Merge pull request #3 from ROCmSoftwarePlatform/downstream-internal

Downstream from public to internal

Merge pull request #3 from ROCmSoftwarePlatform/downstream-internal
Downstream from public to internal
52f64967 · Illia Silin · GitHub · dda3a0a1 · 246ceee4 · 52f64967
Unverified Commit 52f64967 authored Feb 23, 2023 by Illia Silin Committed by GitHub Feb 23, 2023
20 changed files
--- a/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_dl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_data_nwc_kxc_nwk_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_elementwise_2d_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_elementwise_2d_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_elementwise.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_elementwise.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_elementwise_normalization_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_elementwise_normalization_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_dl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_dl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_dl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_dl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_layernorm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_reduce_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_reduce_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_wmma.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_layernorm_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_layernorm_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_skip_b_lds.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_skip_b_lds.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_splitk_c_shuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_gnwc_gkxc_gnwk_dl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_bwd_weight_gnwc_gkxc_gnwk_dl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_convnd_bwd_weight_nwc_kxc_nwk_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_multiple_r_xdl_cshuffle.hpp