mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-06-29 19:28:33 +00:00
for gfx350 kernel debug
This commit is contained in:
root
0
.azuredevops/rocm-ci.yml
Normal file → Executable file
0
.azuredevops/rocm-ci.yml
Normal file → Executable file
0
.clang-format
Normal file → Executable file
0
.clang-format
Normal file → Executable file
0
.clang-tidy
Normal file → Executable file
0
.clang-tidy
Normal file → Executable file
0
.github/CODEOWNERS
vendored
Normal file → Executable file
0
.github/CODEOWNERS
vendored
Normal file → Executable file
0
.github/CONTRIBUTING.md
vendored
Normal file → Executable file
0
.github/CONTRIBUTING.md
vendored
Normal file → Executable file
0
.github/ISSUE_TEMPLATE.md
vendored
Normal file → Executable file
0
.github/ISSUE_TEMPLATE.md
vendored
Normal file → Executable file
0
.github/ISSUE_TEMPLATE/config.yml
vendored
Normal file → Executable file
0
.github/ISSUE_TEMPLATE/config.yml
vendored
Normal file → Executable file
0
.github/ISSUE_TEMPLATE/issue_report.yml
vendored
Normal file → Executable file
0
.github/ISSUE_TEMPLATE/issue_report.yml
vendored
Normal file → Executable file
0
.github/PULL_REQUEST_TEMPLATE.md
vendored
Normal file → Executable file
0
.github/PULL_REQUEST_TEMPLATE.md
vendored
Normal file → Executable file
0
.github/dependabot.yml
vendored
Normal file → Executable file
0
.github/dependabot.yml
vendored
Normal file → Executable file
0
.gitignore
vendored
Normal file → Executable file
0
.gitignore
vendored
Normal file → Executable file
0
.readthedocs.yaml
Normal file → Executable file
0
.readthedocs.yaml
Normal file → Executable file
0
CHANGELOG.md
Normal file → Executable file
0
CHANGELOG.md
Normal file → Executable file
0
CITATION.cff
Normal file → Executable file
0
CITATION.cff
Normal file → Executable file
0
CMakeLists.txt
Normal file → Executable file
0
CMakeLists.txt
Normal file → Executable file
0
CONTRIBUTORS.md
Normal file → Executable file
0
CONTRIBUTORS.md
Normal file → Executable file
0
Config.cmake.in
Normal file → Executable file
0
Config.cmake.in
Normal file → Executable file
0
Dockerfile
Normal file → Executable file
0
Dockerfile
Normal file → Executable file
0
Dockerfile.compiler
Normal file → Executable file
0
Dockerfile.compiler
Normal file → Executable file
0
Jenkinsfile
vendored
Normal file → Executable file
0
Jenkinsfile
vendored
Normal file → Executable file
0
TERMINOLOGY.md
Normal file → Executable file
0
TERMINOLOGY.md
Normal file → Executable file
0
client_example/01_gemm/CMakeLists.txt
Normal file → Executable file
0
client_example/01_gemm/CMakeLists.txt
Normal file → Executable file
0
client_example/01_gemm/README.md
Normal file → Executable file
0
client_example/01_gemm/README.md
Normal file → Executable file
0
client_example/01_gemm/gemm.cpp
Normal file → Executable file
0
client_example/01_gemm/gemm.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/CMakeLists.txt
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/CMakeLists.txt
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu_generic.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_add_add_fastgelu_generic.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu_generic.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_add_fastgelu_generic.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_fastgelu.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_fastgelu.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_fastgelu_generic.cpp
Normal file → Executable file
0
client_example/02_gemm_add_add_fastgelu/gemm_fastgelu_generic.cpp
Normal file → Executable file
0
client_example/03_gemm_layernorm/CMakeLists.txt
Normal file → Executable file
0
client_example/03_gemm_layernorm/CMakeLists.txt
Normal file → Executable file
0
client_example/03_gemm_layernorm/gemm_add_add_layernorm_naive.cpp
Normal file → Executable file
0
client_example/03_gemm_layernorm/gemm_add_add_layernorm_naive.cpp
Normal file → Executable file
0
client_example/03_gemm_layernorm/gemm_add_relu_add_layernorm_welford.cpp
Normal file → Executable file
0
client_example/03_gemm_layernorm/gemm_add_relu_add_layernorm_welford.cpp
Normal file → Executable file
0
client_example/04_contraction/CMakeLists.txt
Normal file → Executable file
0
client_example/04_contraction/CMakeLists.txt
Normal file → Executable file
0
client_example/04_contraction/contraction_bilinear_fp32.cpp
Normal file → Executable file
0
client_example/04_contraction/contraction_bilinear_fp32.cpp
Normal file → Executable file
0
client_example/04_contraction/contraction_bilinear_fp64.cpp
Normal file → Executable file
0
client_example/04_contraction/contraction_bilinear_fp64.cpp
Normal file → Executable file
0
client_example/04_contraction/contraction_g1m2n3k1_add_xdl_fp16.cpp
Normal file → Executable file
0
client_example/04_contraction/contraction_g1m2n3k1_add_xdl_fp16.cpp
Normal file → Executable file
0
client_example/04_contraction/contraction_scale_fp32.cpp
Normal file → Executable file
0
client_example/04_contraction/contraction_scale_fp32.cpp
Normal file → Executable file
0
client_example/04_contraction/contraction_scale_fp64.cpp
Normal file → Executable file
0
client_example/04_contraction/contraction_scale_fp64.cpp
Normal file → Executable file
0
client_example/05_layernorm/CMakeLists.txt
Normal file → Executable file
0
client_example/05_layernorm/CMakeLists.txt
Normal file → Executable file
0
client_example/05_layernorm/layernorm2d_bwd_data.cpp
Normal file → Executable file
0
client_example/05_layernorm/layernorm2d_bwd_data.cpp
Normal file → Executable file
0
client_example/05_layernorm/layernorm2d_bwd_gamma_beta.cpp
Normal file → Executable file
0
client_example/05_layernorm/layernorm2d_bwd_gamma_beta.cpp
Normal file → Executable file
0
client_example/05_layernorm/layernorm2d_fwd.cpp
Normal file → Executable file
0
client_example/05_layernorm/layernorm2d_fwd.cpp
Normal file → Executable file
0
client_example/05_layernorm/layernorm4d_fwd.cpp
Normal file → Executable file
0
client_example/05_layernorm/layernorm4d_fwd.cpp
Normal file → Executable file
0
client_example/06_softmax/CMakeLists.txt
Normal file → Executable file
0
client_example/06_softmax/CMakeLists.txt
Normal file → Executable file
0
client_example/06_softmax/softmax4d.cpp
Normal file → Executable file
0
client_example/06_softmax/softmax4d.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/CMakeLists.txt
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/CMakeLists.txt
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/README.md
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/README.md
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/common.hpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/common.hpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv1d_fwd.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv1d_fwd.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv2d_fwd.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv2d_fwd.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv2d_fwd_ngchw.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv2d_fwd_ngchw.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv3d_fwd_bf8.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv3d_fwd_bf8.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv3d_fwd_bf8_fp8.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv3d_fwd_bf8_fp8.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv3d_fwd_fp8.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv3d_fwd_fp8.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv3d_fwd_fp8_bf8.cpp
Normal file → Executable file
0
client_example/07_grouped_convnd_fwd/grouped_conv3d_fwd_fp8_bf8.cpp
Normal file → Executable file
0
client_example/08_fused_attention/CMakeLists.txt
Normal file → Executable file
0
client_example/08_fused_attention/CMakeLists.txt
Normal file → Executable file
0
client_example/08_fused_attention/fused_attention.cpp
Normal file → Executable file
0
client_example/08_fused_attention/fused_attention.cpp
Normal file → Executable file
0
client_example/08_fused_attention/fused_attention_bias.cpp
Normal file → Executable file
0
client_example/08_fused_attention/fused_attention_bias.cpp
Normal file → Executable file
0
client_example/09_quantization/CMakeLists.txt
Normal file → Executable file
0
client_example/09_quantization/CMakeLists.txt
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_bias_relu_perchannel_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_bias_relu_perchannel_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_bias_relu_perlayer_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_bias_relu_perlayer_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_bias_tanh_perchannel_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_bias_tanh_perchannel_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_bias_tanh_perlayer_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_bias_tanh_perlayer_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_perchannel_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_perchannel_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_perlayer_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/conv2d_fwd_perlayer_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/gemm_quantization.cpp
Normal file → Executable file
0
client_example/09_quantization/gemm_quantization.cpp
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/CMakeLists.txt
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/CMakeLists.txt
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/README.md
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/README.md
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data.cpp
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data.cpp
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data_ngchw.cpp
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data_ngchw.cpp
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data.cpp
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data.cpp
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data_input_fp16_comp_bf8f8.cpp
Normal file → Executable file
0
client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data_input_fp16_comp_bf8f8.cpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/CMakeLists.txt
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/CMakeLists.txt
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/README.md
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/README.md
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/common.hpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/common.hpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/grouped_conv1d_bwd_weight_fp16.cpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/grouped_conv1d_bwd_weight_fp16.cpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/grouped_conv2d_bwd_weight_fp16.cpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/grouped_conv2d_bwd_weight_fp16.cpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16.cpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16.cpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16_comp_bf8_fp8.cpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16_comp_bf8_fp8.cpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp32.cpp
Normal file → Executable file
0
client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp32.cpp
Normal file → Executable file
0
client_example/12_elementwise_normalization/CMakeLists.txt
Normal file → Executable file
0
client_example/12_elementwise_normalization/CMakeLists.txt
Normal file → Executable file
0
client_example/12_elementwise_normalization/elementwise_layernorm2d.cpp
Normal file → Executable file
0
client_example/12_elementwise_normalization/elementwise_layernorm2d.cpp
Normal file → Executable file
0
client_example/13_batchnorm/CMakeLists.txt
Normal file → Executable file
0
client_example/13_batchnorm/CMakeLists.txt
Normal file → Executable file
0
client_example/13_batchnorm/batchnorm_bwd_nhwc.cpp
Normal file → Executable file
0
client_example/13_batchnorm/batchnorm_bwd_nhwc.cpp
Normal file → Executable file
0
client_example/13_batchnorm/batchnorm_fwd_nhwc.cpp
Normal file → Executable file
0
client_example/13_batchnorm/batchnorm_fwd_nhwc.cpp
Normal file → Executable file
0
client_example/13_batchnorm/batchnorm_infer_nhwc.cpp
Normal file → Executable file
0
client_example/13_batchnorm/batchnorm_infer_nhwc.cpp
Normal file → Executable file
0
client_example/14_instance_id/CMakeLists.txt
Normal file → Executable file
0
client_example/14_instance_id/CMakeLists.txt
Normal file → Executable file
0
client_example/14_instance_id/batchnorm_fwd_instance_id.cpp
Normal file → Executable file
0
client_example/14_instance_id/batchnorm_fwd_instance_id.cpp
Normal file → Executable file
0
client_example/15_convnd_bwd_data/CMakeLists.txt
Normal file → Executable file
0
client_example/15_convnd_bwd_data/CMakeLists.txt
Normal file → Executable file
0
client_example/15_convnd_bwd_data/common.hpp
Normal file → Executable file
0
client_example/15_convnd_bwd_data/common.hpp
Normal file → Executable file
0
client_example/15_convnd_bwd_data/conv3d_bwd_data_fp16.cpp
Normal file → Executable file
0
client_example/15_convnd_bwd_data/conv3d_bwd_data_fp16.cpp
Normal file → Executable file
0
client_example/15_convnd_bwd_data/conv3d_bwd_data_fp32.cpp
Normal file → Executable file
0
client_example/15_convnd_bwd_data/conv3d_bwd_data_fp32.cpp
Normal file → Executable file
0
client_example/15_gemm_add_multiply/CMakeLists.txt
Normal file → Executable file
0
client_example/15_gemm_add_multiply/CMakeLists.txt
Normal file → Executable file
0
client_example/15_gemm_add_multiply/gemm_add_multiply.cpp
Normal file → Executable file
0
client_example/15_gemm_add_multiply/gemm_add_multiply.cpp
Normal file → Executable file
0
client_example/15_reduce/CMakeLists.txt
Normal file → Executable file
0
client_example/15_reduce/CMakeLists.txt
Normal file → Executable file
0
client_example/15_reduce/reduce_nhwc_c.cpp
Normal file → Executable file
0
client_example/15_reduce/reduce_nhwc_c.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