Merge branch 'develop' into gemm_layernorm_welford

5aa3c344 · rocking5566 · GitHub · 7fefc966 · 9d8f834a · 5aa3c344
Unverified Commit 5aa3c344 authored Oct 05, 2022 by rocking5566 Committed by GitHub Oct 05, 2022
20 changed files
--- a/include/ck/tensor_operation/gpu/device/device_layernorm_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_layernorm_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/device_permute.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_permute.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_data_multiple_d_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_permute_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_permute_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/matrix_padder.hpp
+++ b/include/ck/tensor_operation/gpu/device/matrix_padder.hpp
--- a/include/ck/tensor_operation/gpu/device/tensor_layout.hpp
+++ b/include/ck/tensor_operation/gpu/device/tensor_layout.hpp
--- a/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/binary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
+++ b/include/ck/tensor_operation/gpu/grid/block_to_ctile_map.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_multiple_d_gemm_multiple_d_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_batched_gemm_softmax_gemm_xdl_cshuffle_v1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_1d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_elementwise_1d.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_layernorm_naive_variance.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_layernorm_naive_variance.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_layernorm_welford_variance.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_layernorm_welford_variance.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v3r1.hpp
@@ -6,6 +6,7 @@
 #include "ck/utility/common_header.hpp"
 #include "ck/tensor_description/tensor_descriptor.hpp"
 #include "ck/tensor_description/tensor_descriptor_helper.hpp"
+#include "ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp"
 #include "ck/tensor/static_tensor.hpp"
 namespace ck {

--- a/include/ck/tensor_operation/operator_transform/transform_conv_bwd_data_to_gemm_v1.hpp
+++ b/include/ck/tensor_operation/operator_transform/transform_conv_bwd_data_to_gemm_v1.hpp
--- a/include/ck/tensor_operation/operator_transform/transform_conv_fwd_to_gemm.hpp
+++ b/include/ck/tensor_operation/operator_transform/transform_conv_fwd_to_gemm.hpp
--- a/include/ck/utility/ignore.hpp
+++ b/include/ck/utility/ignore.hpp