Merge branch 'develop' into aosewski/ggemm_multi_d2

defa2071 · Adam Osewski · 28a68428 · f2398f61 · defa2071 · defa2071
Commit defa2071 authored Nov 15, 2023 by Adam Osewski
20 changed files
--- a/example/62_conv_fwd_activ/run_convnd_fwd_activ_example.inc
+++ b/example/62_conv_fwd_activ/run_convnd_fwd_activ_example.inc
--- a/example/63_layernorm4d_fwd/CMakeLists.txt
+++ b/example/63_layernorm4d_fwd/CMakeLists.txt
--- a/example/63_layernorm4d_fwd/common.hpp
+++ b/example/63_layernorm4d_fwd/common.hpp
--- a/example/63_layernorm4d_fwd/layernorm4d_fwd_fp16.cpp
+++ b/example/63_layernorm4d_fwd/layernorm4d_fwd_fp16.cpp
--- a/example/63_layernorm4d_fwd/layernorm4d_fwd_splitk_fp16.cpp
+++ b/example/63_layernorm4d_fwd/layernorm4d_fwd_splitk_fp16.cpp
--- a/example/63_layernorm4d_fwd/run_layernorm4d_fwd_example.inc
+++ b/example/63_layernorm4d_fwd/run_layernorm4d_fwd_example.inc
--- a/example/CMakeLists.txt
+++ b/example/CMakeLists.txt
--- a/include/ck/ck.hpp
+++ b/include/ck/ck.hpp
--- a/include/ck/host_utility/hip_check_error.hpp
+++ b/include/ck/host_utility/hip_check_error.hpp
--- a/include/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_contraction_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_conv_tensor_rearrange.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_conv_tensor_rearrange.hpp
--- a/include/ck/tensor_operation/gpu/device/device_elementwise_scale.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_elementwise_scale.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_abd.hpp
--- a/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_grouped_conv_fwd_multiple_d.hpp
--- a/include/ck/tensor_operation/gpu/device/device_normalization_bwd_gamma_beta.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_normalization_bwd_gamma_beta.hpp
--- a/include/ck/tensor_operation/gpu/device/device_normalization.hpp
+++ b/include/ck/tensor_operation/gpu/device/device_normalization.hpp
--- a/include/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_column_to_image_impl.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_elementwise_3d_impl.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_elementwise_3d_impl.hpp