merge develop

2724c519 · Jing Zhang · 1fb4a474 · 2eb74a9c · 2724c519 · 2724c519
Commit 2724c519 authored Feb 24, 2024 by Jing Zhang
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_gemm_softmax_gemm_permute_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_splitk_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_image_to_column_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_max_pool_bwd_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_max_pool_bwd_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_normalization_bwd_data_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_normalization_bwd_data_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_normalization_bwd_gamma_beta_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_normalization_bwd_gamma_beta_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_put_element_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_put_element_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_splitk_contraction_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_splitk_contraction_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/tensor_layout.hpp
+++ b/include/ck/tensor_operation/gpu/device/tensor_layout.hpp
--- a/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_batchnorm_forward.hpp
+++ b/include/ck/tensor_operation/gpu/grid/batchnorm_multiblock/gridwise_multiblock_batchnorm_forward.hpp