Merge branch 'develop' into amd-develop

457308e3 · Jun Liu · a5fd9747 · 341ad956 · 457308e3 · 457308e3
Commit 457308e3 authored Jun 19, 2023 by Jun Liu
20 changed files
--- a/include/ck/tensor_description/tensor_descriptor_helper.hpp
+++ b/include/ck/tensor_description/tensor_descriptor_helper.hpp
--- a/include/ck/tensor_description/tensor_space_filling_curve.hpp
+++ b/include/ck/tensor_description/tensor_space_filling_curve.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_dl_v2r3.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v2r2.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_dlops_v3.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_wmma.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_gemm_xdlops_skip_b_lds.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_softmax.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_tensor_slice_transfer_v5r1.hpp
--- a/include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
+++ b/include/ck/tensor_operation/gpu/block/blockwise_welford.hpp
--- a/include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
+++ b/include/ck/tensor_operation/gpu/block/reduction_functions_blockwise.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v4r1.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r1.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r2.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v6r3.hpp
--- a/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
+++ b/include/ck/tensor_operation/gpu/block/thread_group_tensor_slice_transfer_v7.hpp
--- a/include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/convolution_backward_data_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/convolution_backward_weight_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/convolution_forward_specialization.hpp