NotificationsYou must be signed in to change notification settings
Fork56.4k
Star85.3k

dnn: use dispatching for Winograd optimizations#26155

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Jump to bottom

Merged

asmorkalov merged 1 commit intoopencv:4.xfrommshabunin:dnn-dispatch

Nov 14, 2024

Merged

dnn: use dispatching for Winograd optimizations#26155

asmorkalov merged 1 commit intoopencv:4.xfrommshabunin:dnn-dispatch

Nov 14, 2024

Conversation

Copy link

Contributor

mshabunin commentedSep 17, 2024•
edited
Loading

Problem:

build OpenCV with-DCPU_BASELINE= configuration option (x86_64)
build fails with missing symbols indnn module

Solution

Use standard OpenCV dispatching mechanism for Winograd function

TODO:

Remove debugging output (CV_LOG_WARNING andWinofunc::name field)
Check NEON_FP16 Winograd implementation (build with-DENABLE_FP16=ON should enableuseFP16)
~~Remove block size assertions in implementations (e.g.CV_Assert(winoIblock == 3 && ...)~~
Use single namespace in.simd.hpp file

mshabunin force-pushed thednn-dispatch branch fromad655e3 to3cf6487Compare

September 17, 2024 13:28

asmorkalov added optimization category: dnn labels

Sep 23, 2024

asmorkalov self-requested a review

October 25, 2024 06:59

asmorkalov self-assigned this

Oct 25, 2024

asmorkalov added this to the4.11.0 milestone

Oct 25, 2024

Copy link

Contributor

asmorkalov commentedOct 25, 2024

Dispatch works with jetson orin. Please go ahead and clean-up the debug logs.

mshabunin force-pushed thednn-dispatch branch 2 times, most recently from59b6ef2 to0db738cCompare

October 25, 2024 17:15

mshabunin force-pushed thednn-dispatch branch from0db738c toe93a7c0Compare

November 5, 2024 13:19

Copy link

Contributor

asmorkalov commentedNov 6, 2024

I tried ARMv7 withcmake -DCPU_BASELINE= -DCPU_DISPATCH=NEON ../opencv and got build error:

[ 38%] Building CXX object modules/highgui/CMakeFiles/opencv_highgui.dir/src/backend.cpp.o/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp: In function ‘cv::dnn::Winofunc cv::dnn::getWinofunc_F32()’:/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp:14:50: error: ‘getWinofunc_F32’ is not a member of ‘cv::dnn::opt_NEON’     CV_CPU_DISPATCH(getWinofunc_F32, (), CV_CPU_DISPATCH_MODES_ALL);                                                  ^/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp:14:50: note: suggested alternatives:/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp:12:19: note:   ‘cv::dnn::getWinofunc_F32’ cv::dnn::Winofunc getWinofunc_F32()                   ^In file included from /mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp:6:0:/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.simd.hpp:1342:19: note:   ‘cv::cpu_baseline::getWinofunc_F32’ cv::dnn::Winofunc getWinofunc_F32()                   ^In file included from /mnt/disk/opencv/modules/core/include/opencv2/core/private/cv_cpu_include_simd_declarations.hpp:26:0,                 from /mnt/disk/opencv-build/modules/dnn/layers/cpu_kernels/conv_winograd_f63.simd_declarations.hpp:3,                 from /mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp:7:/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.simd.hpp:13:19: note:   ‘cv::opt_NEON::getWinofunc_F32’ cv::dnn::Winofunc getWinofunc_F32();                   ^/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp: In function ‘cv::dnn::Winofunc cv::dnn::getWinofunc_F16()’:/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp:19:50: error: ‘getWinofunc_F16’ is not a member of ‘cv::dnn::opt_NEON’     CV_CPU_DISPATCH(getWinofunc_F16, (), CV_CPU_DISPATCH_MODES_ALL);                                                  ^/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp:19:50: note: suggested alternatives:/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp:17:19: note:   ‘cv::dnn::getWinofunc_F16’ cv::dnn::Winofunc getWinofunc_F16()                   ^In file included from /mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp:6:0:/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.simd.hpp:1851:19: note:   ‘cv::cpu_baseline::getWinofunc_F16’ cv::dnn::Winofunc getWinofunc_F16()                   ^In file included from /mnt/disk/opencv/modules/core/include/opencv2/core/private/cv_cpu_include_simd_declarations.hpp:26:0,                 from /mnt/disk/opencv-build/modules/dnn/layers/cpu_kernels/conv_winograd_f63.simd_declarations.hpp:3,                 from /mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp:7:/mnt/disk/opencv/modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.simd.hpp:14:19: note:   ‘cv::opt_NEON::getWinofunc_F16’ cv::dnn::Winofunc getWinofunc_F16();                   ^modules/dnn/CMakeFiles/opencv_dnn.dir/build.make:718: recipe for target 'modules/dnn/CMakeFiles/opencv_dnn.dir/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp.o' failedmake[2]: *** [modules/dnn/CMakeFiles/opencv_dnn.dir/src/layers/cpu_kernels/conv_winograd_f63.dispatch.cpp.o] Error 1make[2]: *** Waiting for unfinished jobs....[ 39%] Building CXX object modules/highgui/CMakeFiles/opencv_highgui.dir/src/window.cpp.o