Merge branch 'develop' into aosewski/wavelet_omniperf

dc0bae32 · Adam Osewski · 68474822 · ba40c2ce · dc0bae32 · dc0bae32
Commit dc0bae32 authored Feb 01, 2023 by Adam Osewski
20 changed files
--- 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_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_gemm_xdl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_multiple_reduce_multiblock.hpp
--- 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_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