summaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Collapse)Author
2018-07-29Removed complex numbers support for CONVGEMMCedric Nugteren
2018-07-29Merge branch 'master' into CLBlast-267-convgemmCedric Nugteren
2018-07-28Disabled the use of staggered indices on AMD GPUs for the new GEMMK == 1 ↵Cedric Nugteren
kernels to improve performance
2018-07-27Fixed an issue with AMD GPUs and the new GEMMK == 1 kernelCedric Nugteren
2018-07-25Added code to report the average tuning resultsCedric Nugteren
2018-07-23Merge pull request #297 from tyler-utah/masterCedric Nugteren
inline PTX to support subgroup shuffle for Nvidia GPUs
2018-07-16moved a two-line macro to a single lineTyler Sorensen
2018-07-14forgot to add test cases back in, oopsTyler Sorensen
2018-07-14Applied feedback from Cedric from first pull requestTyler Sorensen
2018-07-13Added tuning results for Intel i5-4970SCedric Nugteren
2018-07-13Added device-name removal code to handle POCL naming conventionCedric Nugteren
2018-07-13Added tuning results for GeForce GTX 1070 TiCedric Nugteren
2018-07-13Added tuning results for HD Graphics 6000 Broadwell GT3Cedric Nugteren
2018-07-11restored some of the changed tuning files for xgemmTyler Sorensen
2018-07-11added inline ptx to support shuffle on Nvidia GPUsTyler Sorensen
2018-07-06Eliminate a temporary Program objectAlastair Murray
This was causing a crash for me because the temporary Program destructor called clReleaseProgram on the cl_program with Program, and then clBuildProgram was called on the same cl_program (belonging to the Program owned by the shared_ptr, but it's the same cl_program).
2018-06-28Disabled calls to clReleaseProgram under Windows to avoid segfaults when the ↵Cedric Nugteren
OpenCL driver unloads first
2018-06-03Merge branch 'master' into CLBlast-267-convgemmCedric Nugteren
2018-06-03Fixes for CUDA version of CLBlastCedric Nugteren
2018-06-01Fixes for Apple OpenCL CPU implementation which requires a LWGS of 1 when ↵Cedric Nugteren
barriers are present
2018-05-31Added error-checking for half-empty local work group sizes; fixed a minor ↵Cedric Nugteren
TRSV global worksize issue
2018-05-31Some potential fixes for error -54 when launching TRSV and TRSM kernelsCedric Nugteren
2018-05-30Widened Apple OpenCL check, added way to debug too-large-workgroups issueCedric Nugteren
2018-05-29Added Apple OpenCL TRSV block size override; removed failing old Intel GPU ↵Cedric Nugteren
test from README
2018-05-27Merge pull request #287 from CNugteren/apple-opencl-limitations-fixesCedric Nugteren
Apple opencl limitations for TRSV/TRSM now return not-implemented status
2018-05-27Added a check to return 'NotImplemented' error code in case of systems with ↵Cedric Nugteren
< 16 LWGS for TSRV and TRSM
2018-05-27Made FillMatrix and FillVector functions take a configurable local workgroup ↵Cedric Nugteren
size
2018-05-23Added an option in the clients to output timing statistics: minimum, mean, ↵Cedric Nugteren
and standard-deviation
2018-05-21Further implemented single-kernel approach of convgemm; extended test to ↵Cedric Nugteren
capture other parts of the kernel code
2018-05-21Added method selection option to switch between im2col and single-kernel ↵Cedric Nugteren
approach for convgemm
2018-05-19Moved new convgemm kernel to levelx kernel folderCedric Nugteren
2018-05-19Second version of direct reading from image tensor for convgemm: also with ↵Cedric Nugteren
local memory support now
2018-05-19Merge branch 'master' into CLBlast-267-convgemmCedric Nugteren
2018-05-19Added an option to run the routine tuner for a single specific GEMM sizeCedric Nugteren
2018-05-19Fixed compilation issuesCedric Nugteren
2018-05-19The GEMM routine tuner now loads kernel JSON tuning results from disk if ↵Cedric Nugteren
available; now run part of alltuners target
2018-05-18Merge branch 'master' into canary_buffer_overflow_protectionCedric Nugteren
2018-05-17Added a canary region for overflow detection to the tunersCedric Nugteren
2018-05-17First version of direct reading from image tensor for convgemm: only for ↵Cedric Nugteren
edge cases now
2018-05-13Created a dedicated convgemm GEMM kernel as a copy of the batched direct ↵Cedric Nugteren
gemm kernel
2018-05-13Plugged in the code of strided-batched-gemm into convgemm in preparation of ↵Cedric Nugteren
a new kernel
2018-05-09Changed temporary convgemm implementation to use batched-strided GEMMCedric Nugteren
2018-05-09Implemented convolution as im2col + GEMMCedric Nugteren
2018-05-06Added convgemm skeleton, test infrastructure, and first reference implementationCedric Nugteren
2018-05-05Added interface of batched convolution as GEMMCedric Nugteren
2018-05-01Now stores a shared_ptr to the Program class in the cacheCedric Nugteren
2018-04-29Merge pull request #277 from CNugteren/CLBlast-257-intel-subgroupsCedric Nugteren
Intel subgroup shuffling
2018-04-26Fixed an access violation when compiled with Visual Studio upon releasing ↵Cedric Nugteren
the OpenCL program
2018-04-24Added Intel subgroup shuffle support to the 2D register caching GEMM kernelCedric Nugteren
2018-04-24Added a define to enable subgroup shuffling if supported by the deviceCedric Nugteren
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-05 01:04:40 +0000