This repository was archived by the owner on Apr 23, 2024. It is now read-only.
a #1
Open
a #1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
merge develop branch into master branch
minor bug fix in client code
do not build bingen if offline compilation is disabled
fix travis CI build
…tra barrier at the beginning of the outer loop.
improve big sgemm column NN perf. improve small sgemm NN perf.
bump develop version to 2.5
improve small sgemm column major TN on Hawaii
fix a very silly bug in compuing s/dtrsm flops.
Ben : fixing bonaire path for sgemm using CL2.0 path
some typo fixes
Fix install location of samples
Install scripts/perf to share/clBLAS on non WIN32 systems
Changing unit tests to only print test parameters on unit test failures.
test-functional and test-correctness with derivatives have been enhanced to be able to specify the device under test through the command line. The ordinals can be queried with clinfo program Externally available, comes in AMD SDK --platform-ord is an unsigned value picking the platform --device-ord is an unsigned value picking the device --device has been renamed to --device-type
Unit test improvements
Make installing source tree optional
The library was not developed with the pedantic warning flag enabled, and the build outputs a volume of verbose warning messages on every build. It's not currently helpful to have this enabled. This flag should be enabled again as the warnings get fixed, to enable a more robust library. Various warnings and #pragmas fixed that were remaining. Changed the allocation of a temp buffer in corr-trmv.cpp
Changing default for 'keeping kernel sources' to ON to fix unit test failures on CPU devices
Fix issue affecting AMD & Intel CPU devices; lower warnings :shipit:
Support for altivec on powerpc64 P8 systems :shipit: Thank you for your contribution
…b cblas through client (#274) * (1)update readme: netlib is preferred.(2)now you can verify the correctness of gemm&trmm through client * give more details of how to get CBLAS on windows * find the netlib library dir & library in Cmake files * forget to add this file * disable the validation on windows currently: no easy solution of building/linking netlib CBLAS on windows
Disable clang error on narrowing conversions. 👍
Point the CONTRIBUTING wiki links to the correct repository
add missing dependency to pthread (using rwlock functions)
ixamax and syr2/her2 bugs
.s is more portable, and .x does not work with -std=c99 which does not have anonymous structs. Fix #307.
This increases the chance that they will just work for most users. Previously there was a mixture of CPU and GPU, which only works if users have both CPU and GPU OpenCL devices.
Use CL_DEVICE_TYPE_ALL for all samples
Revert "Use CL_DEVICE_TYPE_ALL for all samples"
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.