Merge remote-tracking branch 'origin/develop' into cpu_avx2

b79df771 · carlushuang · 05d38218 · 63914743 · b79df771 · b79df771
Commit b79df771 authored Jul 12, 2022 by carlushuang
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/device/device_softmax.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_softmax.hpp
--- a/include/ck/tensor_operation/gpu/device/device_unary_elementwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_unary_elementwise.hpp
--- a/include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/gemm_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp
+++ b/include/ck/tensor_operation/gpu/device/reduction_operator_mapping.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/element_wise_reduce_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_reduce_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/block_to_ctile_map.hpp
+++ b/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_5ary_Elementwise_1d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_5ary_Elementwise_1d.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_binary_elementwise_1d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_binary_elementwise_1d.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_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_v1r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_dl_v1r3.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