Merge remote-tracking branch 'origin/develop' into aosewski/ggemm_multi_d2

057140b1 · Adam Osewski · 134fc2e7 · 12a8883c · 057140b1 · 057140b1
Commit 057140b1 authored Dec 19, 2023 by Adam Osewski
20 changed files
--- a/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl_obsolete.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_forward_impl_obsolete.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_abd_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_contraction_multiple_d_xdl_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_contraction_utils.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_contraction_utils.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_elementwise_3d_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_elementwise_3d_impl.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_xdl_cshuffle_lds_direct_load.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_multiple_d_xdl_cshuffle_lds_direct_load.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_lds_direct_load.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_lds_direct_load.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_streamk.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_gemm_xdl_streamk.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_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
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_d_wmma_cshuffle.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_gemm_xdl_fixed_nk.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_normalization_bwd_data_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_normalization_bwd_data_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_normalization_bwd_gamma_beta_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_normalization_bwd_gamma_beta_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_normalization_fwd_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_normalization_fwd_impl.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_normalization_fwd_splitk_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_normalization_fwd_splitk_impl.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/unary_element_wise_operation.hpp
+++ b/include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle_lds_direct_load.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle_lds_direct_load.hpp