diff options
| author | Cedric Nugteren <web@cedricnugteren.nl> | 2018-05-17 20:26:53 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2018-05-17 20:26:53 +0200 |
| commit | a1335635826a31242a61cd0b888ce00a482c625f (patch) | |
| tree | 9dfef78fe0b69a04748a7b4bd5749b8189699242 /CHANGELOG | |
| parent | a65772cd3021d59ed38a2cd9753b38a0521b9528 (diff) | |
| parent | 8258321a74f5b44a559c91bb0adb1358d22da801 (diff) | |
Merge pull request #282 from CNugteren/CLBlast-276-program-release-improvements
Better cache behaviour of OpenCL programs
Diffstat (limited to 'CHANGELOG')
| -rw-r--r-- | CHANGELOG | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -7,7 +7,7 @@ Development (next version) - Added support for Intel specific subgroup shuffling extensions for faster GEMM on Intel GPUs - Re-added a local memory size constraint to the tuners - Updated and reorganised the CLBlast documentation -- Fixed an access violation when compiled with Visual Studio upon releasing the OpenCL program +- Fixed incorrect releasing of the OpenCL program resulting in segfaults / access violations - Various minor fixes and enhancements - Added tuned parameters for various devices (see doc/tuning.md) - Added non-BLAS level-1 routines: |