potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-26 05:43:05 +04:00
Code Packages Releases Wiki Activity
35,906 Commits 8 Branches 132 Tags
4.13.0-python
Commit Graph

10 Commits

Author SHA1 Message Date
Alexander Alekhin 40533dbf69 Merge pull request #24918 from opencv-pushbot:gitee/alalek/core_convertfp16_replacement 
core(OpenCL): optimize convertTo() with CV_16F (convertFp16() replacement) #24918

relates #24909
relates #24917
relates #24892

Performance changes:

- [x] 12700K (1 thread) + Intel iGPU

|Name of Test|noOCL|convertFp16|convertTo BASE|convertTo PATCH|
|---|:-:|:-:|:-:|:-:|
|ConvertFP16FP32MatMat::OCL_Core|3.130|3.152|3.127|3.136|
|ConvertFP16FP32MatUMat::OCL_Core|3.030|3.996|3.007|2.671|
|ConvertFP16FP32UMatMat::OCL_Core|3.010|3.101|3.056|2.854|
|ConvertFP16FP32UMatUMat::OCL_Core|3.016|3.298|2.072|2.061|
|ConvertFP32FP16MatMat::OCL_Core|2.697|2.652|2.723|2.721|
|ConvertFP32FP16MatUMat::OCL_Core|2.752|4.268|2.662|2.947|
|ConvertFP32FP16UMatMat::OCL_Core|2.706|2.601|2.603|2.528|
|ConvertFP32FP16UMatUMat::OCL_Core|2.704|3.215|1.999|1.988|

Patched version is not worse than convertFp16 and convertTo baseline (except MatUMat 32->16, baseline uses CPU code+dst buffer map).
There are still gaps against noOpenCL(CPU only) mode due to T-API implementation issues (unnecessary synchronization).


- [x] 12700K + AMD dGPU

|Name of Test|noOCL|convertFp16 dGPU|convertTo BASE dGPU|convertTo PATCH dGPU|
|---|:-:|:-:|:-:|:-:|
|ConvertFP16FP32MatMat::OCL_Core|3.130|3.133|3.172|3.087|
|ConvertFP16FP32MatUMat::OCL_Core|3.030|1.713|9.559|1.729|
|ConvertFP16FP32UMatMat::OCL_Core|3.010|6.515|6.309|4.452|
|ConvertFP16FP32UMatUMat::OCL_Core|3.016|0.242|23.597|0.170|
|ConvertFP32FP16MatMat::OCL_Core|2.697|2.641|2.713|2.689|
|ConvertFP32FP16MatUMat::OCL_Core|2.752|4.076|6.483|4.191|
|ConvertFP32FP16UMatMat::OCL_Core|2.706|9.042|16.481|1.834|
|ConvertFP32FP16UMatUMat::OCL_Core|2.704|0.229|15.730|0.176|

convertTo-baseline can't compile OpenCL kernel for FP16 properly - FIXED.
dGPU has much more power, so results are x16-17 better than single cpu core. 
Patched version is not worse than convertFp16 and convertTo baseline.
There are still gaps against noOpenCL(CPU only) mode due to T-API implementation issues (unnecessary synchronization) and required memory transfers.

Co-authored-by: Alexander Alekhin <alexander.a.alekhin@gmail.com>
 2024-01-26 12:56:52 +03:00
Kumataro 602caa9cd6 Merge pull request #21937 from Kumataro:4.x-fix-21911 
* Fix warnings for clang15

* Fix warnings: Remove unnecessary code

* Fix warnings: Remove unnecessary code
 2022-05-13 17:32:05 +00:00
Alexander Alekhin 54063c40de core(ocl): options to control buffer access flags 
- control using of clEnqueueMapBuffer or clEnqueueReadBuffer[Rect]
- added benchmarks with OpenCL buffer access use cases
 2020-04-02 11:11:06 +00:00
Alexander Alekhin 4a297a2443 ts: refactor OpenCV tests 
- removed tr1 usage (dropped in C++17)
- moved includes of vector/map/iostream/limits into ts.hpp
- require opencv_test + anonymous namespace (added compile check)
- fixed norm() usage (must be from cvtest::norm for checks) and other conflict functions
- added missing license headers
 2018-02-03 19:39:47 +00:00
Pavel Vlasov 35c7216846 IPP for OpenCV 2017u2 initial enabling patch; 2017-04-20 20:26:30 +03:00
Alexander Alekhin 55188fe991 world fix 2014-08-05 20:12:35 +04:00
Ilya Lavrenov c949845a6b fixed perf test 2014-07-10 16:03:31 +04:00
Ilya Lavrenov 80470f9cf6 added performance test 2014-05-30 18:34:04 +04:00
Ilya Lavrenov 9cc80a68db fixed warnings 2014-04-21 13:14:55 +04:00
Ilya Lavrenov 68957b2757 added some new performance tests 2014-03-02 10:29:50 +04:00