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

6dfb4e78 · carlushuang · 397a68f2 · 1ced00a5 · 6dfb4e78 · 6dfb4e78
Commit 6dfb4e78 authored Jun 12, 2022 by carlushuang
20 changed files
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_bwd_weight.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dlops.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dlops.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v5r1.hpp
--- a/include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp
--- a/include/ck/utility/amd_buffer_addressing.hpp
+++ b/include/ck/utility/amd_buffer_addressing.hpp
--- a/include/ck/utility/amd_xdlops.hpp
+++ b/include/ck/utility/amd_xdlops.hpp
--- a/include/ck/utility/common_header.hpp
+++ b/include/ck/utility/common_header.hpp
--- a/include/ck/utility/dynamic_buffer.hpp
+++ b/include/ck/utility/dynamic_buffer.hpp
--- a/include/ck/utility/generic_memory_space_atomic_add.hpp
+++ b/include/ck/utility/generic_memory_space_atomic_add.hpp
--- a/include/ck/utility/get_id.hpp
+++ b/include/ck/utility/get_id.hpp
--- a/include/ck/utility/inner_product.hpp
+++ b/include/ck/utility/inner_product.hpp
--- a/include/ck/utility/math_v2.hpp
+++ b/include/ck/utility/math_v2.hpp
--- a/include/ck/utility/reduction_functions_accumulate.hpp
+++ b/include/ck/utility/reduction_functions_accumulate.hpp
--- a/include/ck/utility/reduction_operator.hpp
+++ b/include/ck/utility/reduction_operator.hpp