Merge branch 'develop' into codegen_hiprtc

a5137505 · arai713 · GitHub · 208a1dab · 888317e6 · a5137505
Unverified Commit a5137505 authored Jan 06, 2025 by arai713 Committed by GitHub Jan 06, 2025
20 changed files
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/comp/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_bf16_comp_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/comp/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_bf16_comp_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_bf16_mem_inter_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_bf16_mem_inter_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_bf16_mem_intra_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/mem/device_grouped_conv2d_fwd_xdl_ngchw_gkyxc_ngkhw_bf16_mem_intra_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/merged_groups/device_grouped_conv2d_fwd_xdl_merged_groups_ngchw_gkyxc_ngkhw_bf16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_conv2d_fwd/xdl/merged_groups/device_grouped_conv2d_fwd_xdl_merged_groups_ngchw_gkyxc_ngkhw_bf16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
--- a/modified_files.txt
+++ b/modified_files.txt
--- a/profiler/include/profiler/profile_gemm_b_scale_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_b_scale_impl.hpp
--- a/profiler/include/profiler/profile_gemm_universal_batched_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_universal_batched_impl.hpp
--- a/profiler/include/profiler/profile_gemm_universal_impl.hpp
+++ b/profiler/include/profiler/profile_gemm_universal_impl.hpp
--- a/profiler/include/profiler/profile_grouped_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_gemm_impl.hpp
--- a/profiler/src/CMakeLists.txt
+++ b/profiler/src/CMakeLists.txt
--- a/profiler/src/profile_gemm_b_scale.cpp
+++ b/profiler/src/profile_gemm_b_scale.cpp
--- a/profiler/src/profile_gemm_universal.cpp
+++ b/profiler/src/profile_gemm_universal.cpp
--- a/profiler/src/profile_gemm_universal_batched.cpp
+++ b/profiler/src/profile_gemm_universal_batched.cpp
--- a/profiler/src/profile_gemm_universal_streamk.cpp
+++ b/profiler/src/profile_gemm_universal_streamk.cpp
--- a/script/cmake-ck-dev.sh
+++ b/script/cmake-ck-dev.sh
--- a/script/process_perf_data.py
+++ b/script/process_perf_data.py
--- a/script/process_perf_data.sh
+++ b/script/process_perf_data.sh