Merge pull request #33 from ROCm/lwpck-1292

Merge from the public repo.

Merge pull request #33 from ROCm/lwpck-1292
Merge from the public repo.
29dcb956 · Illia Silin · GitHub · 29deceb6 · cbcc844e · 29dcb956
Unverified Commit 29dcb956 authored Feb 08, 2024 by Illia Silin Committed by GitHub Feb 08, 2024
20 changed files
--- a/include/ck/wrapper/utils/tensor_partition.hpp
+++ b/include/ck/wrapper/utils/tensor_partition.hpp
--- a/include/ck/wrapper/utils/tensor_utils.hpp
+++ b/include/ck/wrapper/utils/tensor_utils.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_column_to_image.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_column_to_image.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_data.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_weight.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_bwd_weight.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_conv_fwd.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_groupnorm_bwd.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_groupnorm_bwd.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_image_to_column.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_image_to_column.hpp
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_layernorm_bwd.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_layernorm_bwd.hpp
--- a/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp
+++ b/library/include/ck/library/tensor_operation_instance/device_operation_instance_factory.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_gemm.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/batched_gemm_gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/contraction/device_contraction_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/contraction/device_contraction_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v1_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v1_instance.hpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_instance.cpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v2_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/device_gemm_xdl_c_shuffle_fp8_fp8_fp8_mk_kn_mn_v2_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_add.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_add.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_fastgelu.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_fastgelu.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_relu.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_add_relu.hpp