Merge branch 'develop' into gfx950

ef5e60f6 · illsilin · 2cc0fa26 · 5e93fa9e · ef5e60f6 · ef5e60f6
Commit ef5e60f6 authored Dec 11, 2024 by illsilin
20 changed files
--- a/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
--- a/profiler/README.md
+++ b/profiler/README.md
--- 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_grouped_gemm_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_gemm_impl.hpp
--- a/profiler/include/profiler/profile_grouped_gemm_multiply_tile_loop_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_gemm_multiply_tile_loop_impl.hpp
--- a/profiler/include/profiler/profile_grouped_gemm_tile_loop_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_gemm_tile_loop_impl.hpp
--- a/profiler/include/profiler/profile_grouped_gemm_two_stage_impl.hpp
+++ b/profiler/include/profiler/profile_grouped_gemm_two_stage_impl.hpp
--- a/profiler/src/CMakeLists.txt
+++ b/profiler/src/CMakeLists.txt
--- 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/profiler/src/profile_grouped_gemm.cpp
+++ b/profiler/src/profile_grouped_gemm.cpp
--- a/profiler/src/profile_grouped_gemm_fixed_nk.cpp
+++ b/profiler/src/profile_grouped_gemm_fixed_nk.cpp
--- a/profiler/src/profile_grouped_gemm_two_stage.cpp
+++ b/profiler/src/profile_grouped_gemm_two_stage.cpp
--- a/python/ck4inductor/batched_universal_gemm/gen_instances.py
+++ b/python/ck4inductor/batched_universal_gemm/gen_instances.py
--- a/python/ck4inductor/batched_universal_gemm/op.py
+++ b/python/ck4inductor/batched_universal_gemm/op.py
--- a/python/ck4inductor/grouped_conv_fwd/gen_instances.py
+++ b/python/ck4inductor/grouped_conv_fwd/gen_instances.py
--- a/script/process_perf_data.py
+++ b/script/process_perf_data.py
--- a/script/process_perf_data.sh
+++ b/script/process_perf_data.sh
--- a/script/process_qa_data.sh
+++ b/script/process_qa_data.sh
--- a/script/run_full_performance_tests.sh
+++ b/script/run_full_performance_tests.sh