mirror of
https://github.com/opencv/opencv.git
synced 2026-07-31 00:03:03 +04:00
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
This commit is contained in:
Alexander Alekhin
@@ -445,7 +445,7 @@ void cv::Affine3<T>::rotation(const cv::Mat& data)
|
||||
rotation(_rvec);
|
||||
}
|
||||
else
|
||||
CV_Assert(!"Input matrix can only be 3x3, 1x3 or 3x1");
|
||||
CV_Error(Error::StsError, "Input matrix can only be 3x3, 1x3 or 3x1");
|
||||
}
|
||||
|
||||
template<typename T> inline
|
||||
|
||||
@@ -454,6 +454,17 @@ for example:
|
||||
|
||||
#define CV_Assert_1( expr ) if(!!(expr)) ; else cv::error( cv::Error::StsAssert, #expr, CV_Func, __FILE__, __LINE__ )
|
||||
|
||||
//! @cond IGNORED
|
||||
#ifdef __OPENCV_BUILD
|
||||
#undef CV_Error
|
||||
#define CV_Error CV_ErrorNoReturn
|
||||
#undef CV_Error_
|
||||
#define CV_Error_ CV_ErrorNoReturn_
|
||||
#undef CV_Assert_1
|
||||
#define CV_Assert_1( expr ) if(!!(expr)) ; else cv::errorNoReturn( cv::Error::StsAssert, #expr, CV_Func, __FILE__, __LINE__ )
|
||||
#endif
|
||||
//! @endcond
|
||||
|
||||
#endif // CV_STATIC_ANALYSIS
|
||||
|
||||
#define CV_Assert_2( expr1, expr2 ) CV_Assert_1(expr1); CV_Assert_1(expr2)
|
||||
|
||||
@@ -2,16 +2,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_SSE
|
||||
# define CV_TRY_SSE 1
|
||||
# define CV_CPU_FORCE_SSE 1
|
||||
# define CV_CPU_HAS_SUPPORT_SSE 1
|
||||
# define CV_CPU_CALL_SSE(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_SSE_(fn, args) return (opt_SSE::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_SSE
|
||||
# define CV_TRY_SSE 1
|
||||
# define CV_CPU_FORCE_SSE 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSE (cv::checkHardwareSupport(CV_CPU_SSE))
|
||||
# define CV_CPU_CALL_SSE(fn, args) if (CV_CPU_HAS_SUPPORT_SSE) return (opt_SSE::fn args)
|
||||
# define CV_CPU_CALL_SSE_(fn, args) if (CV_CPU_HAS_SUPPORT_SSE) return (opt_SSE::fn args)
|
||||
#else
|
||||
# define CV_TRY_SSE 0
|
||||
# define CV_CPU_FORCE_SSE 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSE 0
|
||||
# define CV_CPU_CALL_SSE(fn, args)
|
||||
# define CV_CPU_CALL_SSE_(fn, args)
|
||||
@@ -20,16 +23,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_SSE2
|
||||
# define CV_TRY_SSE2 1
|
||||
# define CV_CPU_FORCE_SSE2 1
|
||||
# define CV_CPU_HAS_SUPPORT_SSE2 1
|
||||
# define CV_CPU_CALL_SSE2(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_SSE2_(fn, args) return (opt_SSE2::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_SSE2
|
||||
# define CV_TRY_SSE2 1
|
||||
# define CV_CPU_FORCE_SSE2 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSE2 (cv::checkHardwareSupport(CV_CPU_SSE2))
|
||||
# define CV_CPU_CALL_SSE2(fn, args) if (CV_CPU_HAS_SUPPORT_SSE2) return (opt_SSE2::fn args)
|
||||
# define CV_CPU_CALL_SSE2_(fn, args) if (CV_CPU_HAS_SUPPORT_SSE2) return (opt_SSE2::fn args)
|
||||
#else
|
||||
# define CV_TRY_SSE2 0
|
||||
# define CV_CPU_FORCE_SSE2 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSE2 0
|
||||
# define CV_CPU_CALL_SSE2(fn, args)
|
||||
# define CV_CPU_CALL_SSE2_(fn, args)
|
||||
@@ -38,16 +44,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_SSE3
|
||||
# define CV_TRY_SSE3 1
|
||||
# define CV_CPU_FORCE_SSE3 1
|
||||
# define CV_CPU_HAS_SUPPORT_SSE3 1
|
||||
# define CV_CPU_CALL_SSE3(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_SSE3_(fn, args) return (opt_SSE3::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_SSE3
|
||||
# define CV_TRY_SSE3 1
|
||||
# define CV_CPU_FORCE_SSE3 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSE3 (cv::checkHardwareSupport(CV_CPU_SSE3))
|
||||
# define CV_CPU_CALL_SSE3(fn, args) if (CV_CPU_HAS_SUPPORT_SSE3) return (opt_SSE3::fn args)
|
||||
# define CV_CPU_CALL_SSE3_(fn, args) if (CV_CPU_HAS_SUPPORT_SSE3) return (opt_SSE3::fn args)
|
||||
#else
|
||||
# define CV_TRY_SSE3 0
|
||||
# define CV_CPU_FORCE_SSE3 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSE3 0
|
||||
# define CV_CPU_CALL_SSE3(fn, args)
|
||||
# define CV_CPU_CALL_SSE3_(fn, args)
|
||||
@@ -56,16 +65,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_SSSE3
|
||||
# define CV_TRY_SSSE3 1
|
||||
# define CV_CPU_FORCE_SSSE3 1
|
||||
# define CV_CPU_HAS_SUPPORT_SSSE3 1
|
||||
# define CV_CPU_CALL_SSSE3(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_SSSE3_(fn, args) return (opt_SSSE3::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_SSSE3
|
||||
# define CV_TRY_SSSE3 1
|
||||
# define CV_CPU_FORCE_SSSE3 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSSE3 (cv::checkHardwareSupport(CV_CPU_SSSE3))
|
||||
# define CV_CPU_CALL_SSSE3(fn, args) if (CV_CPU_HAS_SUPPORT_SSSE3) return (opt_SSSE3::fn args)
|
||||
# define CV_CPU_CALL_SSSE3_(fn, args) if (CV_CPU_HAS_SUPPORT_SSSE3) return (opt_SSSE3::fn args)
|
||||
#else
|
||||
# define CV_TRY_SSSE3 0
|
||||
# define CV_CPU_FORCE_SSSE3 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSSE3 0
|
||||
# define CV_CPU_CALL_SSSE3(fn, args)
|
||||
# define CV_CPU_CALL_SSSE3_(fn, args)
|
||||
@@ -74,16 +86,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_SSE4_1
|
||||
# define CV_TRY_SSE4_1 1
|
||||
# define CV_CPU_FORCE_SSE4_1 1
|
||||
# define CV_CPU_HAS_SUPPORT_SSE4_1 1
|
||||
# define CV_CPU_CALL_SSE4_1(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_SSE4_1_(fn, args) return (opt_SSE4_1::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_SSE4_1
|
||||
# define CV_TRY_SSE4_1 1
|
||||
# define CV_CPU_FORCE_SSE4_1 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSE4_1 (cv::checkHardwareSupport(CV_CPU_SSE4_1))
|
||||
# define CV_CPU_CALL_SSE4_1(fn, args) if (CV_CPU_HAS_SUPPORT_SSE4_1) return (opt_SSE4_1::fn args)
|
||||
# define CV_CPU_CALL_SSE4_1_(fn, args) if (CV_CPU_HAS_SUPPORT_SSE4_1) return (opt_SSE4_1::fn args)
|
||||
#else
|
||||
# define CV_TRY_SSE4_1 0
|
||||
# define CV_CPU_FORCE_SSE4_1 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSE4_1 0
|
||||
# define CV_CPU_CALL_SSE4_1(fn, args)
|
||||
# define CV_CPU_CALL_SSE4_1_(fn, args)
|
||||
@@ -92,16 +107,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_SSE4_2
|
||||
# define CV_TRY_SSE4_2 1
|
||||
# define CV_CPU_FORCE_SSE4_2 1
|
||||
# define CV_CPU_HAS_SUPPORT_SSE4_2 1
|
||||
# define CV_CPU_CALL_SSE4_2(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_SSE4_2_(fn, args) return (opt_SSE4_2::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_SSE4_2
|
||||
# define CV_TRY_SSE4_2 1
|
||||
# define CV_CPU_FORCE_SSE4_2 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSE4_2 (cv::checkHardwareSupport(CV_CPU_SSE4_2))
|
||||
# define CV_CPU_CALL_SSE4_2(fn, args) if (CV_CPU_HAS_SUPPORT_SSE4_2) return (opt_SSE4_2::fn args)
|
||||
# define CV_CPU_CALL_SSE4_2_(fn, args) if (CV_CPU_HAS_SUPPORT_SSE4_2) return (opt_SSE4_2::fn args)
|
||||
#else
|
||||
# define CV_TRY_SSE4_2 0
|
||||
# define CV_CPU_FORCE_SSE4_2 0
|
||||
# define CV_CPU_HAS_SUPPORT_SSE4_2 0
|
||||
# define CV_CPU_CALL_SSE4_2(fn, args)
|
||||
# define CV_CPU_CALL_SSE4_2_(fn, args)
|
||||
@@ -110,16 +128,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_POPCNT
|
||||
# define CV_TRY_POPCNT 1
|
||||
# define CV_CPU_FORCE_POPCNT 1
|
||||
# define CV_CPU_HAS_SUPPORT_POPCNT 1
|
||||
# define CV_CPU_CALL_POPCNT(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_POPCNT_(fn, args) return (opt_POPCNT::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_POPCNT
|
||||
# define CV_TRY_POPCNT 1
|
||||
# define CV_CPU_FORCE_POPCNT 0
|
||||
# define CV_CPU_HAS_SUPPORT_POPCNT (cv::checkHardwareSupport(CV_CPU_POPCNT))
|
||||
# define CV_CPU_CALL_POPCNT(fn, args) if (CV_CPU_HAS_SUPPORT_POPCNT) return (opt_POPCNT::fn args)
|
||||
# define CV_CPU_CALL_POPCNT_(fn, args) if (CV_CPU_HAS_SUPPORT_POPCNT) return (opt_POPCNT::fn args)
|
||||
#else
|
||||
# define CV_TRY_POPCNT 0
|
||||
# define CV_CPU_FORCE_POPCNT 0
|
||||
# define CV_CPU_HAS_SUPPORT_POPCNT 0
|
||||
# define CV_CPU_CALL_POPCNT(fn, args)
|
||||
# define CV_CPU_CALL_POPCNT_(fn, args)
|
||||
@@ -128,16 +149,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_AVX
|
||||
# define CV_TRY_AVX 1
|
||||
# define CV_CPU_FORCE_AVX 1
|
||||
# define CV_CPU_HAS_SUPPORT_AVX 1
|
||||
# define CV_CPU_CALL_AVX(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_AVX_(fn, args) return (opt_AVX::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_AVX
|
||||
# define CV_TRY_AVX 1
|
||||
# define CV_CPU_FORCE_AVX 0
|
||||
# define CV_CPU_HAS_SUPPORT_AVX (cv::checkHardwareSupport(CV_CPU_AVX))
|
||||
# define CV_CPU_CALL_AVX(fn, args) if (CV_CPU_HAS_SUPPORT_AVX) return (opt_AVX::fn args)
|
||||
# define CV_CPU_CALL_AVX_(fn, args) if (CV_CPU_HAS_SUPPORT_AVX) return (opt_AVX::fn args)
|
||||
#else
|
||||
# define CV_TRY_AVX 0
|
||||
# define CV_CPU_FORCE_AVX 0
|
||||
# define CV_CPU_HAS_SUPPORT_AVX 0
|
||||
# define CV_CPU_CALL_AVX(fn, args)
|
||||
# define CV_CPU_CALL_AVX_(fn, args)
|
||||
@@ -146,16 +170,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_FP16
|
||||
# define CV_TRY_FP16 1
|
||||
# define CV_CPU_FORCE_FP16 1
|
||||
# define CV_CPU_HAS_SUPPORT_FP16 1
|
||||
# define CV_CPU_CALL_FP16(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_FP16_(fn, args) return (opt_FP16::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_FP16
|
||||
# define CV_TRY_FP16 1
|
||||
# define CV_CPU_FORCE_FP16 0
|
||||
# define CV_CPU_HAS_SUPPORT_FP16 (cv::checkHardwareSupport(CV_CPU_FP16))
|
||||
# define CV_CPU_CALL_FP16(fn, args) if (CV_CPU_HAS_SUPPORT_FP16) return (opt_FP16::fn args)
|
||||
# define CV_CPU_CALL_FP16_(fn, args) if (CV_CPU_HAS_SUPPORT_FP16) return (opt_FP16::fn args)
|
||||
#else
|
||||
# define CV_TRY_FP16 0
|
||||
# define CV_CPU_FORCE_FP16 0
|
||||
# define CV_CPU_HAS_SUPPORT_FP16 0
|
||||
# define CV_CPU_CALL_FP16(fn, args)
|
||||
# define CV_CPU_CALL_FP16_(fn, args)
|
||||
@@ -164,16 +191,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_AVX2
|
||||
# define CV_TRY_AVX2 1
|
||||
# define CV_CPU_FORCE_AVX2 1
|
||||
# define CV_CPU_HAS_SUPPORT_AVX2 1
|
||||
# define CV_CPU_CALL_AVX2(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_AVX2_(fn, args) return (opt_AVX2::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_AVX2
|
||||
# define CV_TRY_AVX2 1
|
||||
# define CV_CPU_FORCE_AVX2 0
|
||||
# define CV_CPU_HAS_SUPPORT_AVX2 (cv::checkHardwareSupport(CV_CPU_AVX2))
|
||||
# define CV_CPU_CALL_AVX2(fn, args) if (CV_CPU_HAS_SUPPORT_AVX2) return (opt_AVX2::fn args)
|
||||
# define CV_CPU_CALL_AVX2_(fn, args) if (CV_CPU_HAS_SUPPORT_AVX2) return (opt_AVX2::fn args)
|
||||
#else
|
||||
# define CV_TRY_AVX2 0
|
||||
# define CV_CPU_FORCE_AVX2 0
|
||||
# define CV_CPU_HAS_SUPPORT_AVX2 0
|
||||
# define CV_CPU_CALL_AVX2(fn, args)
|
||||
# define CV_CPU_CALL_AVX2_(fn, args)
|
||||
@@ -182,16 +212,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_FMA3
|
||||
# define CV_TRY_FMA3 1
|
||||
# define CV_CPU_FORCE_FMA3 1
|
||||
# define CV_CPU_HAS_SUPPORT_FMA3 1
|
||||
# define CV_CPU_CALL_FMA3(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_FMA3_(fn, args) return (opt_FMA3::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_FMA3
|
||||
# define CV_TRY_FMA3 1
|
||||
# define CV_CPU_FORCE_FMA3 0
|
||||
# define CV_CPU_HAS_SUPPORT_FMA3 (cv::checkHardwareSupport(CV_CPU_FMA3))
|
||||
# define CV_CPU_CALL_FMA3(fn, args) if (CV_CPU_HAS_SUPPORT_FMA3) return (opt_FMA3::fn args)
|
||||
# define CV_CPU_CALL_FMA3_(fn, args) if (CV_CPU_HAS_SUPPORT_FMA3) return (opt_FMA3::fn args)
|
||||
#else
|
||||
# define CV_TRY_FMA3 0
|
||||
# define CV_CPU_FORCE_FMA3 0
|
||||
# define CV_CPU_HAS_SUPPORT_FMA3 0
|
||||
# define CV_CPU_CALL_FMA3(fn, args)
|
||||
# define CV_CPU_CALL_FMA3_(fn, args)
|
||||
@@ -200,16 +233,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_AVX_512F
|
||||
# define CV_TRY_AVX_512F 1
|
||||
# define CV_CPU_FORCE_AVX_512F 1
|
||||
# define CV_CPU_HAS_SUPPORT_AVX_512F 1
|
||||
# define CV_CPU_CALL_AVX_512F(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_AVX_512F_(fn, args) return (opt_AVX_512F::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_AVX_512F
|
||||
# define CV_TRY_AVX_512F 1
|
||||
# define CV_CPU_FORCE_AVX_512F 0
|
||||
# define CV_CPU_HAS_SUPPORT_AVX_512F (cv::checkHardwareSupport(CV_CPU_AVX_512F))
|
||||
# define CV_CPU_CALL_AVX_512F(fn, args) if (CV_CPU_HAS_SUPPORT_AVX_512F) return (opt_AVX_512F::fn args)
|
||||
# define CV_CPU_CALL_AVX_512F_(fn, args) if (CV_CPU_HAS_SUPPORT_AVX_512F) return (opt_AVX_512F::fn args)
|
||||
#else
|
||||
# define CV_TRY_AVX_512F 0
|
||||
# define CV_CPU_FORCE_AVX_512F 0
|
||||
# define CV_CPU_HAS_SUPPORT_AVX_512F 0
|
||||
# define CV_CPU_CALL_AVX_512F(fn, args)
|
||||
# define CV_CPU_CALL_AVX_512F_(fn, args)
|
||||
@@ -218,16 +254,19 @@
|
||||
|
||||
#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
|
||||
# define CV_CPU_HAS_SUPPORT_AVX512_SKX 1
|
||||
# define CV_CPU_CALL_AVX512_SKX(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_AVX512_SKX_(fn, args) return (opt_AVX512_SKX::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_AVX512_SKX
|
||||
# define CV_TRY_AVX512_SKX 1
|
||||
# define CV_CPU_FORCE_AVX512_SKX 0
|
||||
# define CV_CPU_HAS_SUPPORT_AVX512_SKX (cv::checkHardwareSupport(CV_CPU_AVX512_SKX))
|
||||
# define CV_CPU_CALL_AVX512_SKX(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_SKX) return (opt_AVX512_SKX::fn args)
|
||||
# define CV_CPU_CALL_AVX512_SKX_(fn, args) if (CV_CPU_HAS_SUPPORT_AVX512_SKX) return (opt_AVX512_SKX::fn args)
|
||||
#else
|
||||
# define CV_TRY_AVX512_SKX 0
|
||||
# define CV_CPU_FORCE_AVX512_SKX 0
|
||||
# define CV_CPU_HAS_SUPPORT_AVX512_SKX 0
|
||||
# define CV_CPU_CALL_AVX512_SKX(fn, args)
|
||||
# define CV_CPU_CALL_AVX512_SKX_(fn, args)
|
||||
@@ -236,16 +275,19 @@
|
||||
|
||||
#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
|
||||
# define CV_CPU_HAS_SUPPORT_NEON 1
|
||||
# define CV_CPU_CALL_NEON(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_NEON_(fn, args) return (opt_NEON::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_NEON
|
||||
# define CV_TRY_NEON 1
|
||||
# define CV_CPU_FORCE_NEON 0
|
||||
# define CV_CPU_HAS_SUPPORT_NEON (cv::checkHardwareSupport(CV_CPU_NEON))
|
||||
# define CV_CPU_CALL_NEON(fn, args) if (CV_CPU_HAS_SUPPORT_NEON) return (opt_NEON::fn args)
|
||||
# define CV_CPU_CALL_NEON_(fn, args) if (CV_CPU_HAS_SUPPORT_NEON) return (opt_NEON::fn args)
|
||||
#else
|
||||
# define CV_TRY_NEON 0
|
||||
# define CV_CPU_FORCE_NEON 0
|
||||
# define CV_CPU_HAS_SUPPORT_NEON 0
|
||||
# define CV_CPU_CALL_NEON(fn, args)
|
||||
# define CV_CPU_CALL_NEON_(fn, args)
|
||||
@@ -254,16 +296,19 @@
|
||||
|
||||
#if !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_COMPILE_VSX
|
||||
# define CV_TRY_VSX 1
|
||||
# define CV_CPU_FORCE_VSX 1
|
||||
# define CV_CPU_HAS_SUPPORT_VSX 1
|
||||
# define CV_CPU_CALL_VSX(fn, args) return (cpu_baseline::fn args)
|
||||
# define CV_CPU_CALL_VSX_(fn, args) return (opt_VSX::fn args)
|
||||
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_VSX
|
||||
# define CV_TRY_VSX 1
|
||||
# define CV_CPU_FORCE_VSX 0
|
||||
# define CV_CPU_HAS_SUPPORT_VSX (cv::checkHardwareSupport(CV_CPU_VSX))
|
||||
# define CV_CPU_CALL_VSX(fn, args) if (CV_CPU_HAS_SUPPORT_VSX) return (opt_VSX::fn args)
|
||||
# define CV_CPU_CALL_VSX_(fn, args) if (CV_CPU_HAS_SUPPORT_VSX) return (opt_VSX::fn args)
|
||||
#else
|
||||
# define CV_TRY_VSX 0
|
||||
# define CV_CPU_FORCE_VSX 0
|
||||
# define CV_CPU_HAS_SUPPORT_VSX 0
|
||||
# define CV_CPU_CALL_VSX(fn, args)
|
||||
# define CV_CPU_CALL_VSX_(fn, args)
|
||||
|
||||
@@ -202,6 +202,7 @@ Regular integers:
|
||||
|pack_u | x | | x | | | |
|
||||
|unpack | x | x | x | x | x | x |
|
||||
|extract | x | x | x | x | x | x |
|
||||
|rotate (lanes) | x | x | x | x | x | x |
|
||||
|cvt_flt32 | | | | | | x |
|
||||
|cvt_flt64 | | | | | | x |
|
||||
|transpose4x4 | | | | | x | x |
|
||||
@@ -215,6 +216,7 @@ Big integers:
|
||||
|shift | x | x |
|
||||
|logical | x | x |
|
||||
|extract | x | x |
|
||||
|rotate (lanes) | x | x |
|
||||
|
||||
Floating point:
|
||||
|
||||
@@ -236,7 +238,8 @@ Floating point:
|
||||
|sqrt, abs | x | x |
|
||||
|float math | x | x |
|
||||
|transpose4x4 | x | |
|
||||
|
||||
|extract | x | x |
|
||||
|rotate (lanes) | x | x |
|
||||
|
||||
@{ */
|
||||
|
||||
@@ -1499,7 +1502,7 @@ Usage:
|
||||
v_int32x4 a, b, c;
|
||||
c = v_extract<2>(a, b);
|
||||
@endcode
|
||||
For integer types only. */
|
||||
For all types. */
|
||||
template<int s, typename _Tp, int n>
|
||||
inline v_reg<_Tp, n> v_extract(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b)
|
||||
{
|
||||
|
||||
@@ -770,15 +770,7 @@ template<int n> inline _Tpvec v_shl(const _Tpvec& a) \
|
||||
template<int n> inline _Tpvec v_shr(const _Tpvec& a) \
|
||||
{ return _Tpvec(vshrq_n_##suffix(a.val, n)); } \
|
||||
template<int n> inline _Tpvec v_rshr(const _Tpvec& a) \
|
||||
{ return _Tpvec(vrshrq_n_##suffix(a.val, n)); } \
|
||||
template<int n> inline _Tpvec v_rotate_right(const _Tpvec& a) \
|
||||
{ return _Tpvec(vextq_##suffix(a.val, vdupq_n_##suffix(0), n)); } \
|
||||
template<int n> inline _Tpvec v_rotate_left(const _Tpvec& a) \
|
||||
{ return _Tpvec(vextq_##suffix(vdupq_n_##suffix(0), a.val, _Tpvec::nlanes - n)); } \
|
||||
template<int n> inline _Tpvec v_rotate_right(const _Tpvec& a, const _Tpvec& b) \
|
||||
{ return _Tpvec(vextq_##suffix(a.val, b.val, n)); } \
|
||||
template<int n> inline _Tpvec v_rotate_left(const _Tpvec& a, const _Tpvec& b) \
|
||||
{ return _Tpvec(vextq_##suffix(b.val, a.val, _Tpvec::nlanes - n)); }
|
||||
{ return _Tpvec(vrshrq_n_##suffix(a.val, n)); }
|
||||
|
||||
OPENCV_HAL_IMPL_NEON_SHIFT_OP(v_uint8x16, u8, schar, s8)
|
||||
OPENCV_HAL_IMPL_NEON_SHIFT_OP(v_int8x16, s8, schar, s8)
|
||||
@@ -789,6 +781,29 @@ OPENCV_HAL_IMPL_NEON_SHIFT_OP(v_int32x4, s32, int, s32)
|
||||
OPENCV_HAL_IMPL_NEON_SHIFT_OP(v_uint64x2, u64, int64, s64)
|
||||
OPENCV_HAL_IMPL_NEON_SHIFT_OP(v_int64x2, s64, int64, s64)
|
||||
|
||||
#define OPENCV_HAL_IMPL_NEON_ROTATE_OP(_Tpvec, suffix) \
|
||||
template<int n> inline _Tpvec v_rotate_right(const _Tpvec& a) \
|
||||
{ return _Tpvec(vextq_##suffix(a.val, vdupq_n_##suffix(0), n)); } \
|
||||
template<int n> inline _Tpvec v_rotate_left(const _Tpvec& a) \
|
||||
{ return _Tpvec(vextq_##suffix(vdupq_n_##suffix(0), a.val, _Tpvec::nlanes - n)); } \
|
||||
template<int n> inline _Tpvec v_rotate_right(const _Tpvec& a, const _Tpvec& b) \
|
||||
{ return _Tpvec(vextq_##suffix(a.val, b.val, n)); } \
|
||||
template<int n> inline _Tpvec v_rotate_left(const _Tpvec& a, const _Tpvec& b) \
|
||||
{ return _Tpvec(vextq_##suffix(b.val, a.val, _Tpvec::nlanes - n)); }
|
||||
|
||||
OPENCV_HAL_IMPL_NEON_ROTATE_OP(v_uint8x16, u8)
|
||||
OPENCV_HAL_IMPL_NEON_ROTATE_OP(v_int8x16, s8)
|
||||
OPENCV_HAL_IMPL_NEON_ROTATE_OP(v_uint16x8, u16)
|
||||
OPENCV_HAL_IMPL_NEON_ROTATE_OP(v_int16x8, s16)
|
||||
OPENCV_HAL_IMPL_NEON_ROTATE_OP(v_uint32x4, u32)
|
||||
OPENCV_HAL_IMPL_NEON_ROTATE_OP(v_int32x4, s32)
|
||||
OPENCV_HAL_IMPL_NEON_ROTATE_OP(v_float32x4, f32)
|
||||
OPENCV_HAL_IMPL_NEON_ROTATE_OP(v_uint64x2, u64)
|
||||
OPENCV_HAL_IMPL_NEON_ROTATE_OP(v_int64x2, s64)
|
||||
#if CV_SIMD128_64F
|
||||
OPENCV_HAL_IMPL_NEON_ROTATE_OP(v_float64x2, f64)
|
||||
#endif
|
||||
|
||||
#define OPENCV_HAL_IMPL_NEON_LOADSTORE_OP(_Tpvec, _Tp, suffix) \
|
||||
inline _Tpvec v_load(const _Tp* ptr) \
|
||||
{ return _Tpvec(vld1q_##suffix(ptr)); } \
|
||||
|
||||
@@ -61,6 +61,7 @@ CV_CPU_OPTIMIZATION_HAL_NAMESPACE_BEGIN
|
||||
struct v_uint8x16
|
||||
{
|
||||
typedef uchar lane_type;
|
||||
typedef __m128i vector_type;
|
||||
enum { nlanes = 16 };
|
||||
|
||||
v_uint8x16() : val(_mm_setzero_si128()) {}
|
||||
@@ -84,6 +85,7 @@ struct v_uint8x16
|
||||
struct v_int8x16
|
||||
{
|
||||
typedef schar lane_type;
|
||||
typedef __m128i vector_type;
|
||||
enum { nlanes = 16 };
|
||||
|
||||
v_int8x16() : val(_mm_setzero_si128()) {}
|
||||
@@ -107,6 +109,7 @@ struct v_int8x16
|
||||
struct v_uint16x8
|
||||
{
|
||||
typedef ushort lane_type;
|
||||
typedef __m128i vector_type;
|
||||
enum { nlanes = 8 };
|
||||
|
||||
v_uint16x8() : val(_mm_setzero_si128()) {}
|
||||
@@ -127,6 +130,7 @@ struct v_uint16x8
|
||||
struct v_int16x8
|
||||
{
|
||||
typedef short lane_type;
|
||||
typedef __m128i vector_type;
|
||||
enum { nlanes = 8 };
|
||||
|
||||
v_int16x8() : val(_mm_setzero_si128()) {}
|
||||
@@ -146,6 +150,7 @@ struct v_int16x8
|
||||
struct v_uint32x4
|
||||
{
|
||||
typedef unsigned lane_type;
|
||||
typedef __m128i vector_type;
|
||||
enum { nlanes = 4 };
|
||||
|
||||
v_uint32x4() : val(_mm_setzero_si128()) {}
|
||||
@@ -164,6 +169,7 @@ struct v_uint32x4
|
||||
struct v_int32x4
|
||||
{
|
||||
typedef int lane_type;
|
||||
typedef __m128i vector_type;
|
||||
enum { nlanes = 4 };
|
||||
|
||||
v_int32x4() : val(_mm_setzero_si128()) {}
|
||||
@@ -182,6 +188,7 @@ struct v_int32x4
|
||||
struct v_float32x4
|
||||
{
|
||||
typedef float lane_type;
|
||||
typedef __m128 vector_type;
|
||||
enum { nlanes = 4 };
|
||||
|
||||
v_float32x4() : val(_mm_setzero_ps()) {}
|
||||
@@ -200,6 +207,7 @@ struct v_float32x4
|
||||
struct v_uint64x2
|
||||
{
|
||||
typedef uint64 lane_type;
|
||||
typedef __m128i vector_type;
|
||||
enum { nlanes = 2 };
|
||||
|
||||
v_uint64x2() : val(_mm_setzero_si128()) {}
|
||||
@@ -220,6 +228,7 @@ struct v_uint64x2
|
||||
struct v_int64x2
|
||||
{
|
||||
typedef int64 lane_type;
|
||||
typedef __m128i vector_type;
|
||||
enum { nlanes = 2 };
|
||||
|
||||
v_int64x2() : val(_mm_setzero_si128()) {}
|
||||
@@ -240,6 +249,7 @@ struct v_int64x2
|
||||
struct v_float64x2
|
||||
{
|
||||
typedef double lane_type;
|
||||
typedef __m128d vector_type;
|
||||
enum { nlanes = 2 };
|
||||
|
||||
v_float64x2() : val(_mm_setzero_pd()) {}
|
||||
@@ -259,6 +269,7 @@ struct v_float64x2
|
||||
struct v_float16x4
|
||||
{
|
||||
typedef short lane_type;
|
||||
typedef __m128i vector_type;
|
||||
enum { nlanes = 4 };
|
||||
|
||||
v_float16x4() : val(_mm_setzero_si128()) {}
|
||||
@@ -275,6 +286,27 @@ struct v_float16x4
|
||||
};
|
||||
#endif
|
||||
|
||||
namespace hal_sse_internal
|
||||
{
|
||||
template <typename to_sse_type, typename from_sse_type>
|
||||
to_sse_type v_sse_reinterpret_as(const from_sse_type& val);
|
||||
|
||||
#define OPENCV_HAL_IMPL_SSE_REINTERPRET_RAW(to_sse_type, from_sse_type, sse_cast_intrin) \
|
||||
template<> inline \
|
||||
to_sse_type v_sse_reinterpret_as(const from_sse_type& a) \
|
||||
{ return sse_cast_intrin(a); }
|
||||
|
||||
OPENCV_HAL_IMPL_SSE_REINTERPRET_RAW(__m128i, __m128i, OPENCV_HAL_NOP);
|
||||
OPENCV_HAL_IMPL_SSE_REINTERPRET_RAW(__m128i, __m128, _mm_castps_si128);
|
||||
OPENCV_HAL_IMPL_SSE_REINTERPRET_RAW(__m128i, __m128d, _mm_castpd_si128);
|
||||
OPENCV_HAL_IMPL_SSE_REINTERPRET_RAW(__m128, __m128i, _mm_castsi128_ps);
|
||||
OPENCV_HAL_IMPL_SSE_REINTERPRET_RAW(__m128, __m128, OPENCV_HAL_NOP);
|
||||
OPENCV_HAL_IMPL_SSE_REINTERPRET_RAW(__m128, __m128d, _mm_castpd_ps);
|
||||
OPENCV_HAL_IMPL_SSE_REINTERPRET_RAW(__m128d, __m128i, _mm_castsi128_pd);
|
||||
OPENCV_HAL_IMPL_SSE_REINTERPRET_RAW(__m128d, __m128, _mm_castps_pd);
|
||||
OPENCV_HAL_IMPL_SSE_REINTERPRET_RAW(__m128d, __m128d, OPENCV_HAL_NOP);
|
||||
}
|
||||
|
||||
#define OPENCV_HAL_IMPL_SSE_INITVEC(_Tpvec, _Tp, suffix, zsuffix, ssuffix, _Tps, cast) \
|
||||
inline _Tpvec v_setzero_##suffix() { return _Tpvec(_mm_setzero_##zsuffix()); } \
|
||||
inline _Tpvec v_setall_##suffix(_Tp v) { return _Tpvec(_mm_set1_##ssuffix((_Tps)v)); } \
|
||||
@@ -796,43 +828,75 @@ OPENCV_HAL_IMPL_SSE_BIN_FUNC(v_float64x2, v_max, _mm_max_pd)
|
||||
|
||||
inline v_int8x16 v_min(const v_int8x16& a, const v_int8x16& b)
|
||||
{
|
||||
#if CV_SSE4_1
|
||||
return v_int8x16(_mm_min_epi8(a.val, b.val));
|
||||
#else
|
||||
__m128i delta = _mm_set1_epi8((char)-128);
|
||||
return v_int8x16(_mm_xor_si128(delta, _mm_min_epu8(_mm_xor_si128(a.val, delta),
|
||||
_mm_xor_si128(b.val, delta))));
|
||||
#endif
|
||||
}
|
||||
inline v_int8x16 v_max(const v_int8x16& a, const v_int8x16& b)
|
||||
{
|
||||
#if CV_SSE4_1
|
||||
return v_int8x16(_mm_max_epi8(a.val, b.val));
|
||||
#else
|
||||
__m128i delta = _mm_set1_epi8((char)-128);
|
||||
return v_int8x16(_mm_xor_si128(delta, _mm_max_epu8(_mm_xor_si128(a.val, delta),
|
||||
_mm_xor_si128(b.val, delta))));
|
||||
#endif
|
||||
}
|
||||
inline v_uint16x8 v_min(const v_uint16x8& a, const v_uint16x8& b)
|
||||
{
|
||||
#if CV_SSE4_1
|
||||
return v_uint16x8(_mm_min_epu16(a.val, b.val));
|
||||
#else
|
||||
return v_uint16x8(_mm_subs_epu16(a.val, _mm_subs_epu16(a.val, b.val)));
|
||||
#endif
|
||||
}
|
||||
inline v_uint16x8 v_max(const v_uint16x8& a, const v_uint16x8& b)
|
||||
{
|
||||
#if CV_SSE4_1
|
||||
return v_uint16x8(_mm_max_epu16(a.val, b.val));
|
||||
#else
|
||||
return v_uint16x8(_mm_adds_epu16(_mm_subs_epu16(a.val, b.val), b.val));
|
||||
#endif
|
||||
}
|
||||
inline v_uint32x4 v_min(const v_uint32x4& a, const v_uint32x4& b)
|
||||
{
|
||||
#if CV_SSE4_1
|
||||
return v_uint32x4(_mm_min_epu32(a.val, b.val));
|
||||
#else
|
||||
__m128i delta = _mm_set1_epi32((int)0x80000000);
|
||||
__m128i mask = _mm_cmpgt_epi32(_mm_xor_si128(a.val, delta), _mm_xor_si128(b.val, delta));
|
||||
return v_uint32x4(v_select_si128(mask, b.val, a.val));
|
||||
#endif
|
||||
}
|
||||
inline v_uint32x4 v_max(const v_uint32x4& a, const v_uint32x4& b)
|
||||
{
|
||||
#if CV_SSE4_1
|
||||
return v_uint32x4(_mm_max_epu32(a.val, b.val));
|
||||
#else
|
||||
__m128i delta = _mm_set1_epi32((int)0x80000000);
|
||||
__m128i mask = _mm_cmpgt_epi32(_mm_xor_si128(a.val, delta), _mm_xor_si128(b.val, delta));
|
||||
return v_uint32x4(v_select_si128(mask, a.val, b.val));
|
||||
#endif
|
||||
}
|
||||
inline v_int32x4 v_min(const v_int32x4& a, const v_int32x4& b)
|
||||
{
|
||||
#if CV_SSE4_1
|
||||
return v_int32x4(_mm_min_epi32(a.val, b.val));
|
||||
#else
|
||||
return v_int32x4(v_select_si128(_mm_cmpgt_epi32(a.val, b.val), b.val, a.val));
|
||||
#endif
|
||||
}
|
||||
inline v_int32x4 v_max(const v_int32x4& a, const v_int32x4& b)
|
||||
{
|
||||
#if CV_SSE4_1
|
||||
return v_int32x4(_mm_max_epi32(a.val, b.val));
|
||||
#else
|
||||
return v_int32x4(v_select_si128(_mm_cmpgt_epi32(a.val, b.val), a.val, b.val));
|
||||
#endif
|
||||
}
|
||||
|
||||
#define OPENCV_HAL_IMPL_SSE_INT_CMP_OP(_Tpuvec, _Tpsvec, suffix, sbit) \
|
||||
@@ -1030,31 +1094,116 @@ OPENCV_HAL_IMPL_SSE_SHIFT_OP(v_uint16x8, v_int16x8, epi16, _mm_srai_epi16)
|
||||
OPENCV_HAL_IMPL_SSE_SHIFT_OP(v_uint32x4, v_int32x4, epi32, _mm_srai_epi32)
|
||||
OPENCV_HAL_IMPL_SSE_SHIFT_OP(v_uint64x2, v_int64x2, epi64, v_srai_epi64)
|
||||
|
||||
namespace hal_sse_internal
|
||||
{
|
||||
template <int imm,
|
||||
bool is_invalid = ((imm < 0) || (imm > 16)),
|
||||
bool is_first = (imm == 0),
|
||||
bool is_half = (imm == 8),
|
||||
bool is_second = (imm == 16),
|
||||
bool is_other = (((imm > 0) && (imm < 8)) || ((imm > 8) && (imm < 16)))>
|
||||
class v_sse_palignr_u8_class;
|
||||
|
||||
template <int imm>
|
||||
class v_sse_palignr_u8_class<imm, true, false, false, false, false>;
|
||||
|
||||
template <int imm>
|
||||
class v_sse_palignr_u8_class<imm, false, true, false, false, false>
|
||||
{
|
||||
public:
|
||||
inline __m128i operator()(const __m128i& a, const __m128i&) const
|
||||
{
|
||||
return a;
|
||||
}
|
||||
};
|
||||
|
||||
template <int imm>
|
||||
class v_sse_palignr_u8_class<imm, false, false, true, false, false>
|
||||
{
|
||||
public:
|
||||
inline __m128i operator()(const __m128i& a, const __m128i& b) const
|
||||
{
|
||||
return _mm_unpacklo_epi64(_mm_unpackhi_epi64(a, a), b);
|
||||
}
|
||||
};
|
||||
|
||||
template <int imm>
|
||||
class v_sse_palignr_u8_class<imm, false, false, false, true, false>
|
||||
{
|
||||
public:
|
||||
inline __m128i operator()(const __m128i&, const __m128i& b) const
|
||||
{
|
||||
return b;
|
||||
}
|
||||
};
|
||||
|
||||
template <int imm>
|
||||
class v_sse_palignr_u8_class<imm, false, false, false, false, true>
|
||||
{
|
||||
#if CV_SSSE3
|
||||
public:
|
||||
inline __m128i operator()(const __m128i& a, const __m128i& b) const
|
||||
{
|
||||
return _mm_alignr_epi8(b, a, imm);
|
||||
}
|
||||
#else
|
||||
public:
|
||||
inline __m128i operator()(const __m128i& a, const __m128i& b) const
|
||||
{
|
||||
enum { imm2 = (sizeof(__m128i) - imm) };
|
||||
return _mm_or_si128(_mm_srli_si128(a, imm), _mm_slli_si128(b, imm2));
|
||||
}
|
||||
#endif
|
||||
};
|
||||
|
||||
template <int imm>
|
||||
inline __m128i v_sse_palignr_u8(const __m128i& a, const __m128i& b)
|
||||
{
|
||||
CV_StaticAssert((imm >= 0) && (imm <= 16), "Invalid imm for v_sse_palignr_u8.");
|
||||
return v_sse_palignr_u8_class<imm>()(a, b);
|
||||
}
|
||||
}
|
||||
|
||||
template<int imm, typename _Tpvec>
|
||||
inline _Tpvec v_rotate_right(const _Tpvec &a)
|
||||
{
|
||||
enum { CV_SHIFT = imm*(sizeof(typename _Tpvec::lane_type)) };
|
||||
return _Tpvec(_mm_srli_si128(a.val, CV_SHIFT));
|
||||
using namespace hal_sse_internal;
|
||||
enum { imm2 = (imm * sizeof(typename _Tpvec::lane_type)) };
|
||||
return _Tpvec(v_sse_reinterpret_as<typename _Tpvec::vector_type>(
|
||||
_mm_srli_si128(
|
||||
v_sse_reinterpret_as<__m128i>(a.val), imm2)));
|
||||
}
|
||||
|
||||
template<int imm, typename _Tpvec>
|
||||
inline _Tpvec v_rotate_left(const _Tpvec &a)
|
||||
{
|
||||
enum { CV_SHIFT = imm*(sizeof(typename _Tpvec::lane_type)) };
|
||||
return _Tpvec(_mm_slli_si128(a.val, CV_SHIFT));
|
||||
using namespace hal_sse_internal;
|
||||
enum { imm2 = (imm * sizeof(typename _Tpvec::lane_type)) };
|
||||
return _Tpvec(v_sse_reinterpret_as<typename _Tpvec::vector_type>(
|
||||
_mm_slli_si128(
|
||||
v_sse_reinterpret_as<__m128i>(a.val), imm2)));
|
||||
}
|
||||
|
||||
template<int imm, typename _Tpvec>
|
||||
inline _Tpvec v_rotate_right(const _Tpvec &a, const _Tpvec &b)
|
||||
{
|
||||
enum { CV_SHIFT1 = imm*(sizeof(typename _Tpvec::lane_type)) };
|
||||
enum { CV_SHIFT2 = 16 - imm*(sizeof(typename _Tpvec::lane_type)) };
|
||||
return _Tpvec(_mm_or_si128(_mm_srli_si128(a.val, CV_SHIFT1), _mm_slli_si128(b.val, CV_SHIFT2)));
|
||||
using namespace hal_sse_internal;
|
||||
enum { imm2 = (imm * sizeof(typename _Tpvec::lane_type)) };
|
||||
return _Tpvec(v_sse_reinterpret_as<typename _Tpvec::vector_type>(
|
||||
v_sse_palignr_u8<imm2>(
|
||||
v_sse_reinterpret_as<__m128i>(a.val),
|
||||
v_sse_reinterpret_as<__m128i>(b.val))));
|
||||
}
|
||||
|
||||
template<int imm, typename _Tpvec>
|
||||
inline _Tpvec v_rotate_left(const _Tpvec &a, const _Tpvec &b)
|
||||
{
|
||||
enum { CV_SHIFT1 = imm*(sizeof(typename _Tpvec::lane_type)) };
|
||||
enum { CV_SHIFT2 = 16 - imm*(sizeof(typename _Tpvec::lane_type)) };
|
||||
return _Tpvec(_mm_or_si128(_mm_slli_si128(a.val, CV_SHIFT1), _mm_srli_si128(b.val, CV_SHIFT2)));
|
||||
using namespace hal_sse_internal;
|
||||
enum { imm2 = ((_Tpvec::nlanes - imm) * sizeof(typename _Tpvec::lane_type)) };
|
||||
return _Tpvec(v_sse_reinterpret_as<typename _Tpvec::vector_type>(
|
||||
v_sse_palignr_u8<imm2>(
|
||||
v_sse_reinterpret_as<__m128i>(b.val),
|
||||
v_sse_reinterpret_as<__m128i>(a.val))));
|
||||
}
|
||||
|
||||
#define OPENCV_HAL_IMPL_SSE_LOADSTORE_INT_OP(_Tpvec, _Tp) \
|
||||
@@ -1371,12 +1520,7 @@ OPENCV_HAL_IMPL_SSE_UNPACKS(v_float64x2, pd, _mm_castpd_si128, _mm_castsi128_pd)
|
||||
template<int s, typename _Tpvec>
|
||||
inline _Tpvec v_extract(const _Tpvec& a, const _Tpvec& b)
|
||||
{
|
||||
const int w = sizeof(typename _Tpvec::lane_type);
|
||||
const int n = _Tpvec::nlanes;
|
||||
__m128i ra, rb;
|
||||
ra = _mm_srli_si128(a.val, s*w);
|
||||
rb = _mm_slli_si128(b.val, (n-s)*w);
|
||||
return _Tpvec(_mm_or_si128(ra, rb));
|
||||
return v_rotate_right<s>(a, b);
|
||||
}
|
||||
|
||||
inline v_int32x4 v_round(const v_float32x4& a)
|
||||
|
||||
@@ -562,9 +562,10 @@ OPENCV_IMPL_VSX_ROTATE_LR(v_uint16x8, vec_ushort8)
|
||||
OPENCV_IMPL_VSX_ROTATE_LR(v_int16x8, vec_short8)
|
||||
OPENCV_IMPL_VSX_ROTATE_LR(v_uint32x4, vec_uint4)
|
||||
OPENCV_IMPL_VSX_ROTATE_LR(v_int32x4, vec_int4)
|
||||
OPENCV_IMPL_VSX_ROTATE_LR(v_float32x4, vec_float4)
|
||||
OPENCV_IMPL_VSX_ROTATE_LR(v_uint64x2, vec_udword2)
|
||||
OPENCV_IMPL_VSX_ROTATE_LR(v_int64x2, vec_dword2)
|
||||
|
||||
OPENCV_IMPL_VSX_ROTATE_LR(v_float64x2, vec_double2)
|
||||
|
||||
template<int imm, typename _Tpvec>
|
||||
inline _Tpvec v_rotate_right(const _Tpvec& a, const _Tpvec& b)
|
||||
|
||||
@@ -104,13 +104,13 @@ namespace cv { namespace cuda {
|
||||
|
||||
#ifndef HAVE_CUDA
|
||||
|
||||
static inline void throw_no_cuda() { CV_Error(cv::Error::GpuNotSupported, "The library is compiled without CUDA support"); }
|
||||
static inline CV_NORETURN void throw_no_cuda() { CV_Error(cv::Error::GpuNotSupported, "The library is compiled without CUDA support"); }
|
||||
|
||||
#else // HAVE_CUDA
|
||||
|
||||
#define nppSafeSetStream(oldStream, newStream) { if(oldStream != newStream) { cudaStreamSynchronize(oldStream); nppSetStream(newStream); } }
|
||||
|
||||
static inline void throw_no_cuda() { CV_Error(cv::Error::StsNotImplemented, "The called functionality is disabled for current build or platform"); }
|
||||
static inline CV_NORETURN void throw_no_cuda() { CV_Error(cv::Error::StsNotImplemented, "The called functionality is disabled for current build or platform"); }
|
||||
|
||||
namespace cv { namespace cuda
|
||||
{
|
||||
|
||||
@@ -184,6 +184,8 @@ T* allocSingleton(size_t count) { return static_cast<T*>(fastMalloc(sizeof(T) *
|
||||
#define IPP_DISABLE_HAAR 1 // improper integration/results
|
||||
#define IPP_DISABLE_HOUGH 1 // improper integration/results
|
||||
|
||||
#define IPP_DISABLE_GAUSSIANBLUR_PARALLEL 1 // not supported (2017u2 / 2017u3)
|
||||
|
||||
// Temporary disabled named IPP region. Performance
|
||||
#define IPP_DISABLE_PERF_COPYMAKE 1 // performance variations
|
||||
#define IPP_DISABLE_PERF_LUT 1 // there are no performance benefits (PR #2653)
|
||||
|
||||
Reference in New Issue
Block a user