mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-07-16 08:44:55 +00:00
experimental power analysis branch
This commit is contained in:
0
include/ck/ck.hpp
Normal file → Executable file
0
include/ck/ck.hpp
Normal file → Executable file
0
include/ck/config.h.in
Normal file → Executable file
0
include/ck/config.h.in
Normal file → Executable file
0
include/ck/host_utility/device_prop.hpp
Normal file → Executable file
0
include/ck/host_utility/device_prop.hpp
Normal file → Executable file
0
include/ck/host_utility/hip_check_error.hpp
Normal file → Executable file
0
include/ck/host_utility/hip_check_error.hpp
Normal file → Executable file
0
include/ck/host_utility/io.hpp
Normal file → Executable file
0
include/ck/host_utility/io.hpp
Normal file → Executable file
0
include/ck/host_utility/kernel_launch.hpp
Normal file → Executable file
0
include/ck/host_utility/kernel_launch.hpp
Normal file → Executable file
0
include/ck/host_utility/stream_utility.hpp
Normal file → Executable file
0
include/ck/host_utility/stream_utility.hpp
Normal file → Executable file
0
include/ck/problem_transform/transform_forward_convolution3d_into_gemm_v4r4r4_ndhwc_kzyxc_ndhwk.hpp
Normal file → Executable file
0
include/ck/problem_transform/transform_forward_convolution3d_into_gemm_v4r4r4_ndhwc_kzyxc_ndhwk.hpp
Normal file → Executable file
0
include/ck/stream_config.hpp
Normal file → Executable file
0
include/ck/stream_config.hpp
Normal file → Executable file
0
include/ck/tensor/static_tensor.hpp
Normal file → Executable file
0
include/ck/tensor/static_tensor.hpp
Normal file → Executable file
0
include/ck/tensor_description/cluster_descriptor.hpp
Normal file → Executable file
0
include/ck/tensor_description/cluster_descriptor.hpp
Normal file → Executable file
0
include/ck/tensor_description/multi_index_transform.hpp
Normal file → Executable file
0
include/ck/tensor_description/multi_index_transform.hpp
Normal file → Executable file
0
include/ck/tensor_description/multi_index_transform_helper.hpp
Normal file → Executable file
0
include/ck/tensor_description/multi_index_transform_helper.hpp
Normal file → Executable file
0
include/ck/tensor_description/tensor_adaptor.hpp
Normal file → Executable file
0
include/ck/tensor_description/tensor_adaptor.hpp
Normal file → Executable file
0
include/ck/tensor_description/tensor_descriptor.hpp
Normal file → Executable file
0
include/ck/tensor_description/tensor_descriptor.hpp
Normal file → Executable file
0
include/ck/tensor_description/tensor_descriptor_helper.hpp
Normal file → Executable file
0
include/ck/tensor_description/tensor_descriptor_helper.hpp
Normal file → Executable file
0
include/ck/tensor_description/tensor_space_filling_curve.hpp
Normal file → Executable file
0
include/ck/tensor_description/tensor_space_filling_curve.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_dpp.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_dpp.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_pipeline_xdlops.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_direct_load.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_direct_load.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1_dequant.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1_dequant.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1r2.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1r2.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r2.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r2.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/conv_tensor_rearrange_op.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/conv_tensor_rearrange_op.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_avgpool_bwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_avgpool_bwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_base.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_base.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_contraction_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_e_permute.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_e_permute.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_gemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_multi_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_multiple_d_gemm_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batchnorm_backward.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batchnorm_backward.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batchnorm_forward.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_batchnorm_infer.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_cgemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_cgemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_contraction_multiple_abd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_contraction_multiple_abd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_conv_bwd_data.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_conv_bwd_data.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_conv_fwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_conv_fwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation_add.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_conv_fwd_bias_activation_add.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_conv_tensor_rearrange.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_conv_tensor_rearrange.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_elementwise.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_elementwise.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_elementwise_normalization.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_elementwise_scale.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_elementwise_scale.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_bias_e_permute.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_bias_e_permute.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_dequantB.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_dequantB.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_multiple_abd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_multiple_abd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_layernorm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_layernorm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_multiple_r.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_reduce.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_reduce.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_splitk.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_splitk.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_streamk.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_gemm_streamk.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_contraction_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_data_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_weight.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_conv_bwd_weight.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_gemm.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_gemm_fixed_nk.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_gemm_fixed_nk.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_grouped_gemm_splitk.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_max_pool_bwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_max_pool_bwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_multiple_reduce.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_normalization_bwd_data.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_normalization_bwd_data.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_normalization_bwd_gamma_beta.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_normalization_bwd_gamma_beta.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_normalization_fwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_normalization_fwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_permute.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_permute.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_pool_fwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_pool_fwd.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_put_element.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_put_element.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_reduce.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_reduce.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_softmax.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_softmax.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_splitk_contraction_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/device_splitk_contraction_multiple_d.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/impl/device_avgpool3d_bwd_ndhwc_ndhwc.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/impl/device_avgpool3d_bwd_ndhwc_ndhwc.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
Normal file → Executable file
0
include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
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