mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-07-13 10:37:42 +00:00
experimental power analysis branch
This commit is contained in:
Harisankar Sadasivan
0
example/01_gemm/CMakeLists.txt
Normal file → Executable file
0
example/01_gemm/CMakeLists.txt
Normal file → Executable file
0
example/01_gemm/README.md
Normal file → Executable file
0
example/01_gemm/README.md
Normal file → Executable file
0
example/01_gemm/common.hpp
Normal file → Executable file
0
example/01_gemm/common.hpp
Normal file → Executable file
0
example/01_gemm/gemm_dl_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_dl_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_dl_fp32.cpp
Normal file → Executable file
0
example/01_gemm/gemm_dl_fp32.cpp
Normal file → Executable file
0
example/01_gemm/gemm_dl_int4.cpp
Normal file → Executable file
0
example/01_gemm/gemm_dl_int4.cpp
Normal file → Executable file
0
example/01_gemm/gemm_dl_int8.cpp
Normal file → Executable file
0
example/01_gemm/gemm_dl_int8.cpp
Normal file → Executable file
0
example/01_gemm/gemm_dpp_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_dpp_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_wmma_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_wmma_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_bf16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_bf16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_bf16_rtn.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_bf16_rtn.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp16_fp8.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp16_fp8.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp16_v2.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp16_v2.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp64.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp64.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp8.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp8.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp8_bf8.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_fp8_bf8.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_int4.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_int4.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_int8.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_int8.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_lds_direct_load_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_lds_direct_load_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_lds_direct_load_fp32.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_lds_direct_load_fp32.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_skip_b_lds_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_skip_b_lds_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_streamk.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_streamk.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_wavelet_fp16.cpp
Normal file → Executable file
0
example/01_gemm/gemm_xdl_wavelet_fp16.cpp
Normal file → Executable file
0
example/01_gemm/run_gemm_example.inc
Normal file → Executable file
0
example/01_gemm/run_gemm_example.inc
Normal file → Executable file
0
example/02_gemm_bilinear/CMakeLists.txt
Normal file → Executable file
0
example/02_gemm_bilinear/CMakeLists.txt
Normal file → Executable file
0
example/02_gemm_bilinear/README.md
Normal file → Executable file
0
example/02_gemm_bilinear/README.md
Normal file → Executable file
0
example/02_gemm_bilinear/gemm_bilinear_wmma_fp16.cpp
Normal file → Executable file
0
example/02_gemm_bilinear/gemm_bilinear_wmma_fp16.cpp
Normal file → Executable file
0
example/02_gemm_bilinear/gemm_bilinear_wmma_int8.cpp
Normal file → Executable file
0
example/02_gemm_bilinear/gemm_bilinear_wmma_int8.cpp
Normal file → Executable file
0
example/02_gemm_bilinear/gemm_bilinear_xdl_fp16.cpp
Normal file → Executable file
0
example/02_gemm_bilinear/gemm_bilinear_xdl_fp16.cpp
Normal file → Executable file
0
example/03_gemm_bias_relu/CMakeLists.txt
Normal file → Executable file
0
example/03_gemm_bias_relu/CMakeLists.txt
Normal file → Executable file
0
example/03_gemm_bias_relu/README.md
Normal file → Executable file
0
example/03_gemm_bias_relu/README.md
Normal file → Executable file
0
example/03_gemm_bias_relu/gemm_bias_relu_xdl_fp16.cpp
Normal file → Executable file
0
example/03_gemm_bias_relu/gemm_bias_relu_xdl_fp16.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/CMakeLists.txt
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/CMakeLists.txt
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/README.md
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/README.md
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/common.hpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/common.hpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_bf16.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_bf16.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp16.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp16.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp32.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_fp32.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int4.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int4.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int8.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_int8.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_lds_direct_load_fp32.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/gemm_add_add_fastgelu_xdl_lds_direct_load_fp32.cpp
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/run_gemm_add_add_fastgelu_example.inc
Normal file → Executable file
0
example/04_gemm_add_add_fastgelu/run_gemm_add_add_fastgelu_example.inc
Normal file → Executable file
0
example/09_convnd_fwd/CMakeLists.txt
Normal file → Executable file
0
example/09_convnd_fwd/CMakeLists.txt
Normal file → Executable file
0
example/09_convnd_fwd/README.md
Normal file → Executable file
0
example/09_convnd_fwd/README.md
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_common.hpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_common.hpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_dl_common.hpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_dl_common.hpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_dl_fp16.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_dl_fp16.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_dl_fp32.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_dl_fp32.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_dl_int8.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_dl_int8.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_xdl_bf16.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_xdl_bf16.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_xdl_fp16.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_xdl_fp16.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_xdl_fp32.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_xdl_fp32.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_xdl_fp64.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_xdl_fp64.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_xdl_int8.cpp
Normal file → Executable file
0
example/09_convnd_fwd/convnd_fwd_xdl_int8.cpp
Normal file → Executable file
0
example/09_convnd_fwd/run_convnd_fwd_dl_example.inc
Normal file → Executable file
0
example/09_convnd_fwd/run_convnd_fwd_dl_example.inc
Normal file → Executable file
0
example/09_convnd_fwd/run_convnd_fwd_example.inc
Normal file → Executable file
0
example/09_convnd_fwd/run_convnd_fwd_example.inc
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/CMakeLists.txt
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/CMakeLists.txt
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/common.hpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/common.hpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_bf16.cpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_bf16.cpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp16.cpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp16.cpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp32.cpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_fp32.cpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int4.cpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int4.cpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int8.cpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/convnd_fwd_max_xdl_int8.cpp
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/run_convnd_fwd_max_example.inc
Normal file → Executable file
0
example/10_convnd_fwd_multiple_d_multiple_reduce/run_convnd_fwd_max_example.inc
Normal file → Executable file
0
example/12_reduce/CMakeLists.txt
Normal file → Executable file
0
example/12_reduce/CMakeLists.txt
Normal file → Executable file
0
example/12_reduce/README.md
Normal file → Executable file
0
example/12_reduce/README.md
Normal file → Executable file
0
example/12_reduce/reduce_blockwise.cpp
Normal file → Executable file
0
example/12_reduce/reduce_blockwise.cpp
Normal file → Executable file
0
example/12_reduce/reduce_blockwise_impl.hpp
Normal file → Executable file
0
example/12_reduce/reduce_blockwise_impl.hpp
Normal file → Executable file
0
example/12_reduce/reduce_blockwise_two_call.cpp
Normal file → Executable file
0
example/12_reduce/reduce_blockwise_two_call.cpp
Normal file → Executable file
0
example/12_reduce/reduce_example_common.hpp
Normal file → Executable file
0
example/12_reduce/reduce_example_common.hpp
Normal file → Executable file
0
example/12_reduce/reduce_multiblock_atomic_add.cpp
Normal file → Executable file
0
example/12_reduce/reduce_multiblock_atomic_add.cpp
Normal file → Executable file
0
example/12_reduce/reduce_multiblock_atomic_add_impl.hpp
Normal file → Executable file
0
example/12_reduce/reduce_multiblock_atomic_add_impl.hpp
Normal file → Executable file
0
example/13_pool2d_fwd/CMakeLists.txt
Normal file → Executable file
0
example/13_pool2d_fwd/CMakeLists.txt
Normal file → Executable file
0
example/13_pool2d_fwd/README.md
Normal file → Executable file
0
example/13_pool2d_fwd/README.md
Normal file → Executable file
0
example/13_pool2d_fwd/pool2d_fwd_common.hpp
Normal file → Executable file
0
example/13_pool2d_fwd/pool2d_fwd_common.hpp
Normal file → Executable file
0
example/13_pool2d_fwd/pool2d_fwd_fp16.cpp
Normal file → Executable file
0
example/13_pool2d_fwd/pool2d_fwd_fp16.cpp
Normal file → Executable file
0
example/13_pool2d_fwd/pool2d_fwd_fp32.cpp
Normal file → Executable file
0
example/13_pool2d_fwd/pool2d_fwd_fp32.cpp
Normal file → Executable file
0
example/14_gemm_quantization/CMakeLists.txt
Normal file → Executable file
0
example/14_gemm_quantization/CMakeLists.txt
Normal file → Executable file
0
example/14_gemm_quantization/gemm_dl_quantization_int8.cpp
Normal file → Executable file
0
example/14_gemm_quantization/gemm_dl_quantization_int8.cpp
Normal file → Executable file
0
example/14_gemm_quantization/gemm_xdl_bias_relu_quantization_int8.cpp
Normal file → Executable file
0
example/14_gemm_quantization/gemm_xdl_bias_relu_quantization_int8.cpp
Normal file → Executable file
0
example/14_gemm_quantization/gemm_xdl_quantization_int8.cpp
Normal file → Executable file
0
example/14_gemm_quantization/gemm_xdl_quantization_int8.cpp
Normal file → Executable file
0
example/15_grouped_gemm/CMakeLists.txt
Normal file → Executable file
0
example/15_grouped_gemm/CMakeLists.txt
Normal file → Executable file
0
example/15_grouped_gemm/README.md
Normal file → Executable file
0
example/15_grouped_gemm/README.md
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_multiple_d_dl_fp16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_multiple_d_dl_fp16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_bf16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_bf16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_bias_fp16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_bias_fp16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp8.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp8.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp
Normal file → Executable file
0
example/15_grouped_gemm/run_grouped_gemm_example.inc
Normal file → Executable file
0
example/15_grouped_gemm/run_grouped_gemm_example.inc
Normal file → Executable file
0
example/16_gemm_multi_d_multi_reduces/CMakeLists.txt
Normal file → Executable file
0
example/16_gemm_multi_d_multi_reduces/CMakeLists.txt
Normal file → Executable file
0
example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp
Normal file → Executable file
0
example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp
Normal file → Executable file
0
example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp
Normal file → Executable file
0
example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp
Normal file → Executable file
0
example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp
Normal file → Executable file
0
example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp
Normal file → Executable file
0
example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp
Normal file → Executable file
0
example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp
Normal file → Executable file
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user