summaryrefslogtreecommitdiff
path: root/src/database/database.cpp
AgeCommit message (Collapse)Author
2018-12-31Added convgemm to the CLBlast database, added initial parameters for Skylake GPUCedric 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
2018-01-06Fixed a performance overhead in database creation: it is again a static ↵Cedric Nugteren
variable now as it was before
2017-12-26Made the database-vector a non-static memberCedric Nugteren
2017-12-23Updated the database to use the new TRSV and Invert tunersCedric Nugteren
2017-11-02Integrated the GEMM routine tuner for kernel selection; added first tuning ↵Cedric Nugteren
results
2017-09-23Made program and binary databases dependent on the routine parameters on top ↵Cedric Nugteren
of the name
2017-09-16Updated README with proper AMD device names; fixed device look-up for names ↵Cedric Nugteren
of length 50+
2017-09-16Fixed a compilation error and warning under MacOSCedric Nugteren
2017-09-16Improved compilation time of the tuner databaseCedric Nugteren
2017-09-14Added architecture layer in the tuning database for better performance on ↵Cedric Nugteren
unseen devices
2017-09-10Added the new vendor-architecture-name hierarchy to the tuners as wellCedric Nugteren
2017-09-08Introduced the notion of a device-architecture for the database and added ↵Cedric Nugteren
device and architecture name mappings
2017-09-06Split the database files over multiple directories and files; first step ↵Cedric Nugteren
towards separate compilation
2017-09-04Removed an assumption that the 'default' tuning parameters have to be stored ↵Cedric Nugteren
last; this is no longer needed
2017-06-20Changed the structure of the database to reduce compilation time and save memoryCedric Nugteren
2017-04-10Fixed a compilation issue under MSVC and GCCCedric Nugteren
2017-04-10Removed const-vector-of-const-objects from the database class to remain ↵Cedric Nugteren
according to the C++11 standard
2017-04-07Added a special override database for the Apple CPU implementation on OS X: ↵Cedric Nugteren
this makes the test work, it does not focus on good performance
2017-02-26Merge branch 'development' into triangular_solversCedric Nugteren
2017-02-16Added input-sanity checks for the OverrideParameters functionCedric Nugteren
2017-02-12Split the database into several smaller cached per-kernel databases (in ↵Cedric Nugteren
preparation of per-kernel database overrides)
2017-02-05Merge branch 'development' into triangular_solversCedric Nugteren
2017-02-04Completed a first STRSV implementationCedric Nugteren
2017-01-24Database: pass Device instead of Queue for clarityIvan Shapovalov
2017-01-24Database: ref-count the internal map for cachingIvan Shapovalov
2017-01-15Added a first version of the diagonal block invert routine in preparation of ↵Cedric Nugteren
TRSM
2016-10-22Moved files around a bit; created a utilities subfolderCedric Nugteren
2016-10-22treewide: use C++ exceptions properlyIvan Shapovalov
Since the codebase is designed around proper C++ idioms such as RAII, it makes sense to only use C++ exceptions internally instead of mixing exceptions and error codes. The exceptions are now caught at top level to preserve compatibility with the existing error code-based API. Note that we deliberately do not catch C++ runtime errors (such as `std::bad_alloc`) nor logic errors (aka failed assertions) because no actual handling can ever happen for such errors. However, in the C interface we do catch _all_ exceptions (...) and convert them into a wild-card error code.
2016-10-14Fixed an issue with a growing database: the database is now a global ↵Cedric Nugteren
variable in a namespace and its container uses const-pointers to the actual data
2016-10-10First fixes towards compilation on Visual Studio 2013Cedric Nugteren
2016-10-06Added a kernel selection database to select between the direct and indirect ↵Cedric Nugteren
GEMM kernels
2016-09-25Separated the tuning parameters of the new direct GEMM kernel from the ↵Cedric Nugteren
indirect version
2016-09-12Added XgemvFastRot and Xgemm 16-bit tuning results: just defaults which are ↵Cedric Nugteren
now automatically taken from 32-bit if there are no entries at all
2016-07-25Removed all old tuning results for the XgemvFastRot kernel; re-added for a ↵Cedric Nugteren
couple of devices
2016-07-25Moved the XgemvFast and XgemvFastRot tuning database into a separate fileCedric Nugteren
2016-07-24Minor improvements after merging in groundwork for custom tuning parameters ↵Cedric Nugteren
and kernels
2016-07-22clblast::Database, clblast::Routine: implement "database overlays" provided ↵Ivan Shapovalov
by routine implementation
2016-06-19Renamed all C++ source files to .cpp to match the .hpp extension betterCedric Nugteren