potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-30 07:43:03 +04:00
Code Packages Releases Wiki Activity

Merge remote-tracking branch 'upstream/3.4' into merge-3.4

Browse Source
This commit is contained in:
Alexander Alekhin
2019-10-05 15:45:31 +00:00
parent c54753c185 98fc098216
commit 626bfbf309
23 changed files with 222 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmake/OpenCVCompilerOptimizations.cmake
+11 -9
View File
@@ -5,13 +5,15 @@
# AVX / AVX2 / AVX_512F
# FMA3
#
# AVX512 details: https://en.wikipedia.org/wiki/AVX-512#CPUs_with_AVX-512
#
# 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_CLX (Cascade Lake with AVX-512F/CD/BW/DQ/VL/VNNI)
# AVX512_ICL (Ice Lake with AVX-512F/CD/BW/DQ/VL/IFMA/VBMI/VNNI/VBMI2/BITALG/VPOPCNTDQ/VPCLMULQDQ*/GFNI*/VAES*)
# ppc64le arch:
@@ -43,7 +45,7 @@
# 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")
list(APPEND CPU_ALL_OPTIMIZATIONS "AVX512_COMMON;AVX512_KNL;AVX512_KNM;AVX512_SKX;AVX512_CNL;AVX512_CEL;AVX512_ICL")
list(APPEND CPU_ALL_OPTIMIZATIONS "AVX512_COMMON;AVX512_KNL;AVX512_KNM;AVX512_SKX;AVX512_CNL;AVX512_CLX;AVX512_ICL")
list(APPEND CPU_ALL_OPTIMIZATIONS NEON VFPV3 FP16)
list(APPEND CPU_ALL_OPTIMIZATIONS MSA)
list(APPEND CPU_ALL_OPTIMIZATIONS VSX VSX3)
@@ -163,15 +165,15 @@ elseif(" ${CMAKE_CXX_FLAGS} " MATCHES " -march=native | -xHost | /QxHost ")
endif()
if(X86 OR X86_64)
ocv_update(CPU_KNOWN_OPTIMIZATIONS "SSE;SSE2;SSE3;SSSE3;SSE4_1;POPCNT;SSE4_2;FP16;FMA3;AVX;AVX2;AVX_512F;AVX512_COMMON;AVX512_KNL;AVX512_KNM;AVX512_SKX;AVX512_CNL;AVX512_CEL;AVX512_ICL")
ocv_update(CPU_KNOWN_OPTIMIZATIONS "SSE;SSE2;SSE3;SSSE3;SSE4_1;POPCNT;SSE4_2;FP16;FMA3;AVX;AVX2;AVX_512F;AVX512_COMMON;AVX512_KNL;AVX512_KNM;AVX512_SKX;AVX512_CNL;AVX512_CLX;AVX512_ICL")
ocv_update(CPU_AVX512_COMMON_GROUP "AVX_512F;AVX_512CD")
ocv_update(CPU_AVX512_KNL_GROUP "AVX512_COMMON;AVX512_KNL_EXTRA")
ocv_update(CPU_AVX512_KNM_GROUP "AVX512_KNL;AVX512_KNM_EXTRA;AVX_512VPOPCNTDQ")
ocv_update(CPU_AVX512_SKX_GROUP "AVX512_COMMON;AVX_512VL;AVX_512BW;AVX_512DQ")
ocv_update(CPU_AVX512_CNL_GROUP "AVX512_SKX;AVX_512IFMA;AVX_512VBMI")
ocv_update(CPU_AVX512_CEL_GROUP "AVX512_CNL;AVX_512VNNI")
ocv_update(CPU_AVX512_ICL_GROUP "AVX512_CEL;AVX_512VBMI2;AVX_512BITALG;AVX_512VPOPCNTDQ") # ? VPCLMULQDQ, GFNI, VAES
ocv_update(CPU_AVX512_CLX_GROUP "AVX512_SKX;AVX_512VNNI")
ocv_update(CPU_AVX512_ICL_GROUP "AVX512_SKX;AVX_512IFMA;AVX_512VBMI;AVX_512VNNI;AVX_512VBMI2;AVX_512BITALG;AVX_512VPOPCNTDQ") # ? VPCLMULQDQ, GFNI, VAES
ocv_update(CPU_SSE_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_sse.cpp")
ocv_update(CPU_SSE2_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_sse2.cpp")
@@ -189,12 +191,12 @@ if(X86 OR X86_64)
ocv_update(CPU_AVX512_KNM_TEST_FILE "${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 "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512cel.cpp")
ocv_update(CPU_AVX512_CLX_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512clx.cpp")
ocv_update(CPU_AVX512_ICL_TEST_FILE "${OpenCV_SOURCE_DIR}/cmake/checks/cpu_avx512icl.cpp")
if(NOT OPENCV_CPU_OPT_IMPLIES_IGNORE)
ocv_update(CPU_AVX512_ICL_IMPLIES "AVX512_CEL")
ocv_update(CPU_AVX512_CEL_IMPLIES "AVX512_CNL")
ocv_update(CPU_AVX512_ICL_IMPLIES "AVX512_SKX")
ocv_update(CPU_AVX512_CLX_IMPLIES "AVX512_SKX")
ocv_update(CPU_AVX512_CNL_IMPLIES "AVX512_SKX")
ocv_update(CPU_AVX512_SKX_IMPLIES "AVX512_COMMON")
ocv_update(CPU_AVX512_KNM_IMPLIES "AVX512_KNL")
@@ -251,7 +253,7 @@ if(X86 OR X86_64)
ocv_intel_compiler_optimization_option(AVX512_KNM "-xKNM" "/Qx:KNM")
ocv_intel_compiler_optimization_option(AVX512_SKX "-xSKYLAKE-AVX512" "/Qx:SKYLAKE-AVX512")
ocv_intel_compiler_optimization_option(AVX512_CNL "-xCANNONLAKE" "/Qx:CANNONLAKE")
ocv_intel_compiler_optimization_option(AVX512_CEL "-xCASCADELAKE" "/Qx:CASCADELAKE")
ocv_intel_compiler_optimization_option(AVX512_CLX "-xCASCADELAKE" "/Qx:CASCADELAKE")
ocv_intel_compiler_optimization_option(AVX512_ICL "-xICELAKE-CLIENT" "/Qx:ICELAKE-CLIENT")
elseif(CV_GCC OR CV_CLANG)
ocv_update(CPU_AVX2_FLAGS_ON "-mavx2")
cmake/OpenCVDetectInferenceEngine.cmake
+2 -2
View File
@@ -80,9 +80,9 @@ endif()
if(INF_ENGINE_TARGET)
if(NOT INF_ENGINE_RELEASE)
message(WARNING "InferenceEngine version have not been set, 2019R2 will be used by default. Set INF_ENGINE_RELEASE variable if you experience build errors.")
message(WARNING "InferenceEngine version have not been set, 2019R3 will be used by default. Set INF_ENGINE_RELEASE variable if you experience build errors.")
endif()
set(INF_ENGINE_RELEASE "2019020000" CACHE STRING "Force IE version, should be in form YYYYAABBCC (e.g. 2018R2.0.2 -> 2018020002)")
set(INF_ENGINE_RELEASE "2019030000" CACHE STRING "Force IE version, should be in form YYYYAABBCC (e.g. 2018R2.0.2 -> 2018020002)")
set_target_properties(${INF_ENGINE_TARGET} PROPERTIES
INTERFACE_COMPILE_DEFINITIONS "HAVE_INF_ENGINE=1;INF_ENGINE_RELEASE=${INF_ENGINE_RELEASE}"
)
cmake/checks/cpu_avx512cel.cpp → cmake/checks/cpu_avx512clx.cpp
+3 -3
View File
@@ -3,9 +3,9 @@
void test()
{
__m512i a, b, c;
a = _mm512_dpwssd_epi32(a, b, c);
a = _mm512_dpwssd_epi32(a, b, c); // VNNI
}
#else
#error "AVX512-CEL is not supported"
#error "AVX512-CLX is not supported"
#endif
int main() { return 0; }
int main() { return 0; }
cmake/checks/cpu_avx512icl.cpp
+4 -3
View File
@@ -3,9 +3,10 @@
void test()
{
__m512i a, b, c;
a = _mm512_popcnt_epi8(a);
a = _mm512_shrdv_epi64(a, b, c);
a = _mm512_popcnt_epi64(a);
a = _mm512_popcnt_epi8(a); // BITALG
a = _mm512_shrdv_epi64(a, b, c); // VBMI2
a = _mm512_popcnt_epi64(a); // VPOPCNTDQ
a = _mm512_dpwssd_epi32(a, b, c); // VNNI
}
#else
#error "AVX512-ICL is not supported"