Merge branch 'develop' into lwpck-586

8da05b38 · zjing14 · GitHub · 9a4fd1bc · e6cda9f8 · 8da05b38
Unverified Commit 8da05b38 authored Mar 05, 2023 by zjing14 Committed by GitHub Mar 05, 2023
20 changed files
--- a/example/46_gemm_add_multiply/run_gemm_add_multiply_example.inc
+++ b/example/46_gemm_add_multiply/run_gemm_add_multiply_example.inc
--- a/example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
+++ b/example/47_gemm_bias_softmax_gemm_permute/CMakeLists.txt
--- a/example/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp
+++ b/example/47_gemm_bias_softmax_gemm_permute/gemm_bias_softmax_gemm_permute.cpp
--- a/include/ck/ck.hpp
+++ b/include/ck/ck.hpp
--- a/include/ck/host_utility/kernel_launch.hpp
+++ b/include/ck/host_utility/kernel_launch.hpp
--- a/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_batched_gemm_softmax_gemm_permute.hpp
--- a/include/ck/tensor_operation/gpu/device/device_normalization.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_normalization.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_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_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_elementwise_normalization_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_elementwise_normalization_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_gnwc_gkxc_gnwk_dl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_gnwc_gkxc_gnwk_dl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.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/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