mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-07-13 18:51:13 +00:00
experimental power analysis branch
This commit is contained in:
Harisankar Sadasivan
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/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/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/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/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_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/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
0
client_example/16_convnd_fwd/CMakeLists.txt
Normal file → Executable file
0
client_example/16_convnd_fwd/CMakeLists.txt
Normal file → Executable file
0
client_example/16_convnd_fwd/common.hpp
Normal file → Executable file
0
client_example/16_convnd_fwd/common.hpp
Normal file → Executable file
0
client_example/16_convnd_fwd/conv3d_fwd_fp16.cpp
Normal file → Executable file
0
client_example/16_convnd_fwd/conv3d_fwd_fp16.cpp
Normal file → Executable file
0
client_example/16_convnd_fwd/conv3d_fwd_fp16_comp_fp8.cpp
Normal file → Executable file
0
client_example/16_convnd_fwd/conv3d_fwd_fp16_comp_fp8.cpp
Normal file → Executable file
0
client_example/16_convnd_fwd/conv3d_fwd_fp32.cpp
Normal file → Executable file
0
client_example/16_convnd_fwd/conv3d_fwd_fp32.cpp
Normal file → Executable file
0
client_example/17_grouped_gemm_fastgelu/CMakeLists.txt
Normal file → Executable file
0
client_example/17_grouped_gemm_fastgelu/CMakeLists.txt
Normal file → Executable file
0
client_example/17_grouped_gemm_fastgelu/grouped_gemm_fastgelu.cpp
Normal file → Executable file
0
client_example/17_grouped_gemm_fastgelu/grouped_gemm_fastgelu.cpp
Normal file → Executable file
0
client_example/18_groupnorm/CMakeLists.txt
Normal file → Executable file
0
client_example/18_groupnorm/CMakeLists.txt
Normal file → Executable file
0
client_example/18_groupnorm/groupnorm_bwd_data.cpp
Normal file → Executable file
0
client_example/18_groupnorm/groupnorm_bwd_data.cpp
Normal file → Executable file
0
client_example/18_groupnorm/groupnorm_bwd_gamma_beta.cpp
Normal file → Executable file
0
client_example/18_groupnorm/groupnorm_bwd_gamma_beta.cpp
Normal file → Executable file
0
client_example/18_groupnorm/groupnorm_swish_fwd.cpp
Normal file → Executable file
0
client_example/18_groupnorm/groupnorm_swish_fwd.cpp
Normal file → Executable file
0
client_example/19_pool/CMakeLists.txt
Normal file → Executable file
0
client_example/19_pool/CMakeLists.txt
Normal file → Executable file
0
client_example/19_pool/avg_pool3d_bwd.cpp
Normal file → Executable file
0
client_example/19_pool/avg_pool3d_bwd.cpp
Normal file → Executable file
0
client_example/19_pool/avg_pool3d_fwd.cpp
Normal file → Executable file
0
client_example/19_pool/avg_pool3d_fwd.cpp
Normal file → Executable file
0
client_example/19_pool/max_pool2d_bwd.cpp
Normal file → Executable file
0
client_example/19_pool/max_pool2d_bwd.cpp
Normal file → Executable file
0
client_example/19_pool/max_pool2d_fwd.cpp
Normal file → Executable file
0
client_example/19_pool/max_pool2d_fwd.cpp
Normal file → Executable file
0
client_example/20_splitk_gemm/CMakeLists.txt
Normal file → Executable file
0
client_example/20_splitk_gemm/CMakeLists.txt
Normal file → Executable file
0
client_example/20_splitk_gemm/splitK_gemm_fp16_f8.cpp
Normal file → Executable file
0
client_example/20_splitk_gemm/splitK_gemm_fp16_f8.cpp
Normal file → Executable file
0
client_example/21_grouped_gemm_bias/CMakeLists.txt
Normal file → Executable file
0
client_example/21_grouped_gemm_bias/CMakeLists.txt
Normal file → Executable file
0
client_example/21_grouped_gemm_bias/grouped_gemm_fixed_nk_bias_fp16.cpp
Normal file → Executable file
0
client_example/21_grouped_gemm_bias/grouped_gemm_fixed_nk_bias_fp16.cpp
Normal file → Executable file
0
client_example/22_grouped_gemm/CMakeLists.txt
Normal file → Executable file
0
client_example/22_grouped_gemm/CMakeLists.txt
Normal file → Executable file
0
client_example/22_grouped_gemm/grouped_gemm_fixed_nk_bf16.cpp
Normal file → Executable file
0
client_example/22_grouped_gemm/grouped_gemm_fixed_nk_bf16.cpp
Normal file → Executable file
0
client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp16.cpp
Normal file → Executable file
0
client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp16.cpp
Normal file → Executable file
0
client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp8.cpp
Normal file → Executable file
0
client_example/22_grouped_gemm/grouped_gemm_fixed_nk_fp8.cpp
Normal file → Executable file
0
client_example/22_grouped_gemm/grouped_gemm_fixed_nk_i8.cpp
Normal file → Executable file
0
client_example/22_grouped_gemm/grouped_gemm_fixed_nk_i8.cpp
Normal file → Executable file
0
client_example/22_im2col_col2im/CMakeLists.txt
Normal file → Executable file
0
client_example/22_im2col_col2im/CMakeLists.txt
Normal file → Executable file
0
client_example/22_im2col_col2im/column_to_image.cpp
Normal file → Executable file
0
client_example/22_im2col_col2im/column_to_image.cpp
Normal file → Executable file
0
client_example/22_im2col_col2im/image_to_column.cpp
Normal file → Executable file
0
client_example/22_im2col_col2im/image_to_column.cpp
Normal file → Executable file
0
client_example/23_elementwise_transpose/CMakeLists.txt
Normal file → Executable file
0
client_example/23_elementwise_transpose/CMakeLists.txt
Normal file → Executable file
0
client_example/23_elementwise_transpose/elementwise_transpose_3d.cpp
Normal file → Executable file
0
client_example/23_elementwise_transpose/elementwise_transpose_3d.cpp
Normal file → Executable file
0
client_example/24_grouped_conv_activation/CMakeLists.txt
Normal file → Executable file
0
client_example/24_grouped_conv_activation/CMakeLists.txt
Normal file → Executable file
0
client_example/24_grouped_conv_activation/grouped_convnd_bwd_data_bilinear/grouped_conv_bwd_data_bilinear_residual_fp16.cpp
Normal file → Executable file
0
client_example/24_grouped_conv_activation/grouped_convnd_bwd_data_bilinear/grouped_conv_bwd_data_bilinear_residual_fp16.cpp
Normal file → Executable file
0
client_example/24_grouped_conv_activation/grouped_convnd_bwd_data_scale/grouped_conv_bwd_data_scale_fp16.cpp
Normal file → Executable file
0
client_example/24_grouped_conv_activation/grouped_convnd_bwd_data_scale/grouped_conv_bwd_data_scale_fp16.cpp
Normal file → Executable file
0
client_example/24_grouped_conv_activation/grouped_convnd_fwd_bilinear/grouped_conv_fwd_bilinear_residual_fp16.cpp
Normal file → Executable file
0
client_example/24_grouped_conv_activation/grouped_convnd_fwd_bilinear/grouped_conv_fwd_bilinear_residual_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