merge develop

9dce6851 · Jing Zhang · 3cc57101 · 5d37d7bf · 9dce6851 · 9dce6851
Commit 9dce6851 authored Mar 10, 2022 by Jing Zhang
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_reduce_multiblock_partial_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_multiblock_partial_reduce.hpp
--- a/include/ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp
--- a/device_operation/include/gemm_specialization.hpp
+++ b/device_operation/include/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/device_operation/include/tensor_layout.hpp
+++ b/device_operation/include/tensor_layout.hpp
--- a/composable_kernel/include/tensor_operation/element_wise_operation.hpp
+++ b/composable_kernel/include/tensor_operation/element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_blockwise.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_blockwise.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock_atomic_add.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock_atomic_add.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock_partial_reduce.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_2d_reduction_multiblock_partial_reduce.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/composable_kernel/include/tensor_operation/gridwise_batched_gemm_xdlops_v2r3.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_batched_gemm_xdlops_v2r3.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_contraction_dlops_v1r2.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_contraction_dlops_v1r2.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_dlops_v1r2.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_dlops_v1r2.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_dlops_v1r3.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_dlops_v1r3.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_dlops_v2.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_dlops_v2.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_dlops_v3.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_dlops_v3.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_pipeline_v1.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_pipeline_v1.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v2r3.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v2r3.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v2r4.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v2r4.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v2r4r2.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v2r4r2.hpp