Merge branch 'develop' into amd-develop

20ddaeba · Jun Liu · c5f1cdf7 · 43879b89 · 20ddaeba · 20ddaeba
Commit 20ddaeba authored Apr 22, 2024 by Jun Liu
20 changed files
--- 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_gemm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_multi_abd.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_multi_abd.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/gemm_universal.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_bilinear_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_bilinear_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_scale_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_xdl_scale_instance.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight_bilinear.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight_bilinear.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight_scale.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_backward_weight_scale.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_multi_abd_fixed_nk.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_multi_abd_fixed_nk.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/transpose/device_transpose_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/transpose/device_transpose_instance.hpp
--- a/library/include/ck/library/utility/host_tensor_generator.hpp
+++ b/library/include/ck/library/utility/host_tensor_generator.hpp
--- a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f64_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/batchnorm/device_batchnorm_infer_f64_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/elementwise/device_normalize_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/elementwise/device_normalize_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_multi_abd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_multi_abd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_multi_abd/device_gemm_xdl_multi_abd_bf16_i8_bf16_km_kn_mn_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multi_abd/device_gemm_xdl_multi_abd_bf16_i8_bf16_km_kn_mn_common.hpp
--- a/library/src/tensor_operation_instance/gpu/gemm_multi_abd/device_gemm_xdl_multi_abd_bf16_i8_bf16_mk_kn_mn_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multi_abd/device_gemm_xdl_multi_abd_bf16_i8_bf16_mk_kn_mn_common.hpp