remove unnecessary changes

795bea35 · Umang Yadav · 8216854a · 795bea35 · 795bea35 · 795bea35
Commit 795bea35 authored Sep 26, 2023 by Umang Yadav
20 changed files
--- a/include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.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/impl/device_pool2d_fwd_nhwc_nhwc.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_pool2d_fwd_nhwc_nhwc.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_pool3d_fwd_ndhwc_ndhwc.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_reduce_common.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_reduce_multiblock.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_reduce_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_sparse_embeddings_forward_layernorm.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_splitk_contraction_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_splitk_contraction_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/masking_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/masking_specialization.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/reduction_operator_mapping.hpp
+++ b/include/ck/tensor_operation/gpu/device/reduction_operator_mapping.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/device/tensor_specialization.hpp
+++ b/include/ck/tensor_operation/gpu/device/tensor_specialization.hpp
--- a/include/ck/tensor_operation/gpu/device/welford_helper.hpp
+++ b/include/ck/tensor_operation/gpu/device/welford_helper.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/element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/element_wise_operation.hpp