haraldwolff/CLBlast
1
0
Fork 0
mirror of https://github.com/CNugteren/CLBlast.git synced 2024-07-07 12:23:46 +02:00
Code Issues Packages Projects Releases Wiki Activity
496 commits 13 branches 28 tags 8 MiB
Commit graph

496 commits

This branch
This branch
All branches
Author SHA1 Message Date
cnugteren 1acb31896c Fixed an issue with computing the GFLOPS numbers for the xGEMM performance tests for non-square matrices 2016-05-08 10:06:06 +02:00
Cedric Nugteren ed2904a344 Added preliminary generated API documentation 2016-05-08 09:49:00 +02:00
Cedric Nugteren 6c9e08c5e2 Added an option to the tests to control whether to test against clBLAS or a CPU BLAS library 2016-05-07 12:22:06 +02:00
Cedric Nugteren 56aa1701c9 Added printing of indices when testing in verbose mode 2016-05-05 23:09:57 +02:00
Cedric Nugteren f18c12389d Merge pull request #57 from dividiti/development 
Locate the C BLAS library before the F77 one.
 2016-05-05 22:27:22 +02:00
Anton Lokhmotov e075dc347a Locate the C BLAS library before the F77 one. 2016-05-05 14:38:10 +00:00
Cedric Nugteren aa97c836b1 Fixed an issue with linking against the ATLAS BLAS library 2016-05-04 19:16:09 +02:00
Cedric Nugteren 435729a43e Added tuning results for AMD Hawaii (R9 290X) 2016-05-02 20:20:23 +02:00
Cedric Nugteren a8f109296c Fixed the calculation of the required buffer sizes in case of subvectors and submatrices 2016-05-02 20:04:55 +02:00
Cedric Nugteren 27d0ac7f38 Added tuning results for AMD Pitcairn (R9 270X) 2016-05-01 19:33:50 +02:00
Cedric Nugteren c94b628318 Updated tuning database for reduction/dot kernels based on the new tuner; partially repopulated the database 2016-05-01 19:17:04 +02:00
Cedric Nugteren b9317d7d0c Made the default xDOT tuning size smaller 2016-05-01 14:39:44 +02:00
Cedric Nugteren bee2f943ec Changed the index buffer of IxAMAX routines to unsigned int for proper buffersize checking 2016-05-01 14:03:37 +02:00
Cedric Nugteren 9602c150aa Added a program cache (per-context) next to the per-device binary cache 2016-05-01 12:56:08 +02:00
Cedric Nugteren e113ff0852 Added non-aboslute minimum counter-part IxMIN of the BLAS routine IxAMAX 2016-04-30 09:49:39 +02:00
Cedric Nugteren 2952390f27 Added an example to demonstrate the use of the ClearCache and FillCache functions 2016-04-29 23:33:36 +02:00
Cedric Nugteren 877aad693f Added FillCache: a function to pre-compile all kernels for a specific device 2016-04-29 23:33:12 +02:00
Cedric Nugteren 4f528b1730 Added sample C programs for the SASUM and DGEMV routines 2016-04-29 20:33:19 +02:00
Cedric Nugteren d9b21d7f49 Fixed the cache to store binaries instead of OpenCL programs 2016-04-28 21:14:17 +02:00
Cedric Nugteren d7ddbdeb1f Added non-absolute counter-parts xSUM and IxMAX of the BLAS routines xASUM and IxAMAX 2016-04-27 18:07:30 +02:00
Cedric Nugteren 13eed1a0f9 Added missing namespace to the SGEMM example 2016-04-27 17:59:28 +02:00
Cedric Nugteren 8075934ca7 Added prototypes for non-BLAS routines: xSUM and IxMAX (non-absolute counterparts of xASUM and IxAMAX) 2016-04-27 17:06:19 +02:00
Cedric Nugteren 82be8f211c Moved all cache-related functions to a separate file; added a ClearCompiledProgramCache function to clear the cache 2016-04-27 16:02:13 +02:00
Cedric Nugteren 44bdb60e83 Relaxed the absolute error margin for floating-point value comparisons to 1e-4 2016-04-27 14:42:30 +02:00
Cedric Nugteren 226e834d0a Added a '-verbose' option to the test binaries to report errors in more detail if needed 2016-04-27 14:38:30 +02:00
Cedric Nugteren 3555cd0436 All CLBlast enum constants now have the same raw values as in the cblas standard 2016-04-27 11:37:55 +02:00
cnugteren c8e28a33c0 Merge branch 'level1_routines' into development 2016-04-20 22:14:55 -06:00
cnugteren 16a048f1ac Added support for the iSAMAX/iDAMAX/iCAMAX/iZAMAX routines 2016-04-20 22:12:51 -06:00
cnugteren 894983fc3c Added prototype for ixAMAX routines 2016-04-20 21:11:33 -06:00
cnugteren 5a4f8217be Updated the reduction-kernel tuner to also tune the epilogue 2016-04-14 21:37:52 -06:00
cnugteren 8be99de82d Added support for the SASUM/DASUM/ScASUM/DzASUM routines 2016-04-14 19:58:26 -06:00
cnugteren e0497807e2 Added prototype for xASUM routines 2016-04-13 21:44:49 -06:00
cnugteren a61724ece5 Fixed the way the defaults are calculated in the database; added warning for non-matching tuner arguments 2016-04-11 22:27:44 -06:00
cnugteren 1d3d38a261 Events are now properly implemented using event waiting list and asking the user to wait for event completion 2016-04-09 22:22:24 -06:00
cnugteren c2cfee76c4 Properly set warning flags for Clang 2016-04-04 08:39:13 -07:00
cnugteren 90e237b97a Removed redundant queue synchronisation statements 2016-04-04 08:38:31 -07:00
cnugteren 2981ca4d3c Merge branch 'cpu_blas' into development 2016-04-03 16:08:48 -07:00
cnugteren c4ab9bda63 Updated the documentation in light of the support for a reference CPU BLAS library 2016-04-03 16:07:25 -07:00
cnugteren cf841d1840 Added support for detection of CPU BLAS libraries OpenBLAS, BLIS and Accelerate on OS X 2016-04-03 15:51:03 -07:00
cnugteren 1a82861a90 Added support for testing (performance and correctness) against a CPU BLAS library 2016-04-02 11:58:00 -07:00
cnugteren 5c83217cf2 Added a wrapper for CBLAS libraries for performance/correctness testing 2016-04-01 22:36:39 -07:00
cnugteren a2056f2216 Create a first version of CPU BLAS detection in CMake 2016-03-31 22:22:29 -07:00
cnugteren 8217b01702 Updated the documentation 2016-03-31 20:20:32 -07:00
cnugteren 8c3c6db7d0 Merge branch 'level1_routines' into development 2016-03-30 21:37:56 -07:00
cnugteren 5409f349a1 Fixed the nrm2 kernel for complex data-types 2016-03-30 21:32:04 -07:00
cnugteren 6578102ae9 CMake now downloads the cl.hpp header from the Khronos website when building the samples 2016-03-30 16:24:38 -07:00
Cedric Nugteren c1df786764 Added prototypes for the xROTM and xROTMG routines 2016-03-30 16:13:37 -07:00
Cedric Nugteren 6ecc0d089c Added prototypes for the xROT and xROTG functions 2016-03-30 16:13:32 -07:00
Cedric Nugteren 6e5f558746 Made event an optional argument in the CLBlast C++ API 2016-03-30 16:13:26 -07:00
Cedric Nugteren 6f561abada Added missing newline to the end of the public API file 2016-03-30 16:13:22 -07:00