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 branch 4.x

Browse Source
This commit is contained in:
Alexander Smorkalov
2026-02-11 13:54:39 +03:00
committed by Alexander Smorkalov
parent 1719aa1339 a6c10358a4
commit 82ff8e45e9
468 changed files with 16647 additions and 11284 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/core/include/opencv2/core/cv_cpu_dispatch.h
+8
View File
@@ -239,6 +239,10 @@ struct VZeroUpperGuard {
#elif defined(__ARM_NEON)
# include <arm_neon.h>
# define CV_NEON 1
#ifdef __ARM_FEATURE_SVE
# include<arm_sve.h>
# define CV_SVE 1
#endif
#elif defined(__VSX__) && defined(__PPC64__) && defined(__LITTLE_ENDIAN__)
# include <altivec.h>
# undef vector
@@ -369,6 +373,10 @@ struct VZeroUpperGuard {
# define CV_NEON 0
#endif
#ifndef CV_SVE
# define CV_SVE 0
#endif
#ifndef CV_RVV071
# define CV_RVV071 0
#endif
modules/core/include/opencv2/core/cv_cpu_helper.h
+21
View File
@@ -399,6 +399,27 @@
#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_SVE
# define CV_TRY_SVE 1
# define CV_CPU_FORCE_SVE 1
# define CV_CPU_HAS_SUPPORT_SVE 1
# define CV_CPU_CALL_SVE(fn, args) return (cpu_baseline::fn args)
# define CV_CPU_CALL_SVE_(fn, args) return (opt_SVE::fn args)
#elif !defined CV_DISABLE_OPTIMIZATION && defined CV_ENABLE_INTRINSICS && defined CV_CPU_DISPATCH_COMPILE_SVE
# define CV_TRY_SVE 1
# define CV_CPU_FORCE_SVE 0
# define CV_CPU_HAS_SUPPORT_SVE (cv::checkHardwareSupport(CV_CPU_SVE))
# define CV_CPU_CALL_SVE(fn, args) if (CV_CPU_HAS_SUPPORT_SVE) return (opt_SVE::fn args)
# define CV_CPU_CALL_SVE_(fn, args) if (CV_CPU_HAS_SUPPORT_SVE) return (opt_SVE::fn args)
#else
# define CV_TRY_SVE 0
# define CV_CPU_FORCE_SVE 0
# define CV_CPU_HAS_SUPPORT_SVE 0
# define CV_CPU_CALL_SVE(fn, args)
# define CV_CPU_CALL_SVE_(fn, args)
#endif
#define __CV_CPU_DISPATCH_CHAIN_SVE(fn, args, mode, ...) CV_CPU_CALL_SVE(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
+2
View File
@@ -279,6 +279,7 @@ namespace cv {
#define CV_CPU_NEON_DOTPROD 101
#define CV_CPU_NEON_FP16 102
#define CV_CPU_NEON_BF16 103
#define CV_CPU_SVE 104
#define CV_CPU_MSA 150
@@ -342,6 +343,7 @@ enum CpuFeatures {
CPU_NEON_DOTPROD = 101,
CPU_NEON_FP16 = 102,
CPU_NEON_BF16 = 103,
CPU_SVE = 104,
CPU_MSA = 150,
modules/core/include/opencv2/core/hal/intrin_cpp.hpp
+20 -3
View File
@@ -81,9 +81,26 @@ CV_CPU_OPTIMIZATION_HAL_NAMESPACE_BEGIN
"Universal intrinsics" is a types and functions set intended to simplify vectorization of code on
different platforms. Currently a few different SIMD extensions on different architectures are supported.
128 bit registers of various types support is implemented for a wide range of architectures
including x86(__SSE/SSE2/SSE4.2__), ARM(__NEON__), PowerPC(__VSX__), MIPS(__MSA__).
256 bit long registers are supported on x86(__AVX2__) and 512 bit long registers are supported on x86(__AVX512__).
OpenCV Universal Intrinsics support the following instruction sets:
- *128 bit* registers of various types support is implemented for a wide range of architectures including
- x86(SSE/SSE2/SSE4.2),
- ARM(NEON): 64-bit float (64F) requires AArch64,
- PowerPC(VSX),
- MIPS(MSA),
- LoongArch(LSX),
- RISC-V(RVV 0.7.1): Fixed-length implementation,
- WASM: 64-bit float (64F) is not supported,
- *256 bit* registers are supported on
- x86(AVX2),
- LoongArch (LASX),
- *512 bit* registers are supported on
- x86(AVX512),
- *Vector Length Agnostic (VLA)* registers are supported on
- RISC-V(RVV 1.0)
- ARM(SVE/SVE2): Powered by Arm KleidiCV integration (OpenCV 4.11+),
In case when there is no SIMD extension available during compilation, fallback C++ implementation of intrinsics
will be chosen and code will work as expected although it could be slower.
modules/core/include/opencv2/core/hal/intrin_neon.hpp
+4 -3
View File
@@ -988,9 +988,10 @@ inline v_uint32x4 v_dotprod_expand_fast(const v_uint8x16& a, const v_uint8x16& b
inline v_int32x4 v_dotprod_expand_fast(const v_int8x16& a, const v_int8x16& b)
{
int16x8_t prod = vmull_s8(vget_low_s8(a.val), vget_low_s8(b.val));
prod = vmlal_s8(prod, vget_high_s8(a.val), vget_high_s8(b.val));
return v_int32x4(vaddl_s16(vget_low_s16(prod), vget_high_s16(prod)));
int16x8_t p0 = vmull_s8(vget_low_s8(a.val), vget_low_s8(b.val));
int16x8_t p1 = vmull_s8(vget_high_s8(a.val), vget_high_s8(b.val));
int32x4_t s0 = vaddl_s16(vget_low_s16(p0), vget_low_s16(p1));
return v_int32x4(vaddq_s32(s0, vaddl_s16(vget_high_s16(p0), vget_high_s16(p1))));
}
inline v_int32x4 v_dotprod_expand_fast(const v_int8x16& a, const v_int8x16& b, const v_int32x4& c)
{
modules/core/include/opencv2/core/mat.hpp
+3 -3
View File
@@ -1549,15 +1549,15 @@ public:
/** @overload
* @param cn New number of channels. If the parameter is 0, the number of channels remains the same.
* @param newndims New number of dimentions.
* @param newsz Array with new matrix size by all dimentions. If some sizes are zero,
* @param newndims New number of dimensions.
* @param newsz Array with new matrix size by all dimensions. If some sizes are zero,
* the original sizes in those dimensions are presumed.
*/
Mat reshape(int cn, int newndims, const int* newsz) const;
/** @overload
* @param cn New number of channels. If the parameter is 0, the number of channels remains the same.
* @param newshape Vector with new matrix size by all dimentions. If some sizes are zero,
* @param newshape Vector with new matrix size by all dimensions. If some sizes are zero,
* the original sizes in those dimensions are presumed.
*/
Mat reshape(int cn, const std::vector<int>& newshape) const;
modules/core/include/opencv2/core/quaternion.hpp
+3 -3
View File
@@ -57,7 +57,7 @@ class QuatEnum
public:
/** @brief Enum of Euler angles type.
*
* Without considering the possibility of using two different convertions for the definition of the rotation axes ,
* Without considering the possibility of using two different conversions for the definition of the rotation axes ,
* there exists twelve possible sequences of rotation axes, divided into two groups:
* - Proper Euler angles (Z-X-Z, X-Y-X, Y-Z-Y, Z-Y-Z, X-Z-X, Y-X-Y)
* - Tait–Bryan angles (X-Y-Z, Y-Z-X, Z-X-Y, X-Z-Y, Z-Y-X, Y-X-Z).
@@ -273,7 +273,7 @@ public:
* where \f$ q_{X, \theta_1} \f$ is created from @ref createFromXRot, \f$ q_{Y, \theta_2} \f$ is created from @ref createFromYRot,
* \f$ q_{Z, \theta_3} \f$ is created from @ref createFromZRot.
* @param angles the Euler angles in a vector of length 3
* @param eulerAnglesType the convertion Euler angles type
* @param eulerAnglesType the conversion Euler angles type
*/
static Quat<_Tp> createFromEulerAngles(const Vec<_Tp, 3> &angles, QuatEnum::EulerAnglesType eulerAnglesType);
@@ -1610,7 +1610,7 @@ public:
* EXT_ZXZ| \f$ \theta_1 = \arctan2(m_{31},m_{32}) \\\theta_2 = \arccos(m_{33}) \\\theta_3 = \arctan2(-m_{13},m_{23})\f$| \f$ \theta_1=0\\ \theta_2=0\\ \theta_3=\arctan2(m_{21},m_{22}) \f$| \f$ \theta_1= 0\\ \theta_2=\pi\\ \theta_3=\arctan2(m_{21},m_{11}) \f$
* EXT_ZYZ| \f$ \theta_1 = \arctan2(m_{32},-m_{31})\\\theta_2 = \arccos(m_{33}) \\\theta_3 = \arctan2(m_{23},m_{13}) \f$| \f$ \theta_1=0\\ \theta_2=0\\ \theta_3=\arctan2(m_{21},m_{11}) \f$| \f$ \theta_1= 0\\ \theta_2=\pi\\ \theta_3=\arctan2(m_{21},m_{11}) \f$
*
* @param eulerAnglesType the convertion Euler angles type
* @param eulerAnglesType the conversion Euler angles type
*/
Vec<_Tp, 3> toEulerAngles(QuatEnum::EulerAnglesType eulerAnglesType);