KNL_EXTRA_FLAGS_ON "-mavx512er -mavx512pf")
+      ocv_update(CPU_AVX512_KNM_EXTRA_FLAGS_ON "-mavx5124fmaps -mavx5124vnniw")
+      ocv_update(CPU_AVX_512BW_FLAGS_ON "-mavx512bw")
+      ocv_update(CPU_AVX_512DQ_FLAGS_ON "-mavx512dq")
+      ocv_update(CPU_AVX_512VL_FLAGS_ON "-mavx512vl")
+      ocv_update(CPU_AVX_512IFMA_FLAGS_ON "-mavx512ifma")
+      ocv_update(CPU_AVX_512VBMI_FLAGS_ON "-mavx512vbmi")
+      ocv_update(CPU_AVX_512VNNI_FLAGS_ON "-mavx512vnni")
+      ocv_update(CPU_AVX_512VBMI2_FLAGS_ON "-mavx512vbmi2")
+      ocv_update(CPU_AVX_512BITALG_FLAGS_ON "-mavx512bitalg")
+      ocv_update(CPU_AVX_512VPOPCNTDQ_FLAGS_ON "-mavx512vpopcntdq")
     else()
       ocv_update(CPU_AVX_512F_SUPPORTED OFF)
-      ocv_update(CPU_AVX512_SKX_SUPPORTED OFF)
     endif()
   elseif(MSVC)
     ocv_update(CPU_AVX2_FLAGS_ON "/arch:AVX2")
@@ -408,6 +452,7 @@ foreach(OPT ${CPU_KNOWN_OPTIMIZATIONS})
   if(NOT DEFINED CPU_${OPT}_FORCE)
     set(CPU_${OPT}_FORCE "${CPU_${OPT}_IMPLIES}")
   endif()
+  #message("${OPT}: CPU_${OPT}_FLAGS_ON=${CPU_${OPT}_FLAGS_ON}")
 endforeach()
 
 if(_add_native_flag)

cmake/checks/cpu_avx512cel.cpp

@@ -0,0 +1,11 @@
+#if defined __AVX512__ || defined __AVX512F__
+#include <immintrin.h>
+void test()
+{
+    __m512i a, b, c;
+    a = _mm512_dpwssd_epi32(a, b, c);
+}
+#else
+#error "AVX512-CEL is not supported"
+#endif
+int main() { return 0; }

cmake/checks/cpu_avx512cnl.cpp

@@ -0,0 +1,12 @@
+#if defined __AVX512__ || defined __AVX512F__
+#include <immintrin.h>
+void test()
+{
+    __m512i a, b, c;
+    a = _mm512_madd52hi_epu64(a, b, c);
+    a = _mm512_permutexvar_epi8(a, b);
+}
+#else
+#error "AVX512-CNL is not supported"
+#endif
+int main() { return 0; }

cmake/checks/cpu_avx512common.cpp

@@ -0,0 +1,14 @@
+#if defined __AVX512__ || defined __AVX512F__
+#include <immintrin.h>
+void test()
+{
+    __m512i zmm = _mm512_setzero_si512();
+    zmm = _mm512_lzcnt_epi32(zmm);
+#if defined __GNUC__ && defined __x86_64__
+    asm volatile ("" : : : "zmm16", "zmm17", "zmm18", "zmm19");
+#endif
+}
+#else
+#error "AVX512-COMMON is not supported"
+#endif
+int main() { return 0; }

cmake/checks/cpu_avx512icl.cpp

@@ -0,0 +1,13 @@
+#if defined __AVX512__ || defined __AVX512F__
+#include <immintrin.h>
+void test()
+{
+    __m512i a, b, c;
+    a = _mm512_popcnt_epi8(a);
+    a = _mm512_shrdv_epi64(a, b, c);
+    a = _mm512_popcnt_epi64(a);
+}
+#else
+#error "AVX512-ICL is not supported"
+#endif
+int main() { return 0; }

cmake/checks/cpu_avx512knl.cpp

@@ -0,0 +1,16 @@
+#if defined __AVX512__ || defined __AVX512F__
+#include <immintrin.h>
+
+void test()
+{
+    int* base;
+    __m512i idx;
+    __mmask16 m16;
+    __m512 f;
+    _mm512_mask_prefetch_i32gather_ps(idx, m16, base, 1, _MM_HINT_T1);
+    f = _mm512_rsqrt28_ps(f);
+}
+#else
+#error "AVX512-KNL is not supported"
+#endif
+int main() { return 0; }

cmake/checks/cpu_avx512knm.cpp

@@ -0,0 +1,17 @@
+#if defined __AVX512__ || defined __AVX512F__
+#include <immintrin.h>
+void test()
+{
+    __m512 a, b, c, d, e;
+    __m512i ai, bi, ci, di, ei, fi;
+    __m128  *mem;
+    __m128i *memi;
+    __mmask16 m;
+    a  = _mm512_4fnmadd_ps(a, b, c, d, e, mem);
+    ai = _mm512_4dpwssd_epi32(ai, bi, ci, di, ei, memi);
+    ai = _mm512_popcnt_epi64(ai);
+}
+#else
+#error "AVX512-KNM is not supported"
+#endif
+int main() { return 0; }

modules/core/include/opencv2/core/cv_cpu_dispatch.h

@@ -87,9 +87,41 @@
 #  include <immintrin.h>
 #  define CV_AVX_512F 1
 #endif
+#ifdef CV_CPU_COMPILE_AVX512_COMMON
+#  define CV_AVX512_COMMON 1
+#  define CV_AVX_512CD 1
+#endif
+#ifdef CV_CPU_COMPILE_AVX512_KNL
+#  define CV_AVX512_KNL 1
+#  define CV_AVX_512ER 1
+#  define CV_AVX_512PF 1
+#endif
+#ifdef CV_CPU_COMPILE_AVX512_KNM
+#  define CV_AVX512_KNM 1
+#  define CV_AVX_5124FMAPS 1
+#  define CV_AVX_5124VNNIW 1
+#  define CV_AVX_512VPOPCNTDQ 1
+#endif
 #ifdef CV_CPU_COMPILE_AVX512_SKX
-#  include <immintrin.h>
 #  define CV_AVX512_SKX 1
+#  define CV_AVX_512VL 1
+#  define CV_AVX_512BW 1
+#  define CV_AVX_512DQ 1
+#endif
+#ifdef CV_CPU_COMPILE_AVX512_CNL
+#  define CV_AVX512_CNL 1
+#  define CV_AVX_512IFMA 1
+#  define CV_AVX_512VBMI 1
+#endif
+#ifdef CV_CPU_COMPILE_AVX512_CEL
+#  define CV_AVX512_CEL 1
+#  define CV_AVX_512VNNI 1
+#endif
+#ifdef CV_CPU_COMPILE_AVX512_ICL
+#  define CV_AVX512_ICL 1
+#  define CV_AVX_512VBMI2 1
+#  define CV_AVX_512BITALG 1
+#  define CV_AVX_512VPOPCNTDQ 1
 #endif
 #ifdef CV_CPU_COMPILE_FMA3
 #  define CV_FMA3 1
@@ -223,9 +255,10 @@ struct VZeroUpperGuard {
 #ifndef CV_AVX_512ER
 #  define CV_AVX_512ER 0
 #endif
-#ifndef CV_AVX_512IFMA512
-#  define CV_AVX_512IFMA512 0
+#ifndef CV_AVX_512IFMA
+#  define CV_AVX_512IFMA 0
 #endif
+#define CV_AVX_512IFMA512 CV_AVX_512IFMA // deprecated
 #ifndef CV_AVX_512PF
 #  define CV_AVX_512PF 0
 #endif
@@ -235,9 +268,45 @@ struct VZeroUpperGuard {
 #ifndef CV_AVX_512VL
 #  define CV_AVX_512VL 0
 #endif
+#ifndef CV_AVX_5124FMAPS
+#  define CV_AVX_5124FMAPS 0
+#endif
+#ifndef CV_AVX_5124VNNIW
+#  define CV_AVX_5124VNNIW 0
+#endif
+#ifndef CV_AVX_512VPOPCNTDQ
+#  define CV_AVX_512VPOPCNTDQ 0
+#endif
+#ifndef CV_AVX_512VNNI
+#  define CV_AVX_512VNNI 0
+#endif
+#ifndef CV_AVX_512VBMI2
+#  define CV_AVX_512VBMI2 0
+#endif
+#ifndef CV_AVX_512BITALG
+#  define CV_AVX_512BITALG 0
+#endif
+#ifndef CV_AVX512_COMMON
+#  define CV_AVX512_COMMON 0
+#endif
+#ifndef CV_AVX512_KNL
+#  define CV_AVX512_KNL 0
+#endif
+#ifndef CV_AVX512_KNM
+#  define CV_AVX512_KNM 0
+#endif
 #ifndef CV_AVX512_SKX
 #  define CV_AVX512_SKX 0
 #endif
+#ifndef CV_AVX512_CNL
+#  define CV_AVX512_CNL 0
+#endif
+#ifndef CV_AVX512_CEL
+#  define CV_AVX512_CEL 0
+#endif
+#ifndef CV_AVX512_ICL
+#  define CV_AVX512_ICL 0
+#endif
 
 #ifndef CV_NEON
 #  define CV_NEON 0

modules/core/include/opencv2/core/cv_cpu_helper.h

@@ -252,6 +252,69 @@
 #endif
 #define __CV_CPU_DISPATCH_CHAIN_AVX_512F(fn, args, mode, ...)  CV_CPU_CALL_AVX_512F(fn, args); __CV_EXPAND(__CV_CPU_DISPATCH_CHAIN_ ## mode(fn, args, __VA_ARGS__))
 
+#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_AVX512_COMMON
+#  define CV_TRY_AVX512_COMMON 1
+#  define CV_CPU_FORCE_AVX512_COMMON 1
+#  define CV_CPU_HAS_SUPPORT_AVX512_COMMON 1
+#  define CV_CPU_CALL_AVX512_COMMON(fn, args) return (cpu_baseline::fn args)
+#  define CV_CPU_CALL_AVX512_COMMON_(fn, args) return (opt_AVX512_COMMON::fn args)
+#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_AVX512_COMMON
+#  define CV_TRY_AVX512_COMMON 1
+#  define CV_CPU_FORCE_AVX512_COMMON 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_COMMON (cv::checkHardwareSupport(CV_CPU_AVX512_COMMON))
+#  define CV_CPU_CALL_AVX512_COMMON(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_COMMON) return (opt_AVX512_COMMON::fn args)
+#  define CV_CPU_CALL_AVX512_COMMON_(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_COMMON) return (opt_AVX512_COMMON::fn args)
+#else
+#  define CV_TRY_AVX512_COMMON 0
+#  define CV_CPU_FORCE_AVX512_COMMON 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_COMMON 0
+#  define CV_CPU_CALL_AVX512_COMMON(fn, args)
+#  define CV_CPU_CALL_AVX512_COMMON_(fn, args)
+#endif
+#define __CV_CPU_DISPATCH_CHAIN_AVX512_COMMON(fn, args, mode, ...)  CV_CPU_CALL_AVX512_COMMON(fn, args); __CV_EXPAND(__CV_CPU_DISPATCH_CHAIN_ ## mode(fn, args, __VA_ARGS__))
+
+#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_AVX512_KNL
+#  define CV_TRY_AVX512_KNL 1
+#  define CV_CPU_FORCE_AVX512_KNL 1
+#  define CV_CPU_HAS_SUPPORT_AVX512_KNL 1
+#  define CV_CPU_CALL_AVX512_KNL(fn, args) return (cpu_baseline::fn args)
+#  define CV_CPU_CALL_AVX512_KNL_(fn, args) return (opt_AVX512_KNL::fn args)
+#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_AVX512_KNL
+#  define CV_TRY_AVX512_KNL 1
+#  define CV_CPU_FORCE_AVX512_KNL 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_KNL (cv::checkHardwareSupport(CV_CPU_AVX512_KNL))
+#  define CV_CPU_CALL_AVX512_KNL(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_KNL) return (opt_AVX512_KNL::fn args)
+#  define CV_CPU_CALL_AVX512_KNL_(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_KNL) return (opt_AVX512_KNL::fn args)
+#else
+#  define CV_TRY_AVX512_KNL 0
+#  define CV_CPU_FORCE_AVX512_KNL 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_KNL 0
+#  define CV_CPU_CALL_AVX512_KNL(fn, args)
+#  define CV_CPU_CALL_AVX512_KNL_(fn, args)
+#endif
+#define __CV_CPU_DISPATCH_CHAIN_AVX512_KNL(fn, args, mode, ...)  CV_CPU_CALL_AVX512_KNL(fn, args); __CV_EXPAND(__CV_CPU_DISPATCH_CHAIN_ ## mode(fn, args, __VA_ARGS__))
+
+#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_AVX512_KNM
+#  define CV_TRY_AVX512_KNM 1
+#  define CV_CPU_FORCE_AVX512_KNM 1
+#  define CV_CPU_HAS_SUPPORT_AVX512_KNM 1
+#  define CV_CPU_CALL_AVX512_KNM(fn, args) return (cpu_baseline::fn args)
+#  define CV_CPU_CALL_AVX512_KNM_(fn, args) return (opt_AVX512_KNM::fn args)
+#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_AVX512_KNM
+#  define CV_TRY_AVX512_KNM 1
+#  define CV_CPU_FORCE_AVX512_KNM 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_KNM (cv::checkHardwareSupport(CV_CPU_AVX512_KNM))
+#  define CV_CPU_CALL_AVX512_KNM(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_KNM) return (opt_AVX512_KNM::fn args)
+#  define CV_CPU_CALL_AVX512_KNM_(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_KNM) return (opt_AVX512_KNM::fn args)
+#else
+#  define CV_TRY_AVX512_KNM 0
+#  define CV_CPU_FORCE_AVX512_KNM 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_KNM 0
+#  define CV_CPU_CALL_AVX512_KNM(fn, args)
+#  define CV_CPU_CALL_AVX512_KNM_(fn, args)
+#endif
+#define __CV_CPU_DISPATCH_CHAIN_AVX512_KNM(fn, args, mode, ...)  CV_CPU_CALL_AVX512_KNM(fn, args); __CV_EXPAND(__CV_CPU_DISPATCH_CHAIN_ ## mode(fn, args, __VA_ARGS__))
+
 #if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_AVX512_SKX
 #  define CV_TRY_AVX512_SKX 1
 #  define CV_CPU_FORCE_AVX512_SKX 1
@@ -273,6 +336,69 @@
 #endif
 #define __CV_CPU_DISPATCH_CHAIN_AVX512_SKX(fn, args, mode, ...)  CV_CPU_CALL_AVX512_SKX(fn, args); __CV_EXPAND(__CV_CPU_DISPATCH_CHAIN_ ## mode(fn, args, __VA_ARGS__))
 
+#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_AVX512_CNL
+#  define CV_TRY_AVX512_CNL 1
+#  define CV_CPU_FORCE_AVX512_CNL 1
+#  define CV_CPU_HAS_SUPPORT_AVX512_CNL 1
+#  define CV_CPU_CALL_AVX512_CNL(fn, args) return (cpu_baseline::fn args)
+#  define CV_CPU_CALL_AVX512_CNL_(fn, args) return (opt_AVX512_CNL::fn args)
+#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_AVX512_CNL
+#  define CV_TRY_AVX512_CNL 1
+#  define CV_CPU_FORCE_AVX512_CNL 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_CNL (cv::checkHardwareSupport(CV_CPU_AVX512_CNL))
+#  define CV_CPU_CALL_AVX512_CNL(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_CNL) return (opt_AVX512_CNL::fn args)
+#  define CV_CPU_CALL_AVX512_CNL_(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_CNL) return (opt_AVX512_CNL::fn args)
+#else
+#  define CV_TRY_AVX512_CNL 0
+#  define CV_CPU_FORCE_AVX512_CNL 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_CNL 0
+#  define CV_CPU_CALL_AVX512_CNL(fn, args)
+#  define CV_CPU_CALL_AVX512_CNL_(fn, args)
+#endif
+#define __CV_CPU_DISPATCH_CHAIN_AVX512_CNL(fn, args, mode, ...)  CV_CPU_CALL_AVX512_CNL(fn, args); __CV_EXPAND(__CV_CPU_DISPATCH_CHAIN_ ## mode(fn, args, __VA_ARGS__))
+
+#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_AVX512_CEL
+#  define CV_TRY_AVX512_CEL 1
+#  define CV_CPU_FORCE_AVX512_CEL 1
+#  define CV_CPU_HAS_SUPPORT_AVX512_CEL 1
+#  define CV_CPU_CALL_AVX512_CEL(fn, args) return (cpu_baseline::fn args)
+#  define CV_CPU_CALL_AVX512_CEL_(fn, args) return (opt_AVX512_CEL::fn args)
+#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_AVX512_CEL
+#  define CV_TRY_AVX512_CEL 1
+#  define CV_CPU_FORCE_AVX512_CEL 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_CEL (cv::checkHardwareSupport(CV_CPU_AVX512_CEL))
+#  define CV_CPU_CALL_AVX512_CEL(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_CEL) return (opt_AVX512_CEL::fn args)
+#  define CV_CPU_CALL_AVX512_CEL_(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_CEL) return (opt_AVX512_CEL::fn args)
+#else
+#  define CV_TRY_AVX512_CEL 0
+#  define CV_CPU_FORCE_AVX512_CEL 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_CEL 0
+#  define CV_CPU_CALL_AVX512_CEL(fn, args)
+#  define CV_CPU_CALL_AVX512_CEL_(fn, args)
+#endif
+#define __CV_CPU_DISPATCH_CHAIN_AVX512_CEL(fn, args, mode, ...)  CV_CPU_CALL_AVX512_CEL(fn, args); __CV_EXPAND(__CV_CPU_DISPATCH_CHAIN_ ## mode(fn, args, __VA_ARGS__))
+
+#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_AVX512_ICL
+#  define CV_TRY_AVX512_ICL 1
+#  define CV_CPU_FORCE_AVX512_ICL 1
+#  define CV_CPU_HAS_SUPPORT_AVX512_ICL 1
+#  define CV_CPU_CALL_AVX512_ICL(fn, args) return (cpu_baseline::fn args)
+#  define CV_CPU_CALL_AVX512_ICL_(fn, args) return (opt_AVX512_ICL::fn args)
+#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_AVX512_ICL
+#  define CV_TRY_AVX512_ICL 1
+#  define CV_CPU_FORCE_AVX512_ICL 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_ICL (cv::checkHardwareSupport(CV_CPU_AVX512_ICL))
+#  define CV_CPU_CALL_AVX512_ICL(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_ICL) return (opt_AVX512_ICL::fn args)
+#  define CV_CPU_CALL_AVX512_ICL_(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_ICL) return (opt_AVX512_ICL::fn args)
+#else
+#  define CV_TRY_AVX512_ICL 0
+#  define CV_CPU_FORCE_AVX512_ICL 0
+#  define CV_CPU_HAS_SUPPORT_AVX512_ICL 0
+#  define CV_CPU_CALL_AVX512_ICL(fn, args)
+#  define CV_CPU_CALL_AVX512_ICL_(fn, args)
+#endif
+#define __CV_CPU_DISPATCH_CHAIN_AVX512_ICL(fn, args, mode, ...)  CV_CPU_CALL_AVX512_ICL(fn, args); __CV_EXPAND(__CV_CPU_DISPATCH_CHAIN_ ## mode(fn, args, __VA_ARGS__))
+
 #if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_NEON
 #  define CV_TRY_NEON 1
 #  define CV_CPU_FORCE_NEON 1

modules/core/include/opencv2/core/cvdef.h

@@ -249,6 +249,12 @@ namespace cv { namespace debug_build_guard { } using namespace debug_build_guard
 #define CV_CPU_AVX_512PF        19
 #define CV_CPU_AVX_512VBMI      20
 #define CV_CPU_AVX_512VL        21
+#define CV_CPU_AVX_512VBMI2     22
+#define CV_CPU_AVX_512VNNI      23
+#define CV_CPU_AVX_512BITALG    24
+#define CV_CPU_AVX_512VPOPCNTDQ 25
+#define CV_CPU_AVX_5124VNNIW    26
+#define CV_CPU_AVX_5124FMAPS    27
 
 #define CV_CPU_NEON             100
 
@@ -257,6 +263,12 @@ namespace cv { namespace debug_build_guard { } using namespace debug_build_guard
 
 // CPU features groups
 #define CV_CPU_AVX512_SKX       256
+#define CV_CPU_AVX512_COMMON    257
+#define CV_CPU_AVX512_KNL       258
+#define CV_CPU_AVX512_KNM       259
+#define CV_CPU_AVX512_CNL       260
+#define CV_CPU_AVX512_CEL       261
+#define CV_CPU_AVX512_ICL       262
 
 // when adding to this list remember to update the following enum
 #define CV_HARDWARE_MAX_FEATURE 512
@@ -287,6 +299,12 @@ enum CpuFeatures {
     CPU_AVX_512PF       = 19,
     CPU_AVX_512VBMI     = 20,
     CPU_AVX_512VL       = 21,
+    CPU_AVX_512VBMI2    = 22,
+    CPU_AVX_512VNNI     = 23,
+    CPU_AVX_512BITALG   = 24,
+    CPU_AVX_512VPOPCNTDQ= 25,
+    CPU_AVX_5124VNNIW   = 26,
+    CPU_AVX_5124FMAPS   = 27,
 
     CPU_NEON            = 100,
 
@@ -294,6 +312,12 @@ enum CpuFeatures {
     CPU_VSX3            = 201,
 
     CPU_AVX512_SKX      = 256, //!< Skylake-X with AVX-512F/CD/BW/DQ/VL
+    CPU_AVX512_COMMON   = 257, //!< Common instructions AVX-512F/CD for all CPUs that support AVX-512
+    CPU_AVX512_KNL      = 258, //!< Knights Landing with AVX-512F/CD/ER/PF
+    CPU_AVX512_KNM      = 259, //!< Knights Mill with AVX-512F/CD/ER/PF/4FMAPS/4VNNIW/VPOPCNTDQ
+    CPU_AVX512_CNL      = 260, //!< Cannon Lake with AVX-512F/CD/BW/DQ/VL/IFMA/VBMI
+    CPU_AVX512_CEL      = 261, //!< Cascade Lake with AVX-512F/CD/BW/DQ/VL/IFMA/VBMI/VNNI
+    CPU_AVX512_ICL      = 262, //!< Ice Lake with AVX-512F/CD/BW/DQ/VL/IFMA/VBMI/VNNI/VBMI2/BITALG/VPOPCNTDQ
 
     CPU_MAX_FEATURE     = 512  // see CV_HARDWARE_MAX_FEATURE
 };

modules/core/src/system.cpp

@@ -356,6 +356,12 @@ struct HWFeatures
         g_hwFeatureNames[CPU_AVX_512PF] = "AVX512PF";
         g_hwFeatureNames[CPU_AVX_512VBMI] = "AVX512VBMI";
         g_hwFeatureNames[CPU_AVX_512VL] = "AVX512VL";
+        g_hwFeatureNames[CPU_AVX_512VBMI2] = "AVX512VBMI2";
+        g_hwFeatureNames[CPU_AVX_512VNNI] = "AVX512VNNI";
+        g_hwFeatureNames[CPU_AVX_512BITALG] = "AVX512BITALG";
+        g_hwFeatureNames[CPU_AVX_512VPOPCNTDQ] = "AVX512VPOPCNTDQ";
+        g_hwFeatureNames[CPU_AVX_5124VNNIW] = "AVX5124VNNIW";
+        g_hwFeatureNames[CPU_AVX_5124FMAPS] = "AVX5124FMAPS";
 
         g_hwFeatureNames[CPU_NEON] = "NEON";
 
@@ -363,6 +369,11 @@ struct HWFeatures
         g_hwFeatureNames[CPU_VSX3] = "VSX3";
 
         g_hwFeatureNames[CPU_AVX512_SKX] = "AVX512-SKX";
+        g_hwFeatureNames[CPU_AVX512_KNL] = "AVX512-KNL";
+        g_hwFeatureNames[CPU_AVX512_KNM] = "AVX512-KNM";
+        g_hwFeatureNames[CPU_AVX512_CNL] = "AVX512-CNL";
+        g_hwFeatureNames[CPU_AVX512_CEL] = "AVX512-CEL";
+        g_hwFeatureNames[CPU_AVX512_ICL] = "AVX512-ICL";
     }
 
     void initialize(void)
@@ -404,15 +415,21 @@ struct HWFeatures
 
             have[CV_CPU_AVX2]   = (cpuid_data_ex[1] & (1<<5)) != 0;
 
-            have[CV_CPU_AVX_512F]       = (cpuid_data_ex[1] & (1<<16)) != 0;
-            have[CV_CPU_AVX_512DQ]      = (cpuid_data_ex[1] & (1<<17)) != 0;
-            have[CV_CPU_AVX_512IFMA512] = (cpuid_data_ex[1] & (1<<21)) != 0;
-            have[CV_CPU_AVX_512PF]      = (cpuid_data_ex[1] & (1<<26)) != 0;
-            have[CV_CPU_AVX_512ER]      = (cpuid_data_ex[1] & (1<<27)) != 0;
-            have[CV_CPU_AVX_512CD]      = (cpuid_data_ex[1] & (1<<28)) != 0;
-            have[CV_CPU_AVX_512BW]      = (cpuid_data_ex[1] & (1<<30)) != 0;
-            have[CV_CPU_AVX_512VL]      = (cpuid_data_ex[1] & (1<<31)) != 0;
-            have[CV_CPU_AVX_512VBMI]    = (cpuid_data_ex[2] & (1<<1)) != 0;
+            have[CV_CPU_AVX_512F]         = (cpuid_data_ex[1] & (1<<16)) != 0;
+            have[CV_CPU_AVX_512DQ]        = (cpuid_data_ex[1] & (1<<17)) != 0;
+            have[CV_CPU_AVX_512IFMA]      = (cpuid_data_ex[1] & (1<<21)) != 0;
+            have[CV_CPU_AVX_512PF]        = (cpuid_data_ex[1] & (1<<26)) != 0;
+            have[CV_CPU_AVX_512ER]        = (cpuid_data_ex[1] & (1<<27)) != 0;
+            have[CV_CPU_AVX_512CD]        = (cpuid_data_ex[1] & (1<<28)) != 0;
+            have[CV_CPU_AVX_512BW]        = (cpuid_data_ex[1] & (1<<30)) != 0;
+            have[CV_CPU_AVX_512VL]        = (cpuid_data_ex[1] & (1<<31)) != 0;
+            have[CV_CPU_AVX_512VBMI]      = (cpuid_data_ex[2] & (1<<1))  != 0;
+            have[CV_CPU_AVX_512VBMI2]     = (cpuid_data_ex[2] & (1<<6))  != 0;
+            have[CV_CPU_AVX_512VNNI]      = (cpuid_data_ex[2] & (1<<11)) != 0;
+            have[CV_CPU_AVX_512BITALG]    = (cpuid_data_ex[2] & (1<<12)) != 0;
+            have[CV_CPU_AVX_512VPOPCNTDQ] = (cpuid_data_ex[2] & (1<<14)) != 0;
+            have[CV_CPU_AVX_5124VNNIW]    = (cpuid_data_ex[3] & (1<<2))  != 0;
+            have[CV_CPU_AVX_5124FMAPS]    = (cpuid_data_ex[3] & (1<<3))  != 0;
 
             bool have_AVX_OS_support = true;
             bool have_AVX512_OS_support = true;
@@ -446,15 +463,38 @@ struct HWFeatures
                 have[CV_CPU_AVX_512CD] = false;
                 have[CV_CPU_AVX_512DQ] = false;
                 have[CV_CPU_AVX_512ER] = false;
-                have[CV_CPU_AVX_512IFMA512] = false;
+                have[CV_CPU_AVX_512IFMA] = false;
                 have[CV_CPU_AVX_512PF] = false;
                 have[CV_CPU_AVX_512VBMI] = false;
                 have[CV_CPU_AVX_512VL] = false;
+                have[CV_CPU_AVX_512VBMI2] = false;
+                have[CV_CPU_AVX_512VNNI] = false;
+                have[CV_CPU_AVX_512BITALG] = false;
+                have[CV_CPU_AVX_512VPOPCNTDQ] = false;
+                have[CV_CPU_AVX_5124VNNIW] = false;
+                have[CV_CPU_AVX_5124FMAPS] = false;
             }
 
-            if (have[CV_CPU_AVX_512F])
+            have[CV_CPU_AVX512_COMMON] = have[CV_CPU_AVX_512F] && have[CV_CPU_AVX_512CD];
+            if (have[CV_CPU_AVX512_COMMON])
             {
-                have[CV_CPU_AVX512_SKX] = have[CV_CPU_AVX_512F] & have[CV_CPU_AVX_512CD] & have[CV_CPU_AVX_512BW] & have[CV_CPU_AVX_512DQ] & have[CV_CPU_AVX_512VL];
+                have[CV_CPU_AVX512_KNL] = have[CV_CPU_AVX_512ER]  && have[CV_CPU_AVX_512PF];
+                have[CV_CPU_AVX512_KNM] = have[CV_CPU_AVX512_KNL] && have[CV_CPU_AVX_5124FMAPS] &&
+                                          have[CV_CPU_AVX_5124VNNIW] && have[CV_CPU_AVX_512VPOPCNTDQ];
+                have[CV_CPU_AVX512_SKX] = have[CV_CPU_AVX_512BW] && have[CV_CPU_AVX_512DQ] && have[CV_CPU_AVX_512VL];
+                have[CV_CPU_AVX512_CNL] = have[CV_CPU_AVX512_SKX] && have[CV_CPU_AVX_512IFMA] && have[CV_CPU_AVX_512VBMI];
+                have[CV_CPU_AVX512_CEL] = have[CV_CPU_AVX512_CNL] && have[CV_CPU_AVX_512VNNI];
+                have[CV_CPU_AVX512_ICL] = have[CV_CPU_AVX512_CEL] && have[CV_CPU_AVX_512VBMI2] &&
+                                          have[CV_CPU_AVX_512BITALG] && have[CV_CPU_AVX_512VPOPCNTDQ];
+            }
+            else
+            {
+                have[CV_CPU_AVX512_KNL] = false;
+                have[CV_CPU_AVX512_KNM] = false;
+                have[CV_CPU_AVX512_SKX] = false;
+                have[CV_CPU_AVX512_CNL] = false;
+                have[CV_CPU_AVX512_CEL] = false;
+                have[CV_CPU_AVX512_ICL] = false;
             }
         }
     #endif // CV_CPUID_X86
@@ -621,11 +661,14 @@ struct HWFeatures
                         }
                         if (isBaseline)
                         {
-                            if (dump) fprintf(stderr, "OPENCV: Trying to disable baseline CPU feature: '%s'. This has very limited effect, because code optimizations for this feature are executed unconditionally in the most cases.\n", getHWFeatureNameSafe(i));
+                            if (dump) fprintf(stderr, "OPENCV: Trying to disable baseline CPU feature: '%s'."
+                                                      "This has very limited effect, because code optimizations for this feature are executed unconditionally "
+                                                      "in the most cases.\n", getHWFeatureNameSafe(i));
                         }
                         if (!have[i])
                         {
-                            if (dump) fprintf(stderr, "OPENCV: Trying to disable unavailable CPU feature on the current platform: '%s'.\n", getHWFeatureNameSafe(i));
+                            if (dump) fprintf(stderr, "OPENCV: Trying to disable unavailable CPU feature on the current platform: '%s'.\n",
+                                getHWFeatureNameSafe(i));
                         }
                         have[i] = false;