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 pull request #14210 from terfendail:wui_512

Browse Source 
AVX512 wide universal intrinsics (#14210)

* Added implementation of 512-bit wide universal intrinsics(WIP)

* Added implementation of 512-bit wide universal intrinsics: implemented WUI vector types(WIP)

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented load/store

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented fp16 load/store

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented recombine and zip, implemented non-saturating and saturating arithmetics

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented bit operations

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented comparisons

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented lane shifts and reduction

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented absolute values

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented rounding and cast to float

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented LUT

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented type extension/narrowing and matrix operations

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented load_deinterleave for 2 and 3 channels images

* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented load_deinterleave for 2- and implemented for 4-channel images

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented store_interleave

* Added implementation of 512-bit wide universal intrinsics(WIP): implemented signmask and checks

* Added implementation of 512-bit wide universal intrinsics(WIP): build fixes

* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented popcount in case AVX512_BITALG is unavailable

* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented zip

* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented rotate for s8 and s16

* Added implementation of 512-bit wide universal intrinsics(WIP): reimplemented interleave/deinterleave for s8 and s16

* Added implementation of 512-bit wide universal intrinsics(WIP): updated v512_set macros

* Added implementation of 512-bit wide universal intrinsics(WIP): fix for GCC wrong _mm512_abs_pd definition

* Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_zip to avoid AVX512_VBMI intrinsics

* Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_invsqrt to avoid AVX512_ER intrinsics

* Added implementation of 512-bit wide universal intrinsics(WIP): reworked v_rotate, v_popcount and interleave/deinterleave for U8 to avoid AVX512_VBMI intrinsics

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed integral image SIMD part

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed warnings

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed load_deinterleave for u8 and u16

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed v_invsqrt accuracy for f64

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed interleave/deinterleave for u32 and u64

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed interleave_pairs, interleave_quads and pack_triplets

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed rotate_left

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed rotate_left/right, part 2

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed 512-wide universal intrinsics based resize

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed findContours by avoiding use of uint64 dependent 512-wide v_signmask()

* Added implementation of 512-bit wide universal intrinsics(WIP): fixed trailing whitespaces

* Added implementation of 512-bit wide universal intrinsics(WIP): reworked specific intrinsic sets dependent parts to check availability of intrinsics based on CPU feature group defines

* Added implementation of 512-bit wide universal intrinsics(WIP):Updated AVX512 implementation of v_popcount to avoid AVX512VPOPCNTDQ intrinsics if unavailable.

* Added implementation of 512-bit wide universal intrinsics(WIP): Fixed universal intrinsics data initialisation, v_mul_wrap, v_floor, v_ceil and v_signmask.

* Added implementation of 512-bit wide universal intrinsics(WIP): Removed hasSIMD512()

* Added implementation of 512-bit wide universal intrinsics(WIP): Fixes for gcc build

* Added implementation of 512-bit wide universal intrinsics(WIP): Reworked v_signmask, v_check_any() and v_check_all() implementation.
This commit is contained in:
Vitaly Tuzov
2019-06-03 18:05:35 +03:00
committed by Alexander Alekhin
parent 3289a0aff9
commit 3b015dfc7d
10 changed files with 2902 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/core/test/test_intrin.cpp
+32 -1
View File
@@ -7,11 +7,15 @@
#include "test_intrin128.simd_declarations.hpp"
#undef CV_CPU_DISPATCH_MODES_ALL
#include "opencv2/core/cv_cpu_dispatch.h"
#include "test_intrin256.simd.hpp"
#include "test_intrin256.simd_declarations.hpp"
#undef CV_CPU_DISPATCH_MODES_ALL
#include "opencv2/core/cv_cpu_dispatch.h"
#include "test_intrin512.simd.hpp"
#include "test_intrin512.simd_declarations.hpp"
#ifdef _MSC_VER
# pragma warning(disable:4702) // unreachable code
#endif
@@ -30,6 +34,11 @@ namespace opencv_test { namespace hal {
throw SkipTestException("SIMD256 (" #cpu_opt ") is not available or disabled"); \
} while(0)
#define DISPATCH_SIMD512(fn, cpu_opt) do { \
CV_CPU_CALL_ ## cpu_opt ## _(fn, ()); \
throw SkipTestException("SIMD512 (" #cpu_opt ") is not available or disabled"); \
} while(0)
#define DEFINE_SIMD_TESTS(simd_size, cpu_opt) \
TEST(hal_intrin ## simd_size, uint8x16_ ## cpu_opt) { DISPATCH_SIMD ## simd_size(test_hal_intrin_uint8, cpu_opt); } \
TEST(hal_intrin ## simd_size, int8x16_ ## cpu_opt) { DISPATCH_SIMD ## simd_size(test_hal_intrin_int8, cpu_opt); } \
@@ -67,6 +76,9 @@ DEFINE_SIMD_TESTS(128, AVX)
#if defined CV_CPU_DISPATCH_COMPILE_AVX2 || defined CV_CPU_BASELINE_COMPILE_AVX2
DEFINE_SIMD_TESTS(128, AVX2)
#endif
#if defined CV_CPU_DISPATCH_COMPILE_AVX512_SKX || defined CV_CPU_BASELINE_COMPILE_AVX512_SKX
DEFINE_SIMD_TESTS(128, AVX512_SKX)
#endif
TEST(hal_intrin128, float16x8_FP16)
{
@@ -91,6 +103,10 @@ namespace intrin256 {
DEFINE_SIMD_TESTS(256, AVX2)
#endif
#if defined CV_CPU_DISPATCH_COMPILE_AVX512_SKX || defined CV_CPU_BASELINE_COMPILE_AVX512_SKX
DEFINE_SIMD_TESTS(256, AVX512_SKX)
#endif
TEST(hal_intrin256, float16x16_FP16)
{
//CV_CPU_CALL_FP16_(test_hal_intrin_float16, ());
@@ -101,4 +117,19 @@ TEST(hal_intrin256, float16x16_FP16)
} // namespace intrin256
namespace intrin512 {
#if defined CV_CPU_DISPATCH_COMPILE_AVX512_SKX || defined CV_CPU_BASELINE_COMPILE_AVX512_SKX
DEFINE_SIMD_TESTS(512, AVX512_SKX)
#endif
TEST(hal_intrin512, float16x32_FP16)
{
CV_CPU_CALL_AVX512_SKX_(test_hal_intrin_float16, ());
throw SkipTestException("Unsupported hardware: FP16 is not available");
}
} // namespace intrin512
}} // namespace