generic-library/opencv
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Change kernel for optimization. Remove restriction to align data

Browse Source 
Fix kernel compilation errors on AMD system

Fix licanse information in cl file

Support CV_64F destination type

Change build options of the kernel

Optimize sum of square

Remove separate kernel for integral square

Increase epsilon for perfomance tests

Increase epsilon for perfomance tests

Test double support on AMD devices

Fix some issues

Try to fix problems with AMD device

Try to solve problem with AMD device

Fix error of destination size in kernel

Fix warnings
This commit is contained in:
vbystricky
2014-06-19 14:39:49 +04:00
parent 01a98fae93
commit 09bcc061dd
4 changed files with 199 additions and 825 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
modules/imgproc/perf/opencl/perf_imgproc.cpp
View File

@@ -231,7 +231,7 @@ OCL_PERF_TEST_P(IntegralFixture, Integral1, ::testing::Combine(OCL_TEST_SIZES, O
OCL_TEST_CYCLE() cv::integral(src, dst, ddepth);
SANITY_CHECK(dst, 1e-6, ERROR_RELATIVE);
SANITY_CHECK(dst, 2e-6, ERROR_RELATIVE);
}
OCL_PERF_TEST_P(IntegralFixture, Integral2, ::testing::Combine(OCL_TEST_SIZES, OCL_PERF_ENUM(CV_32S, CV_32F)))
@@ -243,11 +243,11 @@ OCL_PERF_TEST_P(IntegralFixture, Integral2, ::testing::Combine(OCL_TEST_SIZES, O
checkDeviceMaxMemoryAllocSize(srcSize, ddepth);
UMat src(srcSize, CV_8UC1), sum(srcSize + Size(1, 1), ddepth), sqsum(srcSize + Size(1, 1), CV_32F);
declare.in(src, WARMUP_RNG).out(sum).out(sqsum);
declare.in(src, WARMUP_RNG).out(sum, sqsum);
OCL_TEST_CYCLE() cv::integral(src, sum, sqsum, ddepth, CV_32F);
SANITY_CHECK(sum, 1e-6, ERROR_RELATIVE);
SANITY_CHECK(sum, 2e-4, ERROR_RELATIVE);
SANITY_CHECK(sqsum, 5e-5, ERROR_RELATIVE);
}