├── .clang-format ├── .github ├── dependabot.yml └── workflows │ └── scorecard.yml ├── .gitignore ├── .gitmodules ├── .scripts ├── build_OpenBLAS.sh ├── build_dpcpp.sh ├── build_triSYCL.sh └── install_intel_opencl.sh ├── CMakeLists.txt ├── CODE_OF_CONDUCT.md ├── Contributors.md ├── Dockerfile ├── LICENSE ├── NOTICE ├── README.md ├── SECURITY.md ├── benchmark ├── CMakeLists.txt ├── README.md ├── bench_info.cc ├── clBench │ ├── acl │ │ ├── CMakeLists.txt │ │ ├── blas3 │ │ │ └── gemm.cpp │ │ ├── main.cpp │ │ └── utils.hpp │ ├── clblas │ │ ├── CMakeLists.txt │ │ ├── blas2 │ │ │ ├── tbsv.cpp │ │ │ └── trsv.cpp │ │ ├── blas3 │ │ │ └── trsm.cpp │ │ ├── main.cpp │ │ └── utils.hpp │ ├── clblast │ │ ├── CMakeLists.txt │ │ ├── blas1 │ │ │ ├── asum.cpp │ │ │ ├── axpy.cpp │ │ │ ├── dot.cpp │ │ │ ├── iamax.cpp │ │ │ ├── iamin.cpp │ │ │ ├── nrm2.cpp │ │ │ └── scal.cpp │ │ ├── blas2 │ │ │ ├── gbmv.cpp │ │ │ ├── gemv.cpp │ │ │ ├── ger.cpp │ │ │ ├── sbmv.cpp │ │ │ ├── spr.cpp │ │ │ ├── spr2.cpp │ │ │ ├── symv.cpp │ │ │ ├── syr.cpp │ │ │ ├── syr2.cpp │ │ │ ├── tbmv.cpp │ │ │ ├── trmv.cpp │ │ │ └── trsv.cpp │ │ ├── blas3 │ │ │ ├── gemm.cpp │ │ │ ├── gemm_batched.cpp │ │ │ ├── symm.cpp │ │ │ └── trsm.cpp │ │ ├── main.cpp │ │ └── utils.hpp │ └── clwrap.hpp ├── config_csv │ ├── blas1 │ │ ├── blas1_powersof2.csv │ │ └── copy │ │ │ └── copy_powersof2.csv │ ├── blas2 │ │ ├── gbmv │ │ │ └── gbmv_powersof2.csv │ │ ├── gemv │ │ │ └── gemv_powersof2.csv │ │ ├── ger │ │ │ └── ger_square.csv │ │ ├── sbmv │ │ │ └── sbmv_powersof2.csv │ │ ├── spmv │ │ │ └── spmv_powersof2.csv │ │ ├── spr │ │ │ └── spr_powersof2.csv │ │ ├── spr2 │ │ │ └── spr2_powersof2.csv │ │ ├── symv │ │ │ └── symv_powersof2.csv │ │ ├── syr │ │ │ └── syr_powersof2.csv │ │ ├── syr2 │ │ │ └── sry2_powersof2.csv │ │ ├── tbmv │ │ │ └── tbmv_powersof2.csv │ │ ├── tbsv │ │ │ └── tbsv_powersof2.csv │ │ ├── tpmv │ │ │ └── tpmv_powersof2.csv │ │ ├── tpsv │ │ │ └── tpsv_powersof2.csv │ │ ├── trmv │ │ │ └── trmv_powersof2.csv │ │ └── trsv │ │ │ └── trsv_powersof2.csv │ ├── blas3 │ │ ├── gemm │ │ │ ├── gemm_inference_alexnet_im2col_bkfil.csv │ │ │ ├── gemm_inference_alexnet_im2col_bkin.csv │ │ │ ├── gemm_inference_alexnet_im2col_fwd.csv │ │ │ ├── gemm_inference_alexnet_wino_bkfil.csv │ │ │ ├── gemm_inference_alexnet_wino_bkin.csv │ │ │ ├── gemm_inference_alexnet_wino_fwd.csv │ │ │ ├── gemm_inference_resnet_im2col_bkfil.csv │ │ │ ├── gemm_inference_resnet_im2col_bkin.csv │ │ │ ├── gemm_inference_resnet_im2col_fwd.csv │ │ │ ├── gemm_inference_resnet_wino_bkfil.csv │ │ │ ├── gemm_inference_resnet_wino_bkin.csv │ │ │ ├── gemm_inference_resnet_wino_fwd.csv │ │ │ ├── gemm_inference_vgg_im2col_bkfil.csv │ │ │ ├── gemm_inference_vgg_im2col_bkin.csv │ │ │ ├── gemm_inference_vgg_im2col_fwd.csv │ │ │ ├── gemm_inference_vgg_wino_bkfil.csv │ │ │ ├── gemm_inference_vgg_wino_bkin.csv │ │ │ ├── gemm_inference_vgg_wino_fwd.csv │ │ │ ├── gemm_square.csv │ │ │ ├── gemm_training_alexnet_im2col_bkfil.csv │ │ │ ├── gemm_training_alexnet_im2col_bkin.csv │ │ │ ├── gemm_training_alexnet_im2col_fwd.csv │ │ │ ├── gemm_training_alexnet_wino_bkfil.csv │ │ │ ├── gemm_training_alexnet_wino_bkin.csv │ │ │ ├── gemm_training_alexnet_wino_fwd.csv │ │ │ ├── gemm_training_resnet_im2col_bkfil.csv │ │ │ ├── gemm_training_resnet_im2col_bkin.csv │ │ │ ├── gemm_training_resnet_im2col_fwd.csv │ │ │ ├── gemm_training_resnet_wino_bkfil.csv │ │ │ ├── gemm_training_resnet_wino_bkin.csv │ │ │ ├── gemm_training_resnet_wino_fwd.csv │ │ │ ├── gemm_training_vgg_im2col_bkfil.csv │ │ │ ├── gemm_training_vgg_im2col_bkin.csv │ │ │ ├── gemm_training_vgg_im2col_fwd.csv │ │ │ ├── gemm_training_vgg_wino_bkfil.csv │ │ │ ├── gemm_training_vgg_wino_bkin.csv │ │ │ ├── gemm_training_vgg_wino_fwd.csv │ │ │ └── language_models │ │ │ │ ├── gemm_inference_bert.csv │ │ │ │ ├── gemm_inference_gpt_j_2016_32.csv │ │ │ │ ├── gemm_inference_gpt_j_32_32.csv │ │ │ │ ├── gemm_inference_transformer.csv │ │ │ │ ├── gemm_training_bert_bkfil.csv │ │ │ │ ├── gemm_training_bert_bkin.csv │ │ │ │ ├── gemm_training_bert_fwd.csv │ │ │ │ └── gemm_training_transformer.csv │ │ ├── gemm_batched │ │ │ └── gemm_batched_interleaved.csv │ │ ├── gemm_batched_strided │ │ │ ├── gemm_batched_interleaved.csv │ │ │ └── language_models │ │ │ │ ├── gemm_batched_strided_inference_bert.csv │ │ │ │ ├── gemm_batched_strided_inference_gpt_j_2016_32.csv │ │ │ │ ├── gemm_batched_strided_inference_gpt_j_32_32.csv │ │ │ │ ├── gemm_batched_strided_inference_transformer.csv │ │ │ │ ├── gemm_batched_strided_training_bert.csv │ │ │ │ └── gemm_batched_strided_training_transformer.csv │ │ ├── symm │ │ │ └── symm_square.csv │ │ ├── syr2k │ │ │ └── syr2k_square.csv │ │ ├── syrk │ │ │ └── syrk_square.csv │ │ ├── trmm │ │ │ ├── trmm_large.csv │ │ │ ├── trmm_small.csv │ │ │ ├── trmm_square.csv │ │ │ └── trmm_variations.csv │ │ ├── trsm │ │ │ ├── trsm_large.csv │ │ │ ├── trsm_small.csv │ │ │ ├── trsm_square.csv │ │ │ └── trsm_variations.csv │ │ └── trsm_batched │ │ │ ├── trsm_large.csv │ │ │ ├── trsm_small.csv │ │ │ ├── trsm_square.csv │ │ │ └── trsm_variations.csv │ └── extension │ │ └── reduction │ │ └── reduction_powersof2.csv ├── cublas │ ├── CMakeLists.txt │ ├── blas1 │ │ ├── asum.cpp │ │ ├── axpy.cpp │ │ ├── dot.cpp │ │ ├── iamax.cpp │ │ ├── iamin.cpp │ │ ├── nrm2.cpp │ │ ├── rotg.cpp │ │ ├── rotm.cpp │ │ ├── rotmg.cpp │ │ └── scal.cpp │ ├── blas2 │ │ ├── gbmv.cpp │ │ ├── gemv.cpp │ │ ├── ger.cpp │ │ ├── sbmv.cpp │ │ ├── spmv.cpp │ │ ├── spr.cpp │ │ ├── spr2.cpp │ │ ├── symv.cpp │ │ ├── syr.cpp │ │ ├── syr2.cpp │ │ ├── tbmv.cpp │ │ ├── tbsv.cpp │ │ ├── tpmv.cpp │ │ ├── tpsv.cpp │ │ ├── trmv.cpp │ │ └── trsv.cpp │ ├── blas3 │ │ ├── gemm.cpp │ │ ├── gemm_batched.cpp │ │ ├── gemm_batched_strided.cpp │ │ ├── symm.cpp │ │ ├── syr2k.cpp │ │ ├── syrk.cpp │ │ ├── trmm.cpp │ │ ├── trsm.cpp │ │ └── trsm_batched.cpp │ ├── extension │ │ ├── omatadd.cpp │ │ └── omatcopy.cpp │ ├── main.cpp │ └── utils.hpp ├── gen_param.py ├── make_git_config.bat ├── make_git_config.sh ├── portblas │ ├── CMakeLists.txt │ ├── blas1 │ │ ├── asum.cpp │ │ ├── axpy.cpp │ │ ├── copy.cpp │ │ ├── dot.cpp │ │ ├── iamax.cpp │ │ ├── iamin.cpp │ │ ├── nrm2.cpp │ │ ├── rotg.cpp │ │ ├── rotm.cpp │ │ ├── rotmg.cpp │ │ ├── scal.cpp │ │ └── sdsdot.cpp │ ├── blas2 │ │ ├── gbmv.cpp │ │ ├── gemv.cpp │ │ ├── ger.cpp │ │ ├── sbmv.cpp │ │ ├── spmv.cpp │ │ ├── spr.cpp │ │ ├── spr2.cpp │ │ ├── symv.cpp │ │ ├── syr.cpp │ │ ├── syr2.cpp │ │ ├── tbmv.cpp │ │ ├── tbsv.cpp │ │ ├── tpmv.cpp │ │ ├── tpsv.cpp │ │ ├── trmv.cpp │ │ └── trsv.cpp │ ├── blas3 │ │ ├── gemm.cpp │ │ ├── gemm_batched.cpp │ │ ├── gemm_batched_strided.cpp │ │ ├── symm.cpp │ │ └── trsm.cpp │ ├── extension │ │ ├── axpy_batch.cpp │ │ ├── omatadd.cpp │ │ ├── omatadd_batched.cpp │ │ ├── omatcopy.cpp │ │ ├── omatcopy2.cpp │ │ ├── omatcopy_batched.cpp │ │ └── reduction.cpp │ ├── main.cpp │ └── utils.hpp └── rocblas │ ├── CMakeLists.txt │ ├── blas1 │ ├── asum.cpp │ ├── axpy.cpp │ ├── dot.cpp │ ├── iamax.cpp │ ├── iamin.cpp │ ├── nrm2.cpp │ ├── rotg.cpp │ ├── rotm.cpp │ ├── rotmg.cpp │ └── scal.cpp │ ├── blas2 │ ├── gbmv.cpp │ ├── gemv.cpp │ ├── ger.cpp │ ├── sbmv.cpp │ ├── spmv.cpp │ ├── spr.cpp │ ├── spr2.cpp │ ├── symv.cpp │ ├── syr.cpp │ ├── syr2.cpp │ ├── tbmv.cpp │ ├── tbsv.cpp │ ├── tpmv.cpp │ ├── tpsv.cpp │ ├── trmv.cpp │ └── trsv.cpp │ ├── blas3 │ ├── gemm.cpp │ ├── gemm_batched.cpp │ ├── gemm_batched_strided.cpp │ ├── symm.cpp │ ├── syr2k.cpp │ ├── syrk.cpp │ ├── trmm.cpp │ ├── trsm.cpp │ └── trsm_batched.cpp │ ├── extension │ ├── axpy_batch.cpp │ ├── omatadd.cpp │ └── omatcopy.cpp │ ├── main.cpp │ └── utils.hpp ├── cmake ├── CmakeFunctionHelper.cmake ├── Modules │ ├── ConfigurePORTBLAS.cmake │ ├── FindACL.cmake │ ├── FindCLHPP.cmake │ ├── FindClara.cmake │ ├── FindDPCPP.cmake │ ├── FindSB_CLBlast.cmake │ ├── FindSystemBLAS.cmake │ ├── Findnpy.cmake │ └── SYCL.cmake └── templates │ ├── CMakeLists.txt.in │ ├── GBench.txt.in │ └── GTest.txt.in ├── common └── include │ └── common │ ├── benchmark_cli_args.hpp │ ├── benchmark_identifier.hpp │ ├── benchmark_names.hpp │ ├── blas1_state_counters.hpp │ ├── blas2_state_counters.hpp │ ├── blas3_state_counters.hpp │ ├── blas_extension_state_counters.hpp │ ├── cli_device_selector.hpp │ ├── common_utils.hpp │ ├── extract_vendor_type.hpp │ ├── float_comparison.hpp │ ├── print_queue_information.hpp │ ├── set_benchmark_label.hpp │ └── system_reference_blas.hpp ├── doc ├── AddingBlas3Op.md ├── Autotuner.md ├── Doxyfile ├── Gemm.md ├── MissingFeatures.md └── Reduction.md ├── external ├── cblas │ └── include │ │ └── cblas.h └── clara │ └── include │ └── clara.hpp ├── include ├── blas_meta.h ├── container │ └── sycl_iterator.h ├── interface │ ├── blas1_interface.h │ ├── blas2_interface.h │ ├── blas3_interface.h │ ├── extension_interface.h │ ├── gemm_launcher.h │ └── reduction_interface.h ├── operations │ ├── blas1_trees.h │ ├── blas2_trees.h │ ├── blas3_trees.h │ ├── blas_constants.h │ ├── blas_operators.h │ └── extension │ │ ├── axpy_batch.h │ │ ├── matcopy_batch.h │ │ ├── reduction.h │ │ └── transpose.h ├── portblas.h ├── portblas_helper.h ├── sb_handle │ ├── kernel_constructor.h │ ├── portblas_handle.h │ └── temp_memory_pool.h └── views │ └── view.h ├── python_generator ├── gen ├── py_gen_blas_gemm_launcher.py ├── py_gen_blas_ops.py ├── py_gen_blas_reduction.py └── py_gen_blas_rotg.py ├── run_docker.sh ├── samples ├── CMakeLists.txt ├── FindPORTBLAS.cmake ├── README.md ├── gemm.cpp ├── gemv.cpp ├── symm.cpp └── util.hpp ├── src ├── CMakeLists.txt ├── container │ └── sycl_iterator.hpp ├── interface │ ├── CMakeLists.txt │ ├── blas1 │ │ ├── CMakeLists.txt │ │ ├── asum.cpp.in │ │ ├── asum_return.cpp.in │ │ ├── axpy.cpp.in │ │ ├── backend │ │ │ ├── amd_gpu.hpp │ │ │ ├── backend.hpp │ │ │ ├── default.hpp │ │ │ ├── intel_gpu.hpp │ │ │ └── nvidia_gpu.hpp │ │ ├── copy.cpp.in │ │ ├── dot.cpp.in │ │ ├── dot_return.cpp.in │ │ ├── iamax.cpp.in │ │ ├── iamax_return.cpp.in │ │ ├── iamin.cpp.in │ │ ├── iamin_return.cpp.in │ │ ├── nrm2.cpp.in │ │ ├── nrm2_return.cpp.in │ │ ├── rot.cpp.in │ │ ├── rotg.cpp.in │ │ ├── rotg_return.cpp.in │ │ ├── rotm.cpp.in │ │ ├── rotmg.cpp.in │ │ ├── scal.cpp.in │ │ ├── sdsdot.cpp.in │ │ ├── sdsdot_return.cpp.in │ │ └── swap.cpp.in │ ├── blas1_interface.hpp │ ├── blas2 │ │ ├── CMakeLists.txt │ │ ├── backend │ │ │ ├── amd_gpu.hpp │ │ │ ├── backend.hpp │ │ │ ├── default.hpp │ │ │ ├── intel_gpu.hpp │ │ │ └── nvidia_gpu.hpp │ │ ├── gbmv.cpp.in │ │ ├── gemv.cpp.in │ │ ├── ger.cpp.in │ │ ├── sbmv.cpp.in │ │ ├── spmv.cpp.in │ │ ├── spr.cpp.in │ │ ├── spr2.cpp.in │ │ ├── symv.cpp.in │ │ ├── syr.cpp.in │ │ ├── syr2.cpp.in │ │ ├── tbmv.cpp.in │ │ ├── tbsv.cpp.in │ │ ├── tpmv.cpp.in │ │ ├── tpsv.cpp.in │ │ ├── trmv.cpp.in │ │ └── trsv.cpp.in │ ├── blas2_interface.hpp │ ├── blas3 │ │ ├── CMakeLists.txt │ │ ├── backend │ │ │ ├── amd_gpu.hpp │ │ │ ├── backend.hpp │ │ │ ├── default.hpp │ │ │ ├── intel_gpu.hpp │ │ │ └── nvidia_gpu.hpp │ │ ├── gemm.cpp.in │ │ ├── gemm_launcher.cpp.in │ │ ├── symm.cpp.in │ │ └── trsm.cpp.in │ ├── blas3_interface.hpp │ ├── extension │ │ ├── CMakeLists.txt │ │ ├── axpy_batch.cpp.in │ │ ├── backend │ │ │ ├── amd_gpu.hpp │ │ │ ├── backend.hpp │ │ │ ├── default.hpp │ │ │ ├── intel_gpu.hpp │ │ │ └── nvidia_gpu.hpp │ │ ├── matcopy.cpp.in │ │ ├── matcopy_batch.cpp.in │ │ ├── omatadd.cpp.in │ │ ├── omatadd_batch.cpp.in │ │ ├── reduction.cpp.in │ │ └── transpose.cpp.in │ ├── extension_interface.hpp │ ├── gemm_interface.hpp │ ├── gemm_launcher.hpp │ ├── reduction_interface.hpp │ ├── symm_interface.hpp │ └── trsm_interface.hpp ├── operations │ ├── blas1 │ │ ├── IndexMaxMin.hpp │ │ └── WGAtomicReduction.hpp │ ├── blas1_trees.hpp │ ├── blas2 │ │ ├── gbmv.hpp │ │ ├── gemv.hpp │ │ ├── ger.hpp │ │ ├── sbmv.hpp │ │ ├── spr.hpp │ │ ├── tbmv.hpp │ │ ├── txsv.hpp │ │ └── xpmv.hpp │ ├── blas2_trees.hpp │ ├── blas3 │ │ ├── gemm_common.hpp │ │ ├── gemm_interleaved.hpp │ │ ├── gemm_load_store.hpp │ │ ├── gemm_load_store_complex.hpp │ │ ├── gemm_load_store_joint_matrix.hpp │ │ ├── gemm_local.hpp │ │ ├── gemm_local_joint_matrix.hpp │ │ ├── gemm_no_local_full_vec.hpp │ │ ├── gemm_no_local_partial_vec.hpp │ │ ├── gemm_partial_local.hpp │ │ ├── gemm_ref.hpp │ │ └── trsm.hpp │ ├── blas3_trees.hpp │ ├── blas_constants.hpp │ ├── blas_operators.hpp │ └── extension │ │ ├── axpy_batch.hpp │ │ ├── matcopy_batch.hpp │ │ ├── reduction.hpp │ │ └── transpose.hpp ├── portblas.hpp ├── sb_handle │ ├── kernel_constructor.hpp │ ├── portblas_handle.hpp │ └── temp_memory_pool.hpp └── views │ ├── view.hpp │ └── view_sycl.hpp ├── test ├── .gitignore ├── CMakeLists.txt ├── README.md ├── blas_test.hpp ├── blas_test_macros.hpp ├── exprtest │ ├── CMakeLists.txt │ ├── blas1_axpy_copy_test.cpp │ ├── blas1_iface_test.cpp │ ├── blas1_scal_asum_test.cpp │ ├── collapse_nested_tuple.cpp │ └── main.cpp └── unittest │ ├── CMakeLists.txt │ ├── blas1 │ ├── blas1_asum_test.cpp │ ├── blas1_axpy_test.cpp │ ├── blas1_copy_test.cpp │ ├── blas1_dot_test.cpp │ ├── blas1_iamax_test.cpp │ ├── blas1_iamin_test.cpp │ ├── blas1_iaminmax_common.hpp │ ├── blas1_nrm2_test.cpp │ ├── blas1_rot_test.cpp │ ├── blas1_rotg_test.cpp │ ├── blas1_rotm_test.cpp │ ├── blas1_rotmg_test.cpp │ ├── blas1_scal_test.cpp │ ├── blas1_sdsdot_test.cpp │ └── blas1_swap_test.cpp │ ├── blas2 │ ├── blas2_gbmv_test.cpp │ ├── blas2_gemv_test.cpp │ ├── blas2_ger_test.cpp │ ├── blas2_sbmv_test.cpp │ ├── blas2_spmv_test.cpp │ ├── blas2_spr2_test.cpp │ ├── blas2_spr_test.cpp │ ├── blas2_symv_test.cpp │ ├── blas2_syr2_test.cpp │ ├── blas2_syr_test.cpp │ ├── blas2_tbmv_test.cpp │ ├── blas2_tbsv_test.cpp │ ├── blas2_tpmv_test.cpp │ ├── blas2_tpsv_test.cpp │ ├── blas2_trmv_test.cpp │ └── blas2_trsv_test.cpp │ ├── blas3 │ ├── blas3_gemm_batched_test.cpp │ ├── blas3_gemm_common.hpp │ ├── blas3_gemm_tall_skinny_test.cpp │ ├── blas3_gemm_test.cpp │ ├── blas3_symm_test.cpp │ └── blas3_trsm_test.cpp │ ├── buffers │ └── sycl_buffer_test.cpp │ ├── extension │ ├── axpy_batch_test.cpp │ ├── extension_reference.hpp │ ├── omatadd_batched_test.cpp │ ├── omatadd_test.cpp │ ├── omatcopy2_test.cpp │ ├── omatcopy_batched_test.cpp │ ├── omatcopy_test.cpp │ ├── reduction_test.cpp │ └── transpose_test.cpp │ ├── joint_matrix │ ├── CMakeLists.txt │ ├── bfloat16_float_16_16_16.cpp │ ├── bfloat16_float_32_8_16.cpp │ ├── bfloat16_float_8_32_16.cpp │ ├── cmake │ │ └── FindPORTBLAS.cmake │ ├── half_float_16_16_16.cpp │ ├── half_float_32_8_16.cpp │ ├── half_float_8_32_16.cpp │ ├── half_half_16_16_16.cpp │ ├── half_half_32_8_16.cpp │ ├── half_half_8_32_16.cpp │ ├── joint_matrix_common.hpp │ ├── launch_gemm.hpp │ └── tf32_float_16_16_8.cpp │ └── main.cpp └── tools └── auto_tuner ├── CMakeLists.txt ├── README.md ├── gen ├── amd_gpu.json ├── default.json ├── generate_combinations.py ├── intel_gpu.json └── nvidia_gpu.json ├── include ├── gemm_tuner.hpp ├── reference_gemm.hpp ├── tune.hpp ├── tune_impl.hpp ├── tuner_types.hpp └── utils.hpp └── src ├── tune_all.cpp ├── tune_nn.cpp ├── tune_nt.cpp ├── tune_tn.cpp └── tune_tt.cpp /.clang-format: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/.clang-format -------------------------------------------------------------------------------- /.github/dependabot.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/.github/dependabot.yml -------------------------------------------------------------------------------- /.github/workflows/scorecard.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/.github/workflows/scorecard.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/.gitmodules -------------------------------------------------------------------------------- /.scripts/build_OpenBLAS.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/.scripts/build_OpenBLAS.sh -------------------------------------------------------------------------------- /.scripts/build_dpcpp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/.scripts/build_dpcpp.sh -------------------------------------------------------------------------------- /.scripts/build_triSYCL.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/.scripts/build_triSYCL.sh -------------------------------------------------------------------------------- /.scripts/install_intel_opencl.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/.scripts/install_intel_opencl.sh -------------------------------------------------------------------------------- /CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/CMakeLists.txt -------------------------------------------------------------------------------- /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /Contributors.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/Contributors.md -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/Dockerfile -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/LICENSE -------------------------------------------------------------------------------- /NOTICE: -------------------------------------------------------------------------------- 1 | portBLAS 2 | Copyright (C) Codeplay Software Limited. 3 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/README.md -------------------------------------------------------------------------------- /SECURITY.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/SECURITY.md -------------------------------------------------------------------------------- /benchmark/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/CMakeLists.txt -------------------------------------------------------------------------------- /benchmark/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/README.md -------------------------------------------------------------------------------- /benchmark/bench_info.cc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/bench_info.cc -------------------------------------------------------------------------------- /benchmark/clBench/acl/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/acl/CMakeLists.txt -------------------------------------------------------------------------------- /benchmark/clBench/acl/blas3/gemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/acl/blas3/gemm.cpp -------------------------------------------------------------------------------- /benchmark/clBench/acl/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/acl/main.cpp -------------------------------------------------------------------------------- /benchmark/clBench/acl/utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/acl/utils.hpp -------------------------------------------------------------------------------- /benchmark/clBench/clblas/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblas/CMakeLists.txt -------------------------------------------------------------------------------- /benchmark/clBench/clblas/blas2/tbsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblas/blas2/tbsv.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblas/blas2/trsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblas/blas2/trsv.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblas/blas3/trsm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblas/blas3/trsm.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblas/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblas/main.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblas/utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblas/utils.hpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/CMakeLists.txt -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas1/asum.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas1/asum.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas1/axpy.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas1/axpy.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas1/dot.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas1/dot.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas1/iamax.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas1/iamax.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas1/iamin.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas1/iamin.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas1/nrm2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas1/nrm2.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas1/scal.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas1/scal.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/gbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/gbmv.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/gemv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/gemv.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/ger.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/ger.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/sbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/sbmv.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/spr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/spr.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/spr2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/spr2.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/symv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/symv.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/syr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/syr.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/syr2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/syr2.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/tbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/tbmv.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/trmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/trmv.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas2/trsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas2/trsv.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas3/gemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas3/gemm.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas3/gemm_batched.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas3/gemm_batched.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas3/symm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas3/symm.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/blas3/trsm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/blas3/trsm.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/main.cpp -------------------------------------------------------------------------------- /benchmark/clBench/clblast/utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clblast/utils.hpp -------------------------------------------------------------------------------- /benchmark/clBench/clwrap.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/clBench/clwrap.hpp -------------------------------------------------------------------------------- /benchmark/config_csv/blas1/blas1_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas1/blas1_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas1/copy/copy_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas1/copy/copy_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/gbmv/gbmv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/gbmv/gbmv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/gemv/gemv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/gemv/gemv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/ger/ger_square.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/ger/ger_square.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/sbmv/sbmv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/sbmv/sbmv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/spmv/spmv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/spmv/spmv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/spr/spr_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/spr/spr_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/spr2/spr2_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/spr2/spr2_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/symv/symv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/symv/symv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/syr/syr_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/syr/syr_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/syr2/sry2_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/syr2/sry2_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/tbmv/tbmv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/tbmv/tbmv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/tbsv/tbsv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/tbsv/tbsv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/tpmv/tpmv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/tpmv/tpmv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/tpsv/tpsv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/tpsv/tpsv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/trmv/trmv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/trmv/trmv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas2/trsv/trsv_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas2/trsv/trsv_powersof2.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_im2col_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_im2col_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_im2col_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_im2col_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_im2col_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_im2col_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_wino_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_wino_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_wino_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_wino_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_wino_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_alexnet_wino_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_resnet_im2col_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_resnet_im2col_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_resnet_im2col_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_resnet_im2col_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_resnet_im2col_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_resnet_im2col_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_resnet_wino_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_resnet_wino_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_resnet_wino_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_resnet_wino_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_resnet_wino_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_resnet_wino_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_vgg_im2col_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_vgg_im2col_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_vgg_im2col_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_vgg_im2col_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_vgg_im2col_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_vgg_im2col_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_vgg_wino_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_vgg_wino_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_vgg_wino_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_vgg_wino_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_inference_vgg_wino_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_inference_vgg_wino_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_square.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_square.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_alexnet_im2col_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_alexnet_im2col_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_alexnet_im2col_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_alexnet_im2col_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_alexnet_im2col_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_alexnet_im2col_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_alexnet_wino_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_alexnet_wino_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_alexnet_wino_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_alexnet_wino_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_alexnet_wino_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_alexnet_wino_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_resnet_im2col_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_resnet_im2col_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_resnet_im2col_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_resnet_im2col_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_resnet_im2col_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_resnet_im2col_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_resnet_wino_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_resnet_wino_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_resnet_wino_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_resnet_wino_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_resnet_wino_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_resnet_wino_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_vgg_im2col_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_vgg_im2col_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_vgg_im2col_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_vgg_im2col_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_vgg_im2col_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_vgg_im2col_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_vgg_wino_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_vgg_wino_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_vgg_wino_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_vgg_wino_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/gemm_training_vgg_wino_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/gemm_training_vgg_wino_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/language_models/gemm_inference_bert.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/language_models/gemm_inference_bert.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/language_models/gemm_inference_gpt_j_2016_32.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/language_models/gemm_inference_gpt_j_2016_32.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/language_models/gemm_inference_gpt_j_32_32.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/language_models/gemm_inference_gpt_j_32_32.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/language_models/gemm_inference_transformer.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/language_models/gemm_inference_transformer.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/language_models/gemm_training_bert_bkfil.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/language_models/gemm_training_bert_bkfil.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/language_models/gemm_training_bert_bkin.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/language_models/gemm_training_bert_bkin.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/language_models/gemm_training_bert_fwd.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/language_models/gemm_training_bert_fwd.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm/language_models/gemm_training_transformer.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm/language_models/gemm_training_transformer.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm_batched/gemm_batched_interleaved.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm_batched/gemm_batched_interleaved.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm_batched_strided/gemm_batched_interleaved.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm_batched_strided/gemm_batched_interleaved.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_inference_bert.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_inference_bert.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_inference_gpt_j_2016_32.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_inference_gpt_j_2016_32.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_inference_gpt_j_32_32.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_inference_gpt_j_32_32.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_inference_transformer.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_inference_transformer.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_training_bert.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_training_bert.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_training_transformer.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/gemm_batched_strided/language_models/gemm_batched_strided_training_transformer.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/symm/symm_square.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/symm/symm_square.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/syr2k/syr2k_square.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/syr2k/syr2k_square.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/syrk/syrk_square.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/syrk/syrk_square.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trmm/trmm_large.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trmm/trmm_large.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trmm/trmm_small.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trmm/trmm_small.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trmm/trmm_square.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trmm/trmm_square.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trmm/trmm_variations.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trmm/trmm_variations.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trsm/trsm_large.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trsm/trsm_large.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trsm/trsm_small.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trsm/trsm_small.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trsm/trsm_square.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trsm/trsm_square.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trsm/trsm_variations.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trsm/trsm_variations.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trsm_batched/trsm_large.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trsm_batched/trsm_large.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trsm_batched/trsm_small.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trsm_batched/trsm_small.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trsm_batched/trsm_square.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trsm_batched/trsm_square.csv -------------------------------------------------------------------------------- /benchmark/config_csv/blas3/trsm_batched/trsm_variations.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/blas3/trsm_batched/trsm_variations.csv -------------------------------------------------------------------------------- /benchmark/config_csv/extension/reduction/reduction_powersof2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/config_csv/extension/reduction/reduction_powersof2.csv -------------------------------------------------------------------------------- /benchmark/cublas/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/CMakeLists.txt -------------------------------------------------------------------------------- /benchmark/cublas/blas1/asum.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas1/asum.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas1/axpy.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas1/axpy.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas1/dot.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas1/dot.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas1/iamax.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas1/iamax.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas1/iamin.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas1/iamin.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas1/nrm2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas1/nrm2.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas1/rotg.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas1/rotg.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas1/rotm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas1/rotm.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas1/rotmg.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas1/rotmg.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas1/scal.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas1/scal.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/gbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/gbmv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/gemv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/gemv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/ger.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/ger.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/sbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/sbmv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/spmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/spmv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/spr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/spr.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/spr2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/spr2.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/symv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/symv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/syr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/syr.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/syr2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/syr2.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/tbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/tbmv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/tbsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/tbsv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/tpmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/tpmv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/tpsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/tpsv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/trmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/trmv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas2/trsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas2/trsv.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas3/gemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas3/gemm.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas3/gemm_batched.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas3/gemm_batched.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas3/gemm_batched_strided.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas3/gemm_batched_strided.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas3/symm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas3/symm.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas3/syr2k.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas3/syr2k.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas3/syrk.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas3/syrk.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas3/trmm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas3/trmm.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas3/trsm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas3/trsm.cpp -------------------------------------------------------------------------------- /benchmark/cublas/blas3/trsm_batched.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/blas3/trsm_batched.cpp -------------------------------------------------------------------------------- /benchmark/cublas/extension/omatadd.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/extension/omatadd.cpp -------------------------------------------------------------------------------- /benchmark/cublas/extension/omatcopy.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/extension/omatcopy.cpp -------------------------------------------------------------------------------- /benchmark/cublas/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/main.cpp -------------------------------------------------------------------------------- /benchmark/cublas/utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/cublas/utils.hpp -------------------------------------------------------------------------------- /benchmark/gen_param.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/gen_param.py -------------------------------------------------------------------------------- /benchmark/make_git_config.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/make_git_config.bat -------------------------------------------------------------------------------- /benchmark/make_git_config.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/make_git_config.sh -------------------------------------------------------------------------------- /benchmark/portblas/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/CMakeLists.txt -------------------------------------------------------------------------------- /benchmark/portblas/blas1/asum.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/asum.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/axpy.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/axpy.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/copy.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/copy.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/dot.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/dot.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/iamax.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/iamax.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/iamin.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/iamin.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/nrm2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/nrm2.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/rotg.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/rotg.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/rotm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/rotm.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/rotmg.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/rotmg.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/scal.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/scal.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas1/sdsdot.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas1/sdsdot.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/gbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/gbmv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/gemv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/gemv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/ger.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/ger.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/sbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/sbmv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/spmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/spmv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/spr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/spr.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/spr2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/spr2.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/symv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/symv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/syr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/syr.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/syr2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/syr2.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/tbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/tbmv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/tbsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/tbsv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/tpmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/tpmv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/tpsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/tpsv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/trmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/trmv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas2/trsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas2/trsv.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas3/gemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas3/gemm.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas3/gemm_batched.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas3/gemm_batched.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas3/gemm_batched_strided.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas3/gemm_batched_strided.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas3/symm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas3/symm.cpp -------------------------------------------------------------------------------- /benchmark/portblas/blas3/trsm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/blas3/trsm.cpp -------------------------------------------------------------------------------- /benchmark/portblas/extension/axpy_batch.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/extension/axpy_batch.cpp -------------------------------------------------------------------------------- /benchmark/portblas/extension/omatadd.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/extension/omatadd.cpp -------------------------------------------------------------------------------- /benchmark/portblas/extension/omatadd_batched.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/extension/omatadd_batched.cpp -------------------------------------------------------------------------------- /benchmark/portblas/extension/omatcopy.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/extension/omatcopy.cpp -------------------------------------------------------------------------------- /benchmark/portblas/extension/omatcopy2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/extension/omatcopy2.cpp -------------------------------------------------------------------------------- /benchmark/portblas/extension/omatcopy_batched.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/extension/omatcopy_batched.cpp -------------------------------------------------------------------------------- /benchmark/portblas/extension/reduction.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/extension/reduction.cpp -------------------------------------------------------------------------------- /benchmark/portblas/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/main.cpp -------------------------------------------------------------------------------- /benchmark/portblas/utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/portblas/utils.hpp -------------------------------------------------------------------------------- /benchmark/rocblas/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/CMakeLists.txt -------------------------------------------------------------------------------- /benchmark/rocblas/blas1/asum.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas1/asum.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas1/axpy.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas1/axpy.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas1/dot.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas1/dot.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas1/iamax.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas1/iamax.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas1/iamin.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas1/iamin.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas1/nrm2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas1/nrm2.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas1/rotg.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas1/rotg.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas1/rotm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas1/rotm.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas1/rotmg.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas1/rotmg.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas1/scal.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas1/scal.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/gbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/gbmv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/gemv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/gemv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/ger.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/ger.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/sbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/sbmv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/spmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/spmv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/spr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/spr.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/spr2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/spr2.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/symv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/symv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/syr.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/syr.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/syr2.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/syr2.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/tbmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/tbmv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/tbsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/tbsv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/tpmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/tpmv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/tpsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/tpsv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/trmv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/trmv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas2/trsv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas2/trsv.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas3/gemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas3/gemm.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas3/gemm_batched.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas3/gemm_batched.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas3/gemm_batched_strided.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas3/gemm_batched_strided.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas3/symm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas3/symm.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas3/syr2k.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas3/syr2k.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas3/syrk.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas3/syrk.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas3/trmm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas3/trmm.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas3/trsm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas3/trsm.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/blas3/trsm_batched.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/blas3/trsm_batched.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/extension/axpy_batch.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/extension/axpy_batch.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/extension/omatadd.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/extension/omatadd.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/extension/omatcopy.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/extension/omatcopy.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/main.cpp -------------------------------------------------------------------------------- /benchmark/rocblas/utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/benchmark/rocblas/utils.hpp -------------------------------------------------------------------------------- /cmake/CmakeFunctionHelper.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/CmakeFunctionHelper.cmake -------------------------------------------------------------------------------- /cmake/Modules/ConfigurePORTBLAS.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/Modules/ConfigurePORTBLAS.cmake -------------------------------------------------------------------------------- /cmake/Modules/FindACL.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/Modules/FindACL.cmake -------------------------------------------------------------------------------- /cmake/Modules/FindCLHPP.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/Modules/FindCLHPP.cmake -------------------------------------------------------------------------------- /cmake/Modules/FindClara.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/Modules/FindClara.cmake -------------------------------------------------------------------------------- /cmake/Modules/FindDPCPP.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/Modules/FindDPCPP.cmake -------------------------------------------------------------------------------- /cmake/Modules/FindSB_CLBlast.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/Modules/FindSB_CLBlast.cmake -------------------------------------------------------------------------------- /cmake/Modules/FindSystemBLAS.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/Modules/FindSystemBLAS.cmake -------------------------------------------------------------------------------- /cmake/Modules/Findnpy.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/Modules/Findnpy.cmake -------------------------------------------------------------------------------- /cmake/Modules/SYCL.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/Modules/SYCL.cmake -------------------------------------------------------------------------------- /cmake/templates/CMakeLists.txt.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/templates/CMakeLists.txt.in -------------------------------------------------------------------------------- /cmake/templates/GBench.txt.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/templates/GBench.txt.in -------------------------------------------------------------------------------- /cmake/templates/GTest.txt.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/cmake/templates/GTest.txt.in -------------------------------------------------------------------------------- /common/include/common/benchmark_cli_args.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/benchmark_cli_args.hpp -------------------------------------------------------------------------------- /common/include/common/benchmark_identifier.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/benchmark_identifier.hpp -------------------------------------------------------------------------------- /common/include/common/benchmark_names.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/benchmark_names.hpp -------------------------------------------------------------------------------- /common/include/common/blas1_state_counters.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/blas1_state_counters.hpp -------------------------------------------------------------------------------- /common/include/common/blas2_state_counters.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/blas2_state_counters.hpp -------------------------------------------------------------------------------- /common/include/common/blas3_state_counters.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/blas3_state_counters.hpp -------------------------------------------------------------------------------- /common/include/common/blas_extension_state_counters.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/blas_extension_state_counters.hpp -------------------------------------------------------------------------------- /common/include/common/cli_device_selector.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/cli_device_selector.hpp -------------------------------------------------------------------------------- /common/include/common/common_utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/common_utils.hpp -------------------------------------------------------------------------------- /common/include/common/extract_vendor_type.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/extract_vendor_type.hpp -------------------------------------------------------------------------------- /common/include/common/float_comparison.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/float_comparison.hpp -------------------------------------------------------------------------------- /common/include/common/print_queue_information.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/print_queue_information.hpp -------------------------------------------------------------------------------- /common/include/common/set_benchmark_label.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/set_benchmark_label.hpp -------------------------------------------------------------------------------- /common/include/common/system_reference_blas.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/common/include/common/system_reference_blas.hpp -------------------------------------------------------------------------------- /doc/AddingBlas3Op.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/doc/AddingBlas3Op.md -------------------------------------------------------------------------------- /doc/Autotuner.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/doc/Autotuner.md -------------------------------------------------------------------------------- /doc/Doxyfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/doc/Doxyfile -------------------------------------------------------------------------------- /doc/Gemm.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/doc/Gemm.md -------------------------------------------------------------------------------- /doc/MissingFeatures.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/doc/MissingFeatures.md -------------------------------------------------------------------------------- /doc/Reduction.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/doc/Reduction.md -------------------------------------------------------------------------------- /external/cblas/include/cblas.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/external/cblas/include/cblas.h -------------------------------------------------------------------------------- /external/clara/include/clara.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/external/clara/include/clara.hpp -------------------------------------------------------------------------------- /include/blas_meta.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/blas_meta.h -------------------------------------------------------------------------------- /include/container/sycl_iterator.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/container/sycl_iterator.h -------------------------------------------------------------------------------- /include/interface/blas1_interface.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/interface/blas1_interface.h -------------------------------------------------------------------------------- /include/interface/blas2_interface.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/interface/blas2_interface.h -------------------------------------------------------------------------------- /include/interface/blas3_interface.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/interface/blas3_interface.h -------------------------------------------------------------------------------- /include/interface/extension_interface.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/interface/extension_interface.h -------------------------------------------------------------------------------- /include/interface/gemm_launcher.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/interface/gemm_launcher.h -------------------------------------------------------------------------------- /include/interface/reduction_interface.h: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /include/operations/blas1_trees.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/operations/blas1_trees.h -------------------------------------------------------------------------------- /include/operations/blas2_trees.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/operations/blas2_trees.h -------------------------------------------------------------------------------- /include/operations/blas3_trees.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/operations/blas3_trees.h -------------------------------------------------------------------------------- /include/operations/blas_constants.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/operations/blas_constants.h -------------------------------------------------------------------------------- /include/operations/blas_operators.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/operations/blas_operators.h -------------------------------------------------------------------------------- /include/operations/extension/axpy_batch.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/operations/extension/axpy_batch.h -------------------------------------------------------------------------------- /include/operations/extension/matcopy_batch.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/operations/extension/matcopy_batch.h -------------------------------------------------------------------------------- /include/operations/extension/reduction.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/operations/extension/reduction.h -------------------------------------------------------------------------------- /include/operations/extension/transpose.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/operations/extension/transpose.h -------------------------------------------------------------------------------- /include/portblas.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/portblas.h -------------------------------------------------------------------------------- /include/portblas_helper.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/portblas_helper.h -------------------------------------------------------------------------------- /include/sb_handle/kernel_constructor.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/sb_handle/kernel_constructor.h -------------------------------------------------------------------------------- /include/sb_handle/portblas_handle.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/sb_handle/portblas_handle.h -------------------------------------------------------------------------------- /include/sb_handle/temp_memory_pool.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/sb_handle/temp_memory_pool.h -------------------------------------------------------------------------------- /include/views/view.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/include/views/view.h -------------------------------------------------------------------------------- /python_generator/gen: -------------------------------------------------------------------------------- 1 | @ip1@ 2 | -------------------------------------------------------------------------------- /python_generator/py_gen_blas_gemm_launcher.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/python_generator/py_gen_blas_gemm_launcher.py -------------------------------------------------------------------------------- /python_generator/py_gen_blas_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/python_generator/py_gen_blas_ops.py -------------------------------------------------------------------------------- /python_generator/py_gen_blas_reduction.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/python_generator/py_gen_blas_reduction.py -------------------------------------------------------------------------------- /python_generator/py_gen_blas_rotg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/python_generator/py_gen_blas_rotg.py -------------------------------------------------------------------------------- /run_docker.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/run_docker.sh -------------------------------------------------------------------------------- /samples/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/samples/CMakeLists.txt -------------------------------------------------------------------------------- /samples/FindPORTBLAS.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/samples/FindPORTBLAS.cmake -------------------------------------------------------------------------------- /samples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/samples/README.md -------------------------------------------------------------------------------- /samples/gemm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/samples/gemm.cpp -------------------------------------------------------------------------------- /samples/gemv.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/samples/gemv.cpp -------------------------------------------------------------------------------- /samples/symm.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/samples/symm.cpp -------------------------------------------------------------------------------- /samples/util.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/samples/util.hpp -------------------------------------------------------------------------------- /src/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/CMakeLists.txt -------------------------------------------------------------------------------- /src/container/sycl_iterator.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/container/sycl_iterator.hpp -------------------------------------------------------------------------------- /src/interface/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/CMakeLists.txt -------------------------------------------------------------------------------- /src/interface/blas1/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/CMakeLists.txt -------------------------------------------------------------------------------- /src/interface/blas1/asum.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/asum.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/asum_return.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/asum_return.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/axpy.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/axpy.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/backend/amd_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/backend/amd_gpu.hpp -------------------------------------------------------------------------------- /src/interface/blas1/backend/backend.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/backend/backend.hpp -------------------------------------------------------------------------------- /src/interface/blas1/backend/default.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/backend/default.hpp -------------------------------------------------------------------------------- /src/interface/blas1/backend/intel_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/backend/intel_gpu.hpp -------------------------------------------------------------------------------- /src/interface/blas1/backend/nvidia_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/backend/nvidia_gpu.hpp -------------------------------------------------------------------------------- /src/interface/blas1/copy.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/copy.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/dot.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/dot.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/dot_return.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/dot_return.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/iamax.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/iamax.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/iamax_return.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/iamax_return.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/iamin.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/iamin.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/iamin_return.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/iamin_return.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/nrm2.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/nrm2.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/nrm2_return.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/nrm2_return.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/rot.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/rot.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/rotg.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/rotg.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/rotg_return.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/rotg_return.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/rotm.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/rotm.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/rotmg.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/rotmg.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/scal.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/scal.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/sdsdot.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/sdsdot.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/sdsdot_return.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/sdsdot_return.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1/swap.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1/swap.cpp.in -------------------------------------------------------------------------------- /src/interface/blas1_interface.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas1_interface.hpp -------------------------------------------------------------------------------- /src/interface/blas2/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/CMakeLists.txt -------------------------------------------------------------------------------- /src/interface/blas2/backend/amd_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/backend/amd_gpu.hpp -------------------------------------------------------------------------------- /src/interface/blas2/backend/backend.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/backend/backend.hpp -------------------------------------------------------------------------------- /src/interface/blas2/backend/default.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/backend/default.hpp -------------------------------------------------------------------------------- /src/interface/blas2/backend/intel_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/backend/intel_gpu.hpp -------------------------------------------------------------------------------- /src/interface/blas2/backend/nvidia_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/backend/nvidia_gpu.hpp -------------------------------------------------------------------------------- /src/interface/blas2/gbmv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/gbmv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/gemv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/gemv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/ger.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/ger.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/sbmv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/sbmv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/spmv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/spmv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/spr.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/spr.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/spr2.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/spr2.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/symv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/symv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/syr.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/syr.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/syr2.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/syr2.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/tbmv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/tbmv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/tbsv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/tbsv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/tpmv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/tpmv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/tpsv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/tpsv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/trmv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/trmv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2/trsv.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2/trsv.cpp.in -------------------------------------------------------------------------------- /src/interface/blas2_interface.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas2_interface.hpp -------------------------------------------------------------------------------- /src/interface/blas3/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3/CMakeLists.txt -------------------------------------------------------------------------------- /src/interface/blas3/backend/amd_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3/backend/amd_gpu.hpp -------------------------------------------------------------------------------- /src/interface/blas3/backend/backend.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3/backend/backend.hpp -------------------------------------------------------------------------------- /src/interface/blas3/backend/default.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3/backend/default.hpp -------------------------------------------------------------------------------- /src/interface/blas3/backend/intel_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3/backend/intel_gpu.hpp -------------------------------------------------------------------------------- /src/interface/blas3/backend/nvidia_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3/backend/nvidia_gpu.hpp -------------------------------------------------------------------------------- /src/interface/blas3/gemm.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3/gemm.cpp.in -------------------------------------------------------------------------------- /src/interface/blas3/gemm_launcher.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3/gemm_launcher.cpp.in -------------------------------------------------------------------------------- /src/interface/blas3/symm.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3/symm.cpp.in -------------------------------------------------------------------------------- /src/interface/blas3/trsm.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3/trsm.cpp.in -------------------------------------------------------------------------------- /src/interface/blas3_interface.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/blas3_interface.hpp -------------------------------------------------------------------------------- /src/interface/extension/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/CMakeLists.txt -------------------------------------------------------------------------------- /src/interface/extension/axpy_batch.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/axpy_batch.cpp.in -------------------------------------------------------------------------------- /src/interface/extension/backend/amd_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/backend/amd_gpu.hpp -------------------------------------------------------------------------------- /src/interface/extension/backend/backend.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/backend/backend.hpp -------------------------------------------------------------------------------- /src/interface/extension/backend/default.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/backend/default.hpp -------------------------------------------------------------------------------- /src/interface/extension/backend/intel_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/backend/intel_gpu.hpp -------------------------------------------------------------------------------- /src/interface/extension/backend/nvidia_gpu.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/backend/nvidia_gpu.hpp -------------------------------------------------------------------------------- /src/interface/extension/matcopy.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/matcopy.cpp.in -------------------------------------------------------------------------------- /src/interface/extension/matcopy_batch.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/matcopy_batch.cpp.in -------------------------------------------------------------------------------- /src/interface/extension/omatadd.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/omatadd.cpp.in -------------------------------------------------------------------------------- /src/interface/extension/omatadd_batch.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/omatadd_batch.cpp.in -------------------------------------------------------------------------------- /src/interface/extension/reduction.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/reduction.cpp.in -------------------------------------------------------------------------------- /src/interface/extension/transpose.cpp.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension/transpose.cpp.in -------------------------------------------------------------------------------- /src/interface/extension_interface.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/extension_interface.hpp -------------------------------------------------------------------------------- /src/interface/gemm_interface.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/gemm_interface.hpp -------------------------------------------------------------------------------- /src/interface/gemm_launcher.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/gemm_launcher.hpp -------------------------------------------------------------------------------- /src/interface/reduction_interface.hpp: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/interface/symm_interface.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/symm_interface.hpp -------------------------------------------------------------------------------- /src/interface/trsm_interface.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/interface/trsm_interface.hpp -------------------------------------------------------------------------------- /src/operations/blas1/IndexMaxMin.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas1/IndexMaxMin.hpp -------------------------------------------------------------------------------- /src/operations/blas1/WGAtomicReduction.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas1/WGAtomicReduction.hpp -------------------------------------------------------------------------------- /src/operations/blas1_trees.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas1_trees.hpp -------------------------------------------------------------------------------- /src/operations/blas2/gbmv.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas2/gbmv.hpp -------------------------------------------------------------------------------- /src/operations/blas2/gemv.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas2/gemv.hpp -------------------------------------------------------------------------------- /src/operations/blas2/ger.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas2/ger.hpp -------------------------------------------------------------------------------- /src/operations/blas2/sbmv.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas2/sbmv.hpp -------------------------------------------------------------------------------- /src/operations/blas2/spr.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas2/spr.hpp -------------------------------------------------------------------------------- /src/operations/blas2/tbmv.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas2/tbmv.hpp -------------------------------------------------------------------------------- /src/operations/blas2/txsv.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas2/txsv.hpp -------------------------------------------------------------------------------- /src/operations/blas2/xpmv.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas2/xpmv.hpp -------------------------------------------------------------------------------- /src/operations/blas2_trees.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas2_trees.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_common.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_common.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_interleaved.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_interleaved.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_load_store.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_load_store.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_load_store_complex.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_load_store_complex.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_load_store_joint_matrix.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_load_store_joint_matrix.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_local.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_local.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_local_joint_matrix.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_local_joint_matrix.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_no_local_full_vec.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_no_local_full_vec.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_no_local_partial_vec.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_no_local_partial_vec.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_partial_local.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_partial_local.hpp -------------------------------------------------------------------------------- /src/operations/blas3/gemm_ref.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/gemm_ref.hpp -------------------------------------------------------------------------------- /src/operations/blas3/trsm.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3/trsm.hpp -------------------------------------------------------------------------------- /src/operations/blas3_trees.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas3_trees.hpp -------------------------------------------------------------------------------- /src/operations/blas_constants.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas_constants.hpp -------------------------------------------------------------------------------- /src/operations/blas_operators.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/blas_operators.hpp -------------------------------------------------------------------------------- /src/operations/extension/axpy_batch.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/extension/axpy_batch.hpp -------------------------------------------------------------------------------- /src/operations/extension/matcopy_batch.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/extension/matcopy_batch.hpp -------------------------------------------------------------------------------- /src/operations/extension/reduction.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/extension/reduction.hpp -------------------------------------------------------------------------------- /src/operations/extension/transpose.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/operations/extension/transpose.hpp -------------------------------------------------------------------------------- /src/portblas.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/portblas.hpp -------------------------------------------------------------------------------- /src/sb_handle/kernel_constructor.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/sb_handle/kernel_constructor.hpp -------------------------------------------------------------------------------- /src/sb_handle/portblas_handle.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/sb_handle/portblas_handle.hpp -------------------------------------------------------------------------------- /src/sb_handle/temp_memory_pool.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/sb_handle/temp_memory_pool.hpp -------------------------------------------------------------------------------- /src/views/view.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/views/view.hpp -------------------------------------------------------------------------------- /src/views/view_sycl.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/src/views/view_sycl.hpp -------------------------------------------------------------------------------- /test/.gitignore: -------------------------------------------------------------------------------- 1 | include/ 2 | -------------------------------------------------------------------------------- /test/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/CMakeLists.txt -------------------------------------------------------------------------------- /test/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/README.md -------------------------------------------------------------------------------- /test/blas_test.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/blas_test.hpp -------------------------------------------------------------------------------- /test/blas_test_macros.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/blas_test_macros.hpp -------------------------------------------------------------------------------- /test/exprtest/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/exprtest/CMakeLists.txt -------------------------------------------------------------------------------- /test/exprtest/blas1_axpy_copy_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/exprtest/blas1_axpy_copy_test.cpp -------------------------------------------------------------------------------- /test/exprtest/blas1_iface_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/exprtest/blas1_iface_test.cpp -------------------------------------------------------------------------------- /test/exprtest/blas1_scal_asum_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/exprtest/blas1_scal_asum_test.cpp -------------------------------------------------------------------------------- /test/exprtest/collapse_nested_tuple.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/exprtest/collapse_nested_tuple.cpp -------------------------------------------------------------------------------- /test/exprtest/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/exprtest/main.cpp -------------------------------------------------------------------------------- /test/unittest/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/CMakeLists.txt -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_asum_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_asum_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_axpy_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_axpy_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_copy_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_copy_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_dot_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_dot_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_iamax_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_iamax_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_iamin_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_iamin_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_iaminmax_common.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_iaminmax_common.hpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_nrm2_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_nrm2_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_rot_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_rot_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_rotg_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_rotg_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_rotm_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_rotm_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_rotmg_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_rotmg_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_scal_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_scal_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_sdsdot_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_sdsdot_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas1/blas1_swap_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas1/blas1_swap_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_gbmv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_gbmv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_gemv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_gemv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_ger_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_ger_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_sbmv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_sbmv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_spmv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_spmv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_spr2_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_spr2_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_spr_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_spr_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_symv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_symv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_syr2_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_syr2_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_syr_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_syr_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_tbmv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_tbmv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_tbsv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_tbsv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_tpmv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_tpmv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_tpsv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_tpsv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_trmv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_trmv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas2/blas2_trsv_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas2/blas2_trsv_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas3/blas3_gemm_batched_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas3/blas3_gemm_batched_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas3/blas3_gemm_common.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas3/blas3_gemm_common.hpp -------------------------------------------------------------------------------- /test/unittest/blas3/blas3_gemm_tall_skinny_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas3/blas3_gemm_tall_skinny_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas3/blas3_gemm_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas3/blas3_gemm_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas3/blas3_symm_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas3/blas3_symm_test.cpp -------------------------------------------------------------------------------- /test/unittest/blas3/blas3_trsm_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/blas3/blas3_trsm_test.cpp -------------------------------------------------------------------------------- /test/unittest/buffers/sycl_buffer_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/buffers/sycl_buffer_test.cpp -------------------------------------------------------------------------------- /test/unittest/extension/axpy_batch_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/extension/axpy_batch_test.cpp -------------------------------------------------------------------------------- /test/unittest/extension/extension_reference.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/extension/extension_reference.hpp -------------------------------------------------------------------------------- /test/unittest/extension/omatadd_batched_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/extension/omatadd_batched_test.cpp -------------------------------------------------------------------------------- /test/unittest/extension/omatadd_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/extension/omatadd_test.cpp -------------------------------------------------------------------------------- /test/unittest/extension/omatcopy2_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/extension/omatcopy2_test.cpp -------------------------------------------------------------------------------- /test/unittest/extension/omatcopy_batched_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/extension/omatcopy_batched_test.cpp -------------------------------------------------------------------------------- /test/unittest/extension/omatcopy_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/extension/omatcopy_test.cpp -------------------------------------------------------------------------------- /test/unittest/extension/reduction_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/extension/reduction_test.cpp -------------------------------------------------------------------------------- /test/unittest/extension/transpose_test.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/extension/transpose_test.cpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/CMakeLists.txt -------------------------------------------------------------------------------- /test/unittest/joint_matrix/bfloat16_float_16_16_16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/bfloat16_float_16_16_16.cpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/bfloat16_float_32_8_16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/bfloat16_float_32_8_16.cpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/bfloat16_float_8_32_16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/bfloat16_float_8_32_16.cpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/cmake/FindPORTBLAS.cmake: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/cmake/FindPORTBLAS.cmake -------------------------------------------------------------------------------- /test/unittest/joint_matrix/half_float_16_16_16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/half_float_16_16_16.cpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/half_float_32_8_16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/half_float_32_8_16.cpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/half_float_8_32_16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/half_float_8_32_16.cpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/half_half_16_16_16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/half_half_16_16_16.cpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/half_half_32_8_16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/half_half_32_8_16.cpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/half_half_8_32_16.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/half_half_8_32_16.cpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/joint_matrix_common.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/joint_matrix_common.hpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/launch_gemm.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/launch_gemm.hpp -------------------------------------------------------------------------------- /test/unittest/joint_matrix/tf32_float_16_16_8.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/joint_matrix/tf32_float_16_16_8.cpp -------------------------------------------------------------------------------- /test/unittest/main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/test/unittest/main.cpp -------------------------------------------------------------------------------- /tools/auto_tuner/CMakeLists.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/CMakeLists.txt -------------------------------------------------------------------------------- /tools/auto_tuner/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/README.md -------------------------------------------------------------------------------- /tools/auto_tuner/gen/amd_gpu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/gen/amd_gpu.json -------------------------------------------------------------------------------- /tools/auto_tuner/gen/default.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/gen/default.json -------------------------------------------------------------------------------- /tools/auto_tuner/gen/generate_combinations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/gen/generate_combinations.py -------------------------------------------------------------------------------- /tools/auto_tuner/gen/intel_gpu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/gen/intel_gpu.json -------------------------------------------------------------------------------- /tools/auto_tuner/gen/nvidia_gpu.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/gen/nvidia_gpu.json -------------------------------------------------------------------------------- /tools/auto_tuner/include/gemm_tuner.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/include/gemm_tuner.hpp -------------------------------------------------------------------------------- /tools/auto_tuner/include/reference_gemm.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/include/reference_gemm.hpp -------------------------------------------------------------------------------- /tools/auto_tuner/include/tune.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/include/tune.hpp -------------------------------------------------------------------------------- /tools/auto_tuner/include/tune_impl.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/include/tune_impl.hpp -------------------------------------------------------------------------------- /tools/auto_tuner/include/tuner_types.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/include/tuner_types.hpp -------------------------------------------------------------------------------- /tools/auto_tuner/include/utils.hpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/include/utils.hpp -------------------------------------------------------------------------------- /tools/auto_tuner/src/tune_all.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/src/tune_all.cpp -------------------------------------------------------------------------------- /tools/auto_tuner/src/tune_nn.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/src/tune_nn.cpp -------------------------------------------------------------------------------- /tools/auto_tuner/src/tune_nt.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/src/tune_nt.cpp -------------------------------------------------------------------------------- /tools/auto_tuner/src/tune_tn.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/src/tune_tn.cpp -------------------------------------------------------------------------------- /tools/auto_tuner/src/tune_tt.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/codeplaysoftware/portBLAS/HEAD/tools/auto_tuner/src/tune_tt.cpp --------------------------------------------------------------------------------