Merge branch 'amd-develop-staging-0423' into amd-master

6b9a4bd5 · Jun Liu · 56de337f · c5f1cdf7 · 6b9a4bd5 · 6b9a4bd5
Commit 6b9a4bd5 authored Apr 23, 2024 by Jun Liu
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_scaleadd_scaleadd_relu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_scaleadd_scaleadd_relu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_multiple_d_splitk_xdl_two_stage_bf16_i8_bf16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_multiple_d_splitk_xdl_two_stage_bf16_i8_bf16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_multiple_d_splitk_xdl_two_stage_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_multiple_d_splitk_xdl_two_stage_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_bias/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fastgelu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm_fixed_nk/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/permute_scale/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_1d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_1d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_1d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_1d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_2d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_2d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_2d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_2d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_3d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_3d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_3d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_3d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_4d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_4d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_4d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_4d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_5d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_5d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_5d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_5d_fp32_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_instances.cpp
--- a/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_fp32_instances.cpp
+++ b/library/src/tensor_operation_instance/gpu/permute_scale/device_permute_scale_6d_fp32_instances.cpp