4 files changed
+4
-4
lines changed- .appveyor.yml+2-2
- .github/workflows/build_and_test.yml+7-7
- CHANGELOG+1-10
- CMakeLists.txt+3-5
- README.md+4-2
- cmake/Modules/FindCBLAS.cmake+1-1
- doc/tuning.md+1-15
- include/clblast.h+2-2
- include/clblast_c.h+2-2
- scripts/benchmark/plot.py+1-1
- scripts/generator/generator.py+5-5
- scripts/generator/generator/pyclblast.py+3-13
- src/database/kernels/copy/copy_16.hpp+3-11
- src/database/kernels/copy/copy_32.hpp+1-16
- src/database/kernels/copy/copy_3232.hpp+5-20
- src/database/kernels/copy/copy_64.hpp+3-18
- src/database/kernels/copy/copy_6464.hpp+3-18
- src/database/kernels/gemm_routine/gemm_routine_16.hpp+3-12
- src/database/kernels/gemm_routine/gemm_routine_32.hpp+10-25
- src/database/kernels/gemm_routine/gemm_routine_3232.hpp+5-19
- src/database/kernels/gemm_routine/gemm_routine_64.hpp+3-17
- src/database/kernels/gemm_routine/gemm_routine_6464.hpp+3-18
- src/database/kernels/invert/invert_16.hpp+1-17
- src/database/kernels/invert/invert_32.hpp+3-17
- src/database/kernels/invert/invert_3232.hpp+2-16
- src/database/kernels/invert/invert_64.hpp+1-15
- src/database/kernels/invert/invert_6464.hpp-14
- src/database/kernels/pad/pad_16.hpp+1-10
- src/database/kernels/pad/pad_32.hpp+4-19
- src/database/kernels/pad/pad_3232.hpp+5-20
- src/database/kernels/pad/pad_64.hpp+4-19
- src/database/kernels/pad/pad_6464.hpp+4-19
- src/database/kernels/padtranspose/padtranspose_16.hpp+1-10
- src/database/kernels/padtranspose/padtranspose_32.hpp+2-17
- src/database/kernels/padtranspose/padtranspose_3232.hpp+3-18
- src/database/kernels/padtranspose/padtranspose_64.hpp+1-16
- src/database/kernels/padtranspose/padtranspose_6464.hpp+1-16
- src/database/kernels/transpose/transpose_16.hpp+1-10
- src/database/kernels/transpose/transpose_32.hpp+5-20
- src/database/kernels/transpose/transpose_3232.hpp+5-20
- src/database/kernels/transpose/transpose_64.hpp+2-17
- src/database/kernels/transpose/transpose_6464.hpp+2-17
- src/database/kernels/trsv_routine/trsv_routine_32.hpp+1-27
- src/database/kernels/trsv_routine/trsv_routine_3232.hpp+1-19
- src/database/kernels/trsv_routine/trsv_routine_64.hpp-18
- src/database/kernels/trsv_routine/trsv_routine_6464.hpp+1-19
- src/database/kernels/xaxpy/xaxpy_16.hpp+3-12
- src/database/kernels/xaxpy/xaxpy_32.hpp+3-18
- src/database/kernels/xaxpy/xaxpy_3232.hpp+4-19
- src/database/kernels/xaxpy/xaxpy_64.hpp+6-21
- src/database/kernels/xaxpy/xaxpy_6464.hpp+5-20
- src/database/kernels/xconvgemm/xconvgemm_16.hpp+2-9
- src/database/kernels/xconvgemm/xconvgemm_32.hpp+1-4
- src/database/kernels/xconvgemm/xconvgemm_64.hpp-4
- src/database/kernels/xdot/xdot_16.hpp+3-12
- src/database/kernels/xdot/xdot_32.hpp+5-20
- src/database/kernels/xdot/xdot_3232.hpp+4-19
- src/database/kernels/xdot/xdot_64.hpp+5-20
- src/database/kernels/xdot/xdot_6464.hpp+6-21
- src/database/kernels/xgemm/xgemm_16.hpp+2-10
- src/database/kernels/xgemm/xgemm_32.hpp+3-18
- src/database/kernels/xgemm/xgemm_3232.hpp+5-20
- src/database/kernels/xgemm/xgemm_64.hpp+3-18
- src/database/kernels/xgemm/xgemm_6464.hpp+2-16
- src/database/kernels/xgemm_direct/xgemm_direct_16.hpp+2-11
- src/database/kernels/xgemm_direct/xgemm_direct_32.hpp+4-18
- src/database/kernels/xgemm_direct/xgemm_direct_3232.hpp+3-17
- src/database/kernels/xgemm_direct/xgemm_direct_64.hpp+5-19
- src/database/kernels/xgemm_direct/xgemm_direct_6464.hpp+2-16
- src/database/kernels/xgemv/xgemv_16.hpp+1-17
- src/database/kernels/xgemv/xgemv_32.hpp+2-16
- src/database/kernels/xgemv/xgemv_3232.hpp+1-15
- src/database/kernels/xgemv/xgemv_64.hpp-14
- src/database/kernels/xgemv/xgemv_6464.hpp-17
- src/database/kernels/xgemv_fast/xgemv_fast_16.hpp+1-17
- src/database/kernels/xgemv_fast/xgemv_fast_32.hpp+4-18
- src/database/kernels/xgemv_fast/xgemv_fast_3232.hpp+2-19
- src/database/kernels/xgemv_fast/xgemv_fast_64.hpp+1-15
- src/database/kernels/xgemv_fast/xgemv_fast_6464.hpp-17
- src/database/kernels/xgemv_fast_rot/xgemv_fast_rot_16.hpp+1-17
- src/database/kernels/xgemv_fast_rot/xgemv_fast_rot_32.hpp+3-17
- src/database/kernels/xgemv_fast_rot/xgemv_fast_rot_3232.hpp+3-20
- src/database/kernels/xgemv_fast_rot/xgemv_fast_rot_64.hpp+4-18
- src/database/kernels/xgemv_fast_rot/xgemv_fast_rot_6464.hpp+3-20
- src/database/kernels/xger/xger_16.hpp+3-12
- src/database/kernels/xger/xger_32.hpp+5-20
- src/database/kernels/xger/xger_3232.hpp+4-19
- src/database/kernels/xger/xger_64.hpp+6-21
- src/database/kernels/xger/xger_6464.hpp+4-19
- src/pyclblast/CMakeLists.txt-67
- src/pyclblast/MANIFEST.in+1-2
- src/pyclblast/README.md+14-24
- src/pyclblast/pyproject.toml-32
- src/pyclblast/setup.py+54
- src/pyclblast/src/pyclblast.pyx+25-43
- test/correctness/misc/preprocessor.cpp+1-1
0 commit comments