Merge branch 'develop' into lwpck-726

a7342032 · Rostyslav Geyyer · GitHub · 2ee1c0a7 · 027e46ee · a7342032
Unverified Commit a7342032 authored Jun 16, 2023 by Rostyslav Geyyer Committed by GitHub Jun 16, 2023
20 changed files
--- a/include/ck/tensor_operation/gpu/grid/gridwise_sparse_embeddings_forward_layernorm.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_sparse_embeddings_forward_layernorm.hpp
--- a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_naive_variance.hpp
+++ b/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_naive_variance.hpp
--- a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_selector.hpp
+++ b/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_selector.hpp
--- a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_1st.hpp
+++ b/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_1st.hpp
--- a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_2nd.hpp
+++ b/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_2nd.hpp
--- a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_welford_variance.hpp
+++ b/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_welford_variance.hpp
--- a/include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_gemm_dlops_v3.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_gemm_dlops_v3.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_set.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v4r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v4r1.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/thread/threadwise_tensor_slice_transfer_v6r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r1.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r2.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r2.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r3.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v6r3.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_welford.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_welford.hpp
--- a/include/ck/tensor_operation/gpu/warp/wmma_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/warp/wmma_gemm.hpp
--- a/include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp
+++ b/include/ck/tensor_operation/gpu/warp/xdlops_gemm.hpp