Rewrite SIMD code by using new Universal Intrinsic API : an example. by hanliutong · Pull Request #23885 · opencv/opencv

hanliutong · 2023-06-28T10:15:41Z

We introduced scalable RVV as a new Universal Intrinsic backend last summer and also introduced some changing of the Universal Intrinsic API: #22179. In order to make the current SIMD vectorized loops availableto the scalable backend, we need to rewrite the code already written by Universal Intrinsic.

Since there are ~400 SIMD code blocks in ~50 files written by Universal Intinsic., thousands of lines of code need to be rewritten, which will be a huge work if done manually. Then I am developing a (semi-)automated rewriter/refactor based on clang-tidy, that can convert the convert existing code to the new API. The rewriter can already handle about 80% of the cases, and some corner cases are still under development. The link to the rewriter: https://github.com/hanliutong/rewriter

This patch is automatically generated by using the rewriter(except adding the macro CV_SIMD_SCALABLE). After building the rewriter (refer to usage in the readme), use the following command to process modules/core/src/mean.simd.hpp

clang-tidy --load ./libocv_intrinsic_tidy.so \
'--checks=-*,nlanes-check,operator-check,get0-check,lanetype-check' \
-p <path to>/opencv/build/ \
<path to>/opencv/modules/core/src/mean.simd.hpp \
-fix
# Execute the above command twice, in case some operators are not detected in the first time.

the clang-tidy will identify the statement that needs to be rewritten and use the new API to give suggestions for modification (the term FIX IT HINT in clang-tidy), such as:

This is a nlanes in vector wrapper class used as loop step, need to be replaced with VTraits member vlanes.

mean.simd.hpp:152:42: warning: Found nlanes. [nlanes-check]
            for (int i = 0; i < v_int32::nlanes; ++i)
                                ~~~~~~~~~^~~~~~
                                VTraits<v_int32>::vlanes()

This is also a nlanes in vector wrapper class but is used as array length declaration, which must be a compile-time constant.
Then nlanes need to be replaced with VTraits member max_nlanes.

mean.simd.hpp:149:64: warning: Found nlanes as constant. [nlanes-check]
            int CV_DECL_ALIGNED(CV_SIMD_WIDTH) ar[2 * v_int32::nlanes];
                                                      ~~~~~~~~~^~~~~~
                                                      VTraits<v_int32>::max_nlanes

The overloaded operators are no longer supported in the scalable Universal Intrinsic API, use v_op instead.

mean.simd.hpp:134:19: warning: Found operator. [operator-check]
            v_sum += v_tmp0;
            ~~~~~~^~~~~~~~~
            v_sum = v_add(v_sum, v_tmp0)

The rewriter also supports other cases that do not using in this file. Please refer to the capability part in readme or the examples

Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

I agree to contribute to the project under Apache 2 License.
To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
The PR is proposed to the proper branch
There is a reference to the original bug report and related work
There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
The feature is well documented and sample code can be built with the project CMake

force_builders=Custom
build_image:Custom=riscv-clang-rvv
Xbuild_image:Custom=riscv-clang-rvv-128
Xbuild_image:Custom=riscv-gcc-rvv-07
test_modules:Custom=core,imgproc,dnn
buildworker:Custom=linux-4
test_timeout:Custom=600
build_contrib:Custom=OFF

@brief

Rewrite Universal Intrinsic code by using new API: Core module. opencv#23980 The goal of this PR is to match and modify all SIMD code blocks guarded by `CV_SIMD` macro in the `opencv/modules/core` folder and rewrite them by using the new Universal Intrinsic API. The patch is almost auto-generated by using the [rewriter](https://github.com/hanliutong/rewriter), related PR opencv#23885. Most of the files have been rewritten, but I marked this PR as draft because, the `CV_SIMD` macro also exists in the following files, and the reasons why they are not rewrited are: 1. ~~code design for fixed-size SIMD (v_int16x8, v_float32x4, etc.), need to manually rewrite.~~ Rewrited - ./modules/core/src/stat.simd.hpp - ./modules/core/src/matrix_transform.cpp - ./modules/core/src/matmul.simd.hpp 2. Vector types are wrapped in other class/struct, that are not supported by the compiler in variable-length backends. Can not be rewrited directly. - ./modules/core/src/mathfuncs_core.simd.hpp ```cpp struct v_atan_f32 { explicit v_atan_f32(const float& scale) { ... } v_float32 compute(const v_float32& y, const v_float32& x) { ... } ... v_float32 val90; // sizeless type can not used in a class v_float32 val180; v_float32 val360; v_float32 s; }; ``` 3. The API interface does not support/does not match - ./modules/core/src/norm.cpp Use `v_popcount`, ~~waiting for opencv#23966~~ Fixed - ./modules/core/src/has_non_zero.simd.hpp Use illegal Universal Intrinsic API: For float type, there is no logical operation `|`. Further discussion needed ```cpp /** @brief Bitwise OR Only for integer types. */ template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator|(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b); template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n>& operator|=(v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b); ``` ```cpp #if CV_SIMD typedef v_float32 v_type; const v_type v_zero = vx_setzero_f32(); constexpr const int unrollCount = 8; int step = v_type::nlanes * unrollCount; int len0 = len & -step; const float* srcSimdEnd = src+len0; int countSIMD = static_cast<int>((srcSimdEnd-src)/step); while(!res && countSIMD--) { v_type v0 = vx_load(src); src += v_type::nlanes; v_type v1 = vx_load(src); src += v_type::nlanes; .... src += v_type::nlanes; v0 |= v1; //Illegal ? .... //res = v_check_any(((v0 | v4) != v_zero));//beware : (NaN != 0) returns "false" since != is mapped to _CMP_NEQ_OQ and not _CMP_NEQ_UQ res = !v_check_all(((v0 | v4) == v_zero)); } v_cleanup(); #endif ``` ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [ ] I agree to contribute to the project under Apache 2 License. - [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake

Rewrite Universal Intrinsic code by using new API: ImgProc module. #24058 The goal of this series of PRs is to modify the SIMD code blocks guarded by CV_SIMD macro in the `opencv/modules/imgproc` folder: rewrite them by using the new Universal Intrinsic API. For easier review, this PR includes a part of the rewritten code, and another part will be brought in the next PR (coming soon). I tested this patch on RVV (QEMU) and AVX devices, `opencv_test_imgproc` is passed. The patch is partially auto-generated by using the [rewriter](https://github.com/hanliutong/rewriter), related PR #23885 and #23980. ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [ ] I agree to contribute to the project under Apache 2 License. - [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake

Rewrite Universal Intrinsic code: float related part #24325 The goal of this series of PRs is to modify the SIMD code blocks guarded by CV_SIMD macro: rewrite them by using the new Universal Intrinsic API. The series of PRs is listed below: #23885 First patch, an example #23980 Core module #24058 ImgProc module, part 1 #24132 ImgProc module, part 2 #24166 ImgProc module, part 3 #24301 Features2d and calib3d module #24324 Gapi module This patch (hopefully) is the last one in the series. This patch mainly involves 3 parts 1. Add some modifications related to float (CV_SIMD_64F) 2. Use `#if (CV_SIMD || CV_SIMD_SCALABLE)` instead of `#if CV_SIMD || CV_SIMD_SCALABLE`, then we can get the `CV_SIMD` module that is not enabled for `CV_SIMD_SCALABLE` by looking for `if CV_SIMD` 3. Summary of `CV_SIMD` blocks that remains unmodified: Updated comments - Some blocks will cause test fail when enable for RVV, marked as `TODO: enable for CV_SIMD_SCALABLE, ....` - Some blocks can not be rewrited directly. (Not commented in the source code, just listed here) - ./modules/core/src/mathfuncs_core.simd.hpp (Vector type wrapped in class/struct) - ./modules/imgproc/src/color_lab.cpp (Array of vector type) - ./modules/imgproc/src/color_rgb.simd.hpp (Array of vector type) - ./modules/imgproc/src/sumpixels.simd.hpp (fixed length algorithm, strongly ralated with `CV_SIMD_WIDTH`) These algorithms will need to be redesigned to accommodate scalable backends. ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [ ] I agree to contribute to the project under Apache 2 License. - [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake

Rewrite Universal Intrinsic code: float related part opencv#24325 The goal of this series of PRs is to modify the SIMD code blocks guarded by CV_SIMD macro: rewrite them by using the new Universal Intrinsic API. The series of PRs is listed below: opencv#23885 First patch, an example opencv#23980 Core module opencv#24058 ImgProc module, part 1 opencv#24132 ImgProc module, part 2 opencv#24166 ImgProc module, part 3 opencv#24301 Features2d and calib3d module opencv#24324 Gapi module This patch (hopefully) is the last one in the series. This patch mainly involves 3 parts 1. Add some modifications related to float (CV_SIMD_64F) 2. Use `#if (CV_SIMD || CV_SIMD_SCALABLE)` instead of `#if CV_SIMD || CV_SIMD_SCALABLE`, then we can get the `CV_SIMD` module that is not enabled for `CV_SIMD_SCALABLE` by looking for `if CV_SIMD` 3. Summary of `CV_SIMD` blocks that remains unmodified: Updated comments - Some blocks will cause test fail when enable for RVV, marked as `TODO: enable for CV_SIMD_SCALABLE, ....` - Some blocks can not be rewrited directly. (Not commented in the source code, just listed here) - ./modules/core/src/mathfuncs_core.simd.hpp (Vector type wrapped in class/struct) - ./modules/imgproc/src/color_lab.cpp (Array of vector type) - ./modules/imgproc/src/color_rgb.simd.hpp (Array of vector type) - ./modules/imgproc/src/sumpixels.simd.hpp (fixed length algorithm, strongly ralated with `CV_SIMD_WIDTH`) These algorithms will need to be redesigned to accommodate scalable backends. ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [ ] I agree to contribute to the project under Apache 2 License. - [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake

@brief

Rewrite Universal Intrinsic code by using new API: Core module. opencv#23980 The goal of this PR is to match and modify all SIMD code blocks guarded by `CV_SIMD` macro in the `opencv/modules/core` folder and rewrite them by using the new Universal Intrinsic API. The patch is almost auto-generated by using the [rewriter](https://github.com/hanliutong/rewriter), related PR opencv#23885. Most of the files have been rewritten, but I marked this PR as draft because, the `CV_SIMD` macro also exists in the following files, and the reasons why they are not rewrited are: 1. ~~code design for fixed-size SIMD (v_int16x8, v_float32x4, etc.), need to manually rewrite.~~ Rewrited - ./modules/core/src/stat.simd.hpp - ./modules/core/src/matrix_transform.cpp - ./modules/core/src/matmul.simd.hpp 2. Vector types are wrapped in other class/struct, that are not supported by the compiler in variable-length backends. Can not be rewrited directly. - ./modules/core/src/mathfuncs_core.simd.hpp ```cpp struct v_atan_f32 { explicit v_atan_f32(const float& scale) { ... } v_float32 compute(const v_float32& y, const v_float32& x) { ... } ... v_float32 val90; // sizeless type can not used in a class v_float32 val180; v_float32 val360; v_float32 s; }; ``` 3. The API interface does not support/does not match - ./modules/core/src/norm.cpp Use `v_popcount`, ~~waiting for opencv#23966~~ Fixed - ./modules/core/src/has_non_zero.simd.hpp Use illegal Universal Intrinsic API: For float type, there is no logical operation `|`. Further discussion needed ```cpp /** @brief Bitwise OR Only for integer types. */ template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator|(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b); template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n>& operator|=(v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b); ``` ```cpp #if CV_SIMD typedef v_float32 v_type; const v_type v_zero = vx_setzero_f32(); constexpr const int unrollCount = 8; int step = v_type::nlanes * unrollCount; int len0 = len & -step; const float* srcSimdEnd = src+len0; int countSIMD = static_cast<int>((srcSimdEnd-src)/step); while(!res && countSIMD--) { v_type v0 = vx_load(src); src += v_type::nlanes; v_type v1 = vx_load(src); src += v_type::nlanes; .... src += v_type::nlanes; v0 |= v1; //Illegal ? .... //res = v_check_any(((v0 | v4) != v_zero));//beware : (NaN != 0) returns "false" since != is mapped to _CMP_NEQ_OQ and not _CMP_NEQ_UQ res = !v_check_all(((v0 | v4) == v_zero)); } v_cleanup(); #endif ``` ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [ ] I agree to contribute to the project under Apache 2 License. - [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake

Rewrite Universal Intrinsic code by using new API: ImgProc module. opencv#24058 The goal of this series of PRs is to modify the SIMD code blocks guarded by CV_SIMD macro in the `opencv/modules/imgproc` folder: rewrite them by using the new Universal Intrinsic API. For easier review, this PR includes a part of the rewritten code, and another part will be brought in the next PR (coming soon). I tested this patch on RVV (QEMU) and AVX devices, `opencv_test_imgproc` is passed. The patch is partially auto-generated by using the [rewriter](https://github.com/hanliutong/rewriter), related PR opencv#23885 and opencv#23980. ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [ ] I agree to contribute to the project under Apache 2 License. - [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake

Rewrite Universal Intrinsic code: float related part opencv#24325 The goal of this series of PRs is to modify the SIMD code blocks guarded by CV_SIMD macro: rewrite them by using the new Universal Intrinsic API. The series of PRs is listed below: opencv#23885 First patch, an example opencv#23980 Core module opencv#24058 ImgProc module, part 1 opencv#24132 ImgProc module, part 2 opencv#24166 ImgProc module, part 3 opencv#24301 Features2d and calib3d module opencv#24324 Gapi module This patch (hopefully) is the last one in the series. This patch mainly involves 3 parts 1. Add some modifications related to float (CV_SIMD_64F) 2. Use `#if (CV_SIMD || CV_SIMD_SCALABLE)` instead of `#if CV_SIMD || CV_SIMD_SCALABLE`, then we can get the `CV_SIMD` module that is not enabled for `CV_SIMD_SCALABLE` by looking for `if CV_SIMD` 3. Summary of `CV_SIMD` blocks that remains unmodified: Updated comments - Some blocks will cause test fail when enable for RVV, marked as `TODO: enable for CV_SIMD_SCALABLE, ....` - Some blocks can not be rewrited directly. (Not commented in the source code, just listed here) - ./modules/core/src/mathfuncs_core.simd.hpp (Vector type wrapped in class/struct) - ./modules/imgproc/src/color_lab.cpp (Array of vector type) - ./modules/imgproc/src/color_rgb.simd.hpp (Array of vector type) - ./modules/imgproc/src/sumpixels.simd.hpp (fixed length algorithm, strongly ralated with `CV_SIMD_WIDTH`) These algorithms will need to be redesigned to accommodate scalable backends. ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [ ] I agree to contribute to the project under Apache 2 License. - [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake

@brief

Rewrite Universal Intrinsic code by using new API: Core module. opencv#23980 The goal of this PR is to match and modify all SIMD code blocks guarded by `CV_SIMD` macro in the `opencv/modules/core` folder and rewrite them by using the new Universal Intrinsic API. The patch is almost auto-generated by using the [rewriter](https://github.com/hanliutong/rewriter), related PR opencv#23885. Most of the files have been rewritten, but I marked this PR as draft because, the `CV_SIMD` macro also exists in the following files, and the reasons why they are not rewrited are: 1. ~~code design for fixed-size SIMD (v_int16x8, v_float32x4, etc.), need to manually rewrite.~~ Rewrited - ./modules/core/src/stat.simd.hpp - ./modules/core/src/matrix_transform.cpp - ./modules/core/src/matmul.simd.hpp 2. Vector types are wrapped in other class/struct, that are not supported by the compiler in variable-length backends. Can not be rewrited directly. - ./modules/core/src/mathfuncs_core.simd.hpp ```cpp struct v_atan_f32 { explicit v_atan_f32(const float& scale) { ... } v_float32 compute(const v_float32& y, const v_float32& x) { ... } ... v_float32 val90; // sizeless type can not used in a class v_float32 val180; v_float32 val360; v_float32 s; }; ``` 3. The API interface does not support/does not match - ./modules/core/src/norm.cpp Use `v_popcount`, ~~waiting for opencv#23966~~ Fixed - ./modules/core/src/has_non_zero.simd.hpp Use illegal Universal Intrinsic API: For float type, there is no logical operation `|`. Further discussion needed ```cpp /** @brief Bitwise OR Only for integer types. */ template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n> operator|(const v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b); template<typename _Tp, int n> CV_INLINE v_reg<_Tp, n>& operator|=(v_reg<_Tp, n>& a, const v_reg<_Tp, n>& b); ``` ```cpp #if CV_SIMD typedef v_float32 v_type; const v_type v_zero = vx_setzero_f32(); constexpr const int unrollCount = 8; int step = v_type::nlanes * unrollCount; int len0 = len & -step; const float* srcSimdEnd = src+len0; int countSIMD = static_cast<int>((srcSimdEnd-src)/step); while(!res && countSIMD--) { v_type v0 = vx_load(src); src += v_type::nlanes; v_type v1 = vx_load(src); src += v_type::nlanes; .... src += v_type::nlanes; v0 |= v1; //Illegal ? .... //res = v_check_any(((v0 | v4) != v_zero));//beware : (NaN != 0) returns "false" since != is mapped to _CMP_NEQ_OQ and not _CMP_NEQ_UQ res = !v_check_all(((v0 | v4) == v_zero)); } v_cleanup(); #endif ``` ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [ ] I agree to contribute to the project under Apache 2 License. - [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake

Rewrite Universal Intrinsic code by using new API: ImgProc module. opencv#24058 The goal of this series of PRs is to modify the SIMD code blocks guarded by CV_SIMD macro in the `opencv/modules/imgproc` folder: rewrite them by using the new Universal Intrinsic API. For easier review, this PR includes a part of the rewritten code, and another part will be brought in the next PR (coming soon). I tested this patch on RVV (QEMU) and AVX devices, `opencv_test_imgproc` is passed. The patch is partially auto-generated by using the [rewriter](https://github.com/hanliutong/rewriter), related PR opencv#23885 and opencv#23980. ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [ ] I agree to contribute to the project under Apache 2 License. - [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake

Rewrite Universal Intrinsic code: float related part opencv#24325 The goal of this series of PRs is to modify the SIMD code blocks guarded by CV_SIMD macro: rewrite them by using the new Universal Intrinsic API. The series of PRs is listed below: opencv#23885 First patch, an example opencv#23980 Core module opencv#24058 ImgProc module, part 1 opencv#24132 ImgProc module, part 2 opencv#24166 ImgProc module, part 3 opencv#24301 Features2d and calib3d module opencv#24324 Gapi module This patch (hopefully) is the last one in the series. This patch mainly involves 3 parts 1. Add some modifications related to float (CV_SIMD_64F) 2. Use `#if (CV_SIMD || CV_SIMD_SCALABLE)` instead of `#if CV_SIMD || CV_SIMD_SCALABLE`, then we can get the `CV_SIMD` module that is not enabled for `CV_SIMD_SCALABLE` by looking for `if CV_SIMD` 3. Summary of `CV_SIMD` blocks that remains unmodified: Updated comments - Some blocks will cause test fail when enable for RVV, marked as `TODO: enable for CV_SIMD_SCALABLE, ....` - Some blocks can not be rewrited directly. (Not commented in the source code, just listed here) - ./modules/core/src/mathfuncs_core.simd.hpp (Vector type wrapped in class/struct) - ./modules/imgproc/src/color_lab.cpp (Array of vector type) - ./modules/imgproc/src/color_rgb.simd.hpp (Array of vector type) - ./modules/imgproc/src/sumpixels.simd.hpp (fixed length algorithm, strongly ralated with `CV_SIMD_WIDTH`) These algorithms will need to be redesigned to accommodate scalable backends. ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [ ] I agree to contribute to the project under Apache 2 License. - [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [ ] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake

Rewrite SIMD code by using new Universal Intrinsic API.

d175070

hanliutong changed the title ~~Rewrite SIMD code by using new Universal Intrinsic API : a sample example.~~ Rewrite SIMD code by using new Universal Intrinsic API : an example. Jun 28, 2023

asmorkalov added this to the 4.9.0 milestone Jun 28, 2023

asmorkalov added optimization platform: riscv labels Jun 28, 2023

asmorkalov requested a review from mshabunin June 29, 2023 15:22

mshabunin approved these changes Jul 3, 2023

View reviewed changes

opencv-alalek assigned mshabunin Jul 3, 2023

opencv-pushbot merged commit 67faf16 into opencv:4.x Jul 3, 2023

hanliutong deleted the UniversalIntrinsicRewriter branch July 4, 2023 02:04

hanliutong mentioned this pull request Jul 12, 2023

Rewrite Universal Intrinsic code by using new API: Core module. #23980

Merged

6 tasks

hanliutong mentioned this pull request Jul 26, 2023

Rewrite Universal Intrinsic code by using new API: ImgProc module. #24058

Merged

6 tasks

asmorkalov mentioned this pull request Jul 27, 2023

(5.x) Merge 4.x #24070

Merged

hanliutong mentioned this pull request Sep 27, 2023

Rewrite Universal Intrinsic code: float related part #24325

Merged

6 tasks

s-trinh mentioned this pull request Jan 16, 2024

visp failing to build on opencv 4.9.0 lagadic/visp#1309

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Rewrite SIMD code by using new Universal Intrinsic API : an example.#23885

Rewrite SIMD code by using new Universal Intrinsic API : an example.#23885
opencv-pushbot merged 1 commit intoopencv:4.xfrom
hanliutong:UniversalIntrinsicRewriter

hanliutong commented Jun 28, 2023 •

edited by opencv-alalek

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Uh oh!

Conversation

hanliutong commented Jun 28, 2023 • edited by opencv-alalek Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Pull Request Readiness Checklist

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

hanliutong commented Jun 28, 2023 •

edited by opencv-alalek

Loading