potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 15:23:05 +04:00
Code Packages Releases Wiki Activity

Merge pull request #24918 from opencv-pushbot:gitee/alalek/core_convertfp16_replacement

Browse Source 
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>
This commit is contained in:
Alexander Alekhin
2024-01-26 12:56:52 +03:00
committed by GitHub
parent ae21368eb9
commit 40533dbf69
9 changed files with 355 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/core/include/opencv2/core.hpp
+2
View File
@@ -556,6 +556,8 @@ The format of half precision floating point is defined in IEEE 754-2008.
@param src input array.
@param dst output array.
@deprecated Use Mat::convertTo with CV_16F instead.
*/
CV_EXPORTS_W void convertFp16(InputArray src, OutputArray dst);
modules/core/include/opencv2/core/ocl.hpp
+5
View File
@@ -127,6 +127,11 @@ public:
CV_WRAP int singleFPConfig() const;
CV_WRAP int halfFPConfig() const;
/// true if 'cl_khr_fp64' extension is available
CV_WRAP bool hasFP64() const;
/// true if 'cl_khr_fp16' extension is available
CV_WRAP bool hasFP16() const;
CV_WRAP bool endianLittle() const;
CV_WRAP bool errorCorrectionSupport() const;
modules/core/include/opencv2/core/opencl/opencl_info.hpp
+4 -4
View File
@@ -141,13 +141,13 @@ static void dumpOpenCLInformation()
DUMP_MESSAGE_STDOUT(" Max memory allocation size = " << maxMemAllocSizeStr);
DUMP_CONFIG_PROPERTY("cv_ocl_current_maxMemAllocSize", device.maxMemAllocSize());
const char* doubleSupportStr = device.doubleFPConfig() > 0 ? "Yes" : "No";
const char* doubleSupportStr = device.hasFP64() ? "Yes" : "No";
DUMP_MESSAGE_STDOUT(" Double support = " << doubleSupportStr);
DUMP_CONFIG_PROPERTY("cv_ocl_current_haveDoubleSupport", device.doubleFPConfig() > 0);
DUMP_CONFIG_PROPERTY("cv_ocl_current_haveDoubleSupport", device.hasFP64());
const char* halfSupportStr = device.halfFPConfig() > 0 ? "Yes" : "No";
const char* halfSupportStr = device.hasFP16() ? "Yes" : "No";
DUMP_MESSAGE_STDOUT(" Half support = " << halfSupportStr);
DUMP_CONFIG_PROPERTY("cv_ocl_current_haveHalfSupport", device.halfFPConfig() > 0);
DUMP_CONFIG_PROPERTY("cv_ocl_current_haveHalfSupport", device.hasFP16());
const char* isUnifiedMemoryStr = device.hostUnifiedMemory() ? "Yes" : "No";
DUMP_MESSAGE_STDOUT(" Host unified memory = " << isUnifiedMemoryStr);