summaryrefslogtreecommitdiff
path: root/include/clblast_cuda.h
AgeCommit message (Collapse)Author
2021-04-30Correct capitalization typoGard Spreemann
The CLBlastConfig.cmake file was installed to a directory named CLBLast (notice second capital l), which can cause issues for CMake's search path when looking for CLBlast on the system. This commit also fixes other occurrences of the wrong capitalization, all of it purely cosmetic (i.e. in comments).
2018-11-12Add kernel_mode option to im2col, col2im, and convgemm functionsKoichi Akabe
2018-10-23Added groundwork for col2im algorithm plus first non-working version of ↵Cedric Nugteren
kernel and test
2018-07-29Removed complex numbers support for CONVGEMMCedric Nugteren
2018-05-05Added interface of batched convolution as GEMMCedric Nugteren
2018-01-31Created the API and stubs for the HAD (hadamard-product) routinesCedric Nugteren
2018-01-11Added a RetrieveParameters function to inspect tuning parametersCedric Nugteren
2018-01-07Added API and tests for new GemmStridedBatched routineCedric Nugteren
2018-01-06Fixed the CUDA interface: replaced nullptr with 0Cedric Nugteren
2018-01-06Added CUDA interface to get temporary-buffer size for GEMM routineCedric Nugteren
2018-01-04Added a CUDA version of the GEMM temp-buffer optional argumentCedric Nugteren
2017-10-12CUDA API now takes context and device in instead of streamCedric Nugteren
2017-10-11Added first (untested) version of a CUDA APICedric Nugteren
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-30 08:54:01 +0000