1
0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 15:23:05 +04:00

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
This commit is contained in:
Sayed Adel
2019-05-05 13:19:49 +02:00
committed by Alexander Alekhin
parent fc57129300
commit 5a77f4cee3
11 changed files with 417 additions and 27 deletions
+57 -14
View File
@@ -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;