Age | Commit message (Collapse) | Author | |
---|---|---|---|
2017-03-05 | Added first naive version of the batched AXPY routine | Cedric Nugteren | |
2017-03-01 | Added proper support for the b_offset argument in TRSM | Cedric Nugteren | |
2017-02-27 | Fixed half-precision bugs in HTBMV/HTPMV/HTRMV/HSYR2K/HTRMM related to ↵ | Cedric Nugteren | |
incorrect constants | |||
2017-02-26 | Split the GEMM kernel further up to prevent C1091 in MSVC | Cedric Nugteren | |
2017-02-26 | Merge branch 'development' into triangular_solvers | Cedric Nugteren | |
2017-02-26 | Fixed an out-of-bounds memory access when filling a matrix with a constant | Cedric Nugteren | |
2017-02-24 | Implemented a simple row-major to col-major problem conversion for TRSM | Cedric Nugteren | |
2017-02-22 | Fixed a few issues with the TRSM routine; some tests still failing | Cedric Nugteren | |
2017-02-13 | Fixed a small bug in GEMV: unused kernel in parameter list | Cedric Nugteren | |
2017-02-12 | Split the database into several smaller cached per-kernel databases (in ↵ | Cedric Nugteren | |
preparation of per-kernel database overrides) | |||
2017-02-05 | Merge branch 'development' into triangular_solvers | Cedric Nugteren | |
2017-02-04 | Improved substition kernels a bit; added complex support | Cedric Nugteren | |
2017-02-04 | Completed a first STRSV implementation | Cedric Nugteren | |
2017-02-04 | Added row-major support for TRSV | Cedric Nugteren | |
2017-01-29 | Added first (incomplete) version of TRSV routine | Cedric Nugteren | |
2017-01-24 | Routine, Cache: generalize, reduce amount of copying in fast path | Ivan Shapovalov | |
Implement a generalized Cache<K, V>. Two variants are provided: the first one is based on std::map, using C++14-specific transparent std::less<> and generalized std::map::find() to allow searching by tuple of references. The second one is based on std::vector and O(n) lookup, but remains C++11-compliant. | |||
2017-01-20 | treewide: include clpp11.hpp first to silence deprecation warnings | Ivan Shapovalov | |
Otherwise, cl.h gets included through clblast.h before clpp11.hpp. | |||
2017-01-20 | Added prototype for the TRSV routine | Cedric Nugteren | |
2017-01-18 | Added first version of the TRSM routine based on the diagonal invert kernel | Cedric Nugteren | |
2017-01-15 | Added a first version of the diagonal block invert routine in preparation of ↵ | Cedric Nugteren | |
TRSM | |||
2016-12-18 | Prepared for the addition of the TRSM triangular solver kernel | Cedric Nugteren | |
2016-12-18 | Fixed a bug when using offsets in the direct GEMM kernels | Cedric Nugteren | |
2016-11-24 | Merge pull request #125 from CNugteren/netlib_blas_api | Cedric Nugteren | |
Netlib CBLAS API for CLBlast | |||
2016-11-23 | Fixed a bug in the HSCAL routine | Cedric Nugteren | |
2016-11-20 | Now correctly tests for validaty of the B matrix in the TRMM routine | Cedric Nugteren | |
2016-11-20 | Fixed a bug in the TRMM routine caused by overwriting input data before ↵ | Cedric Nugteren | |
consuming everything | |||
2016-10-23 | Fixed a bug in the transpose-matrix function | Cedric Nugteren | |
2016-10-22 | Merge pull request #117 from intelfx/exceptions | Cedric Nugteren | |
Convert to use C++ exceptions internally | |||
2016-10-22 | Fixed a bug in the SYRK/SYR2K/HERK/HER2K routines that would occur with ↵ | Cedric Nugteren | |
specific tuning parameters | |||
2016-10-22 | Routine: get rid of ::SetUp() | Ivan Shapovalov | |
Since we now use C++ exceptions inside the implementation (and exceptions can be thrown from constructors), there is no need for a separate Routine::SetUp() function. For this, we also change the way how the kernel source string is constructed. The kernel-specific source code is now passed to the Routine ctor via an initializer_list of C strings to avoid unnecessary data copying while also working around C1091 of MSVC 2013. | |||
2016-10-22 | treewide: use C++ exceptions properly | Ivan 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. | |||
2016-10-10 | Fixed an issue with the length of the GEMM OpenCL string for both MSVC 2013 ↵ | Cedric Nugteren | |
and 2015 | |||
2016-10-06 | Added a kernel selection database to select between the direct and indirect ↵ | Cedric Nugteren | |
GEMM kernels | |||
2016-10-03 | Re-organised GEMM direct kernel and added faster fall-back version for ↵ | Cedric Nugteren | |
incomplete rectangles | |||
2016-10-02 | Specialised the GEMM direct kernel in four ways for ↵ | Cedric Nugteren | |
transposing/non-transposing: NN, NT, TN, TT | |||
2016-10-02 | Split the GEMM direct kernel into two files; set the default tuning target ↵ | Cedric Nugteren | |
to 256-256-256 | |||
2016-09-25 | Added a first version of a tuner for the GEMM direct kernel; collapsed MWGD, ↵ | Cedric Nugteren | |
NWGD and KWGD into one WGD parameter | |||
2016-09-25 | Separated the tuning parameters of the new direct GEMM kernel from the ↵ | Cedric Nugteren | |
indirect version | |||
2016-09-21 | Merge branch 'development' into gemm_direct | Cedric Nugteren | |
2016-09-12 | Split the XGEMM kernel further up: now in 3 parts. This is done because MSVC ↵ | Cedric Nugteren | |
can't handle long strings | |||
2016-07-26 | Fixed issues related to the recent changes in the Xgemm infrastructure | Cedric Nugteren | |
2016-07-26 | Merge branch 'development' into gemm_direct | Cedric Nugteren | |
2016-07-25 | Moved the XgemvFast and XgemvFastRot tuning database into a separate file | Cedric Nugteren | |
2016-07-24 | Merge branch 'development' into gemv_performance | Cedric Nugteren | |
2016-07-23 | Improved the XgemvFastRot kernel by tiled loading of the input matrix A, ↵ | Cedric Nugteren | |
enabling better memory performance | |||
2016-07-22 | clblast::RunKernel, cl::Kernel: unify variants with/without waitForEvents, ↵ | Ivan Shapovalov | |
support empty LWS | |||
2016-07-22 | clblast::RunKernel, cl::Kernel: take const vector as waitForEvents | Ivan Shapovalov | |
2016-07-22 | xgemm: do not hardcode kernel requirements for internal matrix layout | Ivan Shapovalov | |
Do not hardcode the knowledge about "A and C col-major, B row-major". This allows for easier reuse of the DoGemm() routine with different kernels. | |||
2016-07-17 | Improved the GEMM direct kernel by adding register blocking. Still not fast ↵ | Cedric Nugteren | |
though | |||
2016-07-16 | Created infrastructure to support a direct GEMM kernel; added correct but ↵ | Cedric Nugteren | |
slow reference kernel as a place-holder |