merge develop

9dce6851 · Jing Zhang · 3cc57101 · 5d37d7bf · 9dce6851 · 9dce6851
Commit 9dce6851 authored Mar 10, 2022 by Jing Zhang
20 changed files
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v3r1.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v3r1.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v3r2.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v3r2.hpp
--- a/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v3r3.hpp
+++ b/composable_kernel/include/tensor_operation/gridwise_gemm_xdlops_v3r3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_grouped_gemm_xdlops_v2r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_grouped_gemm_xdlops_v2r3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_contraction_dlops.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_contraction_dlops.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_gemm_dlops_v3.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_gemm_dlops_v3.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_set.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_set.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v1r4.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v1r4.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v1r5.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v1r5.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v3r1.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v3r1.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v3r3.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v3r3.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v4r1.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v4r1.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v5r1.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v5r1.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v6r1.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v6r1.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v6r2.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v6r2.hpp
--- a/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v6r3.hpp
+++ b/composable_kernel/include/tensor_operation/threadwise_tensor_slice_transfer_v6r3.hpp
--- a/composable_kernel/include/tensor_operation/xdlops_gemm.hpp
+++ b/composable_kernel/include/tensor_operation/xdlops_gemm.hpp
--- a/composable_kernel/include/utility/amd_address_space.hpp
+++ b/composable_kernel/include/utility/amd_address_space.hpp