| Age | Commit message (Expand) | Author |
|---|
| 2015-07-22 | Made the graph script robust against diagnostic system messages | CNugteren |
| 2015-07-22 | Set the correct name for AMD OpenCL devices | CNugteren |
| 2015-07-22 | Updated GEMM tuning results for Tahiti | CNugteren |
| 2015-07-22 | Added workgroup shuffle option to transpose kernel for AMD GPUs | CNugteren |
| 2015-07-21 | Transpose kernel now uses vectorized local memory loads and stores | CNugteren |
| 2015-07-19 | Triangular GEMM kernels are only compiled when needed | CNugteren |
| 2015-07-19 | Kernel caching is now based on a routine's name | CNugteren |
| 2015-07-19 | The kernel source string is now a routine's member variable | CNugteren |
| 2015-07-19 | Fixed complex performance on Intel Iris | CNugteren |
| 2015-07-16 | Fixed a bug when using the Xgemm kernel without local memory | CNugteren |
| 2015-07-16 | Using mad() instruction for AMD devices like clBLAS does | CNugteren |
| 2015-07-15 | Merge pull request #13 from CNugteren/bypass_pre_post_processing | Cedric Nugteren |
| 2015-07-15 | Updated changelog with pre/post-processing bypass | CNugteren |
| 2015-07-15 | Changed performance graphs to default to column-major | CNugteren |
| 2015-07-15 | Skips pre/post processing kernels if not needed | CNugteren |
| 2015-07-13 | Updated interface of the PadCopyTransposeMatrix method | CNugteren |
| 2015-07-12 | Merge pull request #12 from CNugteren/level_subfolders | Cedric Nugteren |
| 2015-07-12 | Added subfolders for the level1/2/3 routines | CNugteren |
| 2015-07-12 | Merge pull request #11 from CNugteren/level3_routines_2 | Cedric Nugteren |
| 2015-07-12 | Added HEMM, HERK, HER2K, and TRMM | CNugteren |
| 2015-07-12 | Added the HEMM routine, tester, and client | CNugteren |
| 2015-07-10 | Disabled prototype of TRSM | CNugteren |
| 2015-07-10 | Added the HER2K routine, tester, and client | CNugteren |
| 2015-07-10 | Added the HERK routine, tester, and client | CNugteren |
| 2015-07-10 | The clients now distinguish between the memory and alpha/beta data-type | CNugteren |
| 2015-07-08 | Added option to set the imaginary part of the diagonal to zero | CNugteren |
| 2015-07-08 | The testers now distinguish between the memory and alpha/beta data-type | CNugteren |
| 2015-07-07 | Added option to set the imaginary part of the diagonal to zero | CNugteren |
| 2015-07-02 | Added the TRMM routine, tester, and client | CNugteren |
| 2015-07-02 | Fixed the order of arguments | CNugteren |
| 2015-07-02 | Added a set-to-one function for kernels | CNugteren |
| 2015-07-01 | Added the unit/non-unit diagonal enum | CNugteren |
| 2015-07-01 | Fixed typos in SYMM | CNugteren |
| 2015-06-30 | Added the TRMM and TRSM interface | CNugteren |
| 2015-06-30 | Added constness to all cl_mem objects | CNugteren |
| 2015-06-30 | Added TRMM and TRSM clBLAS wrappers | CNugteren |
| 2015-06-29 | Merge pull request #10 from CNugteren/test_infrastructure | Cedric Nugteren |
| 2015-06-29 | Re-organized test and client infrastructure | CNugteren |
| 2015-06-29 | Fixed the license for the correctness testers | CNugteren |
| 2015-06-29 | Re-organized the performance-client infrastructure to avoid code duplication | CNugteren |
| 2015-06-28 | Re-organized the test infrastructure to avoid code duplication | CNugteren |
| 2015-06-28 | Added buffer structure and sizes to arguments | CNugteren |
| 2015-06-26 | Merge pull request #9 from CNugteren/level3_routines | Cedric Nugteren |
| 2015-06-26 | Replaced crosses with tickmarks | CNugteren |
| 2015-06-26 | Added the SYR2K routine, tester, and client | CNugteren |
| 2015-06-26 | Added symmetric matrix support for the ABC performance tester | CNugteren |
| 2015-06-25 | Added option to test only symmetric matrices (m=n) | CNugteren |
| 2015-06-25 | Clarified comment | CNugteren |
| 2015-06-25 | Added SSYRK performance graphs | CNugteren |
| 2015-06-24 | Added the SYRK routine | CNugteren |
