Merge branch 'amd-develop' into amd-master

fa9da1a4 · Jun Liu · 4c105089 · 457308e3 · fa9da1a4 · 4c105089
Commit fa9da1a4 authored Jun 19, 2023 by Jun Liu
20 changed files
--- a/include/ck/tensor_operation/gpu/grid/gridwise_batchnorm_forward_blockwise_welford.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_batchnorm_forward_blockwise_welford.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_contraction_dlops_v1r2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_contraction_dlops_v1r2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_1d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_1d.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_2d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_2d.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_layernorm_welford_variance.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_layernorm_welford_variance.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_bias_add_reduce_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_bias_add_reduce_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dlops_v1r2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dlops_v1r2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dlops_v2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dlops_v2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dlops_v3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dlops_v3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_selector.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_selector.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_reduce_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_split_k_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_waveletmodel.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_waveletmodel.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_wmma.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_layernorm_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_layernorm_cshuffle_v1.hpp