Merge branch 'develop' into feature/check-window-lengths

e6bb1dd7 · Po Yen Chen · GitHub · 9d6a3704 · ab250afd · e6bb1dd7
Unverified Commit e6bb1dd7 authored Jul 19, 2024 by Po Yen Chen Committed by GitHub Jul 19, 2024
20 changed files
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r3.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7r3.hpp
--- a/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/device_gemm_streamk_v2.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_gemm_streamk_v2.hpp
--- a/include/ck/tensor_operation/gpu/device/helper.hpp
+++ b/include/ck/tensor_operation/gpu/device/helper.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/codegen_device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/codegen_device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_contraction_multiple_d_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_dl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_dl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_reduce_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batched_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_contraction_utils.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_contraction_utils.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_conv2d_bwd_data_xdl_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_add_nhwc_kyxc_nhwk.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_conv2d_fwd_xdl_c_shuffle_bias_activation_nhwc_kyxc_nhwk.hpp