Commit graph

1044 commits

Author SHA1 Message Date
Cedric Nugteren 6d52eb2956
Merge pull request #240 from CNugteren/retrieve_tuning_parameters
Retrieve tuning parameters
2018-01-11 23:09:48 +01:00
Cedric Nugteren 90e8e55acb Added test for the RetrieveParameters function 2018-01-11 20:34:09 +01:00
Cedric Nugteren a500f537d8 Added a RetrieveParameters function to inspect tuning parameters 2018-01-11 20:32:06 +01:00
Cedric Nugteren 389919faec Fixed bug in override parameters test 2018-01-11 20:30:45 +01:00
Cedric Nugteren 9b084d0409
Merge pull request #239 from CNugteren/gemm_strided_batched
GemmStridedBatched
2018-01-11 19:42:50 +01:00
Cedric Nugteren 99a4df88a6 Implemented the in-direct version of the strided-batched GEMM kernel 2018-01-08 21:07:01 +01:00
Cedric Nugteren 13f0f6fc6e Implemented direct version of strided-batched GEMM kernel 2018-01-07 14:58:45 +01:00
Cedric Nugteren 9fb2c61b25 Added API and tests for new GemmStridedBatched routine 2018-01-07 14:27:15 +01:00
Cedric Nugteren 0c48c6e6c4 Fixed a minor nullptr related issue in the code generator 2018-01-06 19:32:54 +01:00
Cedric Nugteren 00687f8d81 Prevented half-precision batched routines from failing in the tests 2018-01-06 19:26:38 +01:00
Cedric Nugteren f1e3b35541 Reduced duplicate code in the batched GEMM implementation 2018-01-06 19:26:11 +01:00
Cedric Nugteren c988c2cdd1 Updated changelog and roadmap 2018-01-06 17:16:11 +01:00
Cedric Nugteren c9b5d614e2 Fixed a vendor naming bug in the tuners and in the database 2018-01-06 17:02:58 +01:00
Cedric Nugteren a7ccce1969
Merge pull request #238 from CNugteren/gemm_api_with_temp_buffer
GEMM API with optional temp buffer
2018-01-06 16:08:27 +01:00
Cedric Nugteren ad197da08d Fixed the CUDA interface: replaced nullptr with 0 2018-01-06 13:38:44 +01:00
Cedric Nugteren e71c037304 Fixed a performance overhead in database creation: it is again a static variable now as it was before 2018-01-06 11:28:04 +01:00
Cedric Nugteren ce069545d4 Added CUDA interface to get temporary-buffer size for GEMM routine 2018-01-06 10:05:28 +01:00
Cedric Nugteren 44431daecc Added a CUDA version of the GEMM temp-buffer optional argument 2018-01-04 19:33:51 +01:00
Cedric Nugteren af14fff1e9 Updated the generator script to automatically generate the temp-buffer code 2018-01-04 19:31:57 +01:00
Cedric Nugteren a3925e5060 Updated the ROADMAP 2018-01-03 20:38:48 +01:00
Cedric Nugteren 5315b982a9 Added the temp-buffer to the GEMM testers and clients 2018-01-03 20:20:31 +01:00
Cedric Nugteren eb89371d2b Added a queue argument to the get-size function when running the tests/clients 2018-01-03 20:19:45 +01:00
Cedric Nugteren 8040a4e355
Merge pull request #236 from CNugteren/trsm_compilation
Fixed compilation of TRSM/Invert for AMD APP
2018-01-01 16:10:11 +01:00
Cedric Nugteren ad483123e6 Fixed the issue with AMD's APP compiler not being able to compile the invert kernel 2017-12-31 16:13:13 +01:00
Cedric Nugteren 1511909b6f Revert "Added a simple test to check compilation of the invert kernels (issue with AMD APP)"
This reverts commit 0eb9b35481.
2017-12-31 16:11:35 +01:00
Cedric Nugteren 7f893a85d9 Revert "Added options to disable parts of the invert kernel to find out where the AMD compiler crashes"
This reverts commit 407ed52cec.
2017-12-31 16:10:40 +01:00
Cedric Nugteren b4c8e1d9a5 Made plotting script more flexible: extra argument to set the comparison library 2017-12-31 16:02:46 +01:00
Cedric Nugteren 69226ae828 Changed the invert kernel slightly; added part1a/part1b disable-defines 2017-12-31 14:07:08 +01:00
Cedric Nugteren 7ce415b927 Fixed ifdef's into ifndef's 2017-12-30 21:17:31 +01:00
Cedric Nugteren 407ed52cec Added options to disable parts of the invert kernel to find out where the AMD compiler crashes 2017-12-30 21:07:50 +01:00
Cedric Nugteren ad1227c4f2 Added optional temp-buffer argument to C++ interface of GEMM 2017-12-30 18:45:06 +01:00
Cedric Nugteren 6d1e30e61f Added interface to compute the required temporary buffer size for GEMM 2017-12-28 14:46:45 +01:00
Cedric Nugteren aaea9474a1 Factored out argument processing from the GEMM routine 2017-12-28 13:56:18 +01:00
Cedric Nugteren 74792ce96c Refactored GEMM code in preparation of separate temp-buffer computation 2017-12-28 11:08:10 +01:00
Cedric Nugteren 936cf2668d
Merge pull request #234 from CNugteren/database_compilation_split
Database compilation split
2017-12-27 20:05:31 +01:00
Cedric Nugteren 0eb9b35481 Added a simple test to check compilation of the invert kernels (issue with AMD APP) 2017-12-27 17:16:08 +01:00
Cedric Nugteren 2b9bf3a9aa Simplified invert kernel a little 2017-12-27 17:03:06 +01:00
Cedric Nugteren 1e738db6dd Split the database into multiple small compilation units 2017-12-27 12:04:22 +01:00
Cedric Nugteren 4a2fc4aa98 Made the database-vector a non-static member 2017-12-26 11:32:05 +01:00
Cedric Nugteren bd540829ea Fixes for the CUDA backend of CLBlast 2017-12-24 12:10:55 +01:00
Cedric Nugteren 8657e90cf8 Fixed linking of the preprocessor test for MSVC 2017-12-24 11:33:47 +01:00
Cedric Nugteren e81eb4f6d4 Added a note that the ArrayFire Jenkins servers are down, being switched to buildbot 2017-12-24 11:32:31 +01:00
Cedric Nugteren ef71d8e9b5 Fixed unused variable warnings showing up with Clang 2017-12-23 16:07:26 +01:00
Cedric Nugteren 7aabeb44cc Updated the tuning results for the IvyBridge M GT2 GPU 2017-12-23 15:46:41 +01:00
Cedric Nugteren 2b020d59f9 Added defines to disable OpenCL deprecation warnings 2017-12-23 15:32:22 +01:00
Cedric Nugteren 04bf5437bc Fixed a warning under MSVC 2017-12-23 15:30:08 +01:00
Cedric Nugteren c6db6f67d7
Merge pull request #232 from CNugteren/feature/more_tuners
First tuners for the TRSV (block size) and TRSM (invert kernel) routines
2017-12-23 15:26:52 +01:00
Cedric Nugteren 288766debb Now calling main TRSV routine again to fix compilation in MSVC 2017-12-23 14:49:21 +01:00
Cedric Nugteren 736399e528 Split the invert kernel in two parts to prevent error C1091 in MSVC 2013 2017-12-23 14:18:07 +01:00
Cedric Nugteren b1f52f130c Updated the database to use the new TRSV and Invert tuners 2017-12-23 13:55:22 +01:00