summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2016-04-27Added missing namespace to the SGEMM exampleCedric Nugteren
2016-04-27Added prototypes for non-BLAS routines: xSUM and IxMAX (non-absolute ↵Cedric Nugteren
counterparts of xASUM and IxAMAX)
2016-04-27Moved all cache-related functions to a separate file; added a ↵Cedric Nugteren
ClearCompiledProgramCache function to clear the cache
2016-04-27Relaxed the absolute error margin for floating-point value comparisons to 1e-4Cedric Nugteren
2016-04-27Added a '-verbose' option to the test binaries to report errors in more ↵Cedric Nugteren
detail if needed
2016-04-27All CLBlast enum constants now have the same raw values as in the cblas standardCedric Nugteren
2016-04-20Merge branch 'level1_routines' into developmentcnugteren
2016-04-20Added support for the iSAMAX/iDAMAX/iCAMAX/iZAMAX routinescnugteren
2016-04-20Added prototype for ixAMAX routinescnugteren
2016-04-14Updated the reduction-kernel tuner to also tune the epiloguecnugteren
2016-04-14Added support for the SASUM/DASUM/ScASUM/DzASUM routinescnugteren
2016-04-13Added prototype for xASUM routinescnugteren
2016-04-11Fixed the way the defaults are calculated in the database; added warning for ↵cnugteren
non-matching tuner arguments
2016-04-09Events are now properly implemented using event waiting list and asking the ↵cnugteren
user to wait for event completion
2016-04-04Properly set warning flags for Clangcnugteren
2016-04-04Removed redundant queue synchronisation statementscnugteren
2016-04-03Merge branch 'cpu_blas' into developmentcnugteren
2016-04-03Updated the documentation in light of the support for a reference CPU BLAS ↵cnugteren
library
2016-04-03Added support for detection of CPU BLAS libraries OpenBLAS, BLIS and ↵cnugteren
Accelerate on OS X
2016-04-02Added support for testing (performance and correctness) against a CPU BLAS ↵cnugteren
library
2016-04-01Added a wrapper for CBLAS libraries for performance/correctness testingcnugteren
2016-03-31Create a first version of CPU BLAS detection in CMakecnugteren
2016-03-31Updated the documentationcnugteren
2016-03-30Merge branch 'level1_routines' into developmentcnugteren
2016-03-30Fixed the nrm2 kernel for complex data-typescnugteren
2016-03-30CMake now downloads the cl.hpp header from the Khronos website when building ↵cnugteren
the samples
2016-03-30Added prototypes for the xROTM and xROTMG routinesCedric Nugteren
2016-03-30Added prototypes for the xROT and xROTG functionsCedric Nugteren
2016-03-30Made event an optional argument in the CLBlast C++ APICedric Nugteren
2016-03-30Added missing newline to the end of the public API fileCedric Nugteren
2016-03-30Fixed properly passing of OpenCL events to CLBlast functionsCedric Nugteren
2016-03-28Added preliminary support for the xNRM2 routinesCedric Nugteren
2016-03-25Added prototypes for ScNRM2/DzNRM2 routinesCedric Nugteren
2016-03-25Added prototypes for SNRM2/DNRM2 routinesCedric Nugteren
2016-03-23Fixed the C-api export to be able to properly build a DLL on WindowsCedric Nugteren
2016-03-23Fixed compilation of the two SGEMM samplesCedric Nugteren
2016-03-19Added __declspec(dllexport) to create a DLL on WindowsCedric Nugteren
2016-03-14Made the library thread-safe by guarding the kernel cache with a mutexCedric Nugteren
2016-03-13Prepared the changelog for the next releaseCedric Nugteren
2016-03-13Updated to version 0.6.0Cedric Nugteren
2016-03-13Updated Travis to reflect the changes in the Khronos websiteCedric Nugteren
2016-03-13Updated the README fileCedric Nugteren
2016-03-13Updated Travis script to take into account the missing OpenCL packagesCedric Nugteren
2016-03-13Updated Travis script to fix the fglrx=2:8.960-0ubuntu1 issueCedric Nugteren
2016-03-12Added tuning results for the newest xGER family kernelsCedric Nugteren
2016-03-12Added performance graphs for Intel Iris and Radeon M370XCedric Nugteren
2016-03-12Added tuning results for the ARM Mali-T628 GPUCedric Nugteren
2016-03-06Fixed a bug in the GER-family of routines due to incorrect division of the ↵Cedric Nugteren
workgroup size
2016-03-06Made testing against clBLAS in the client binaries truely optional (was ↵Cedric Nugteren
partly implemented before)
2016-03-06Adjusted the correctness-test error marginsCedric Nugteren
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-01 23:53:23 +0000