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

0b11569f · Chao Liu · e8d3a0fb · fa9a0a5c · 0b11569f · 0b11569f
Commit 0b11569f authored Jul 01, 2022 by Chao Liu
20 changed files
--- 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/device_pool2d_fwd.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_pool2d_fwd.hpp
--- a/include/ck/tensor_operation/gpu/device/device_pool2d_fwd_nhwc_nhwc.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_pool2d_fwd_nhwc_nhwc.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_common.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_common.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp
--- 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/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