Merge branch 'develop' into amd-develop

f0759faf · Jun Liu · 20ddaeba · 764164b4 · f0759faf · f0759faf
Commit f0759faf authored Apr 26, 2024 by Jun Liu
20 changed files
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_multi_abd.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_multi_abd.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7r2.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer_v7r2.hpp
--- a/include/ck/utility/debug.hpp
+++ b/include/ck/utility/debug.hpp
--- a/include/ck/utility/flush_icache.hpp
+++ b/include/ck/utility/flush_icache.hpp
--- a/include/ck/utility/loop_scheduler.hpp
+++ b/include/ck/utility/loop_scheduler.hpp
--- a/include/ck/utility/sequence.hpp
+++ b/include/ck/utility/sequence.hpp
--- a/include/ck/utility/type.hpp
+++ b/include/ck/utility/type.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/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_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/grouped_gemm_tile_loop.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_tile_loop.hpp
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_tile_loop_multply.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_gemm_tile_loop_multply.hpp
--- a/library/src/tensor_operation_instance/gpu/gemm_multi_abd/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm_multi_abd/CMakeLists.txt
@@ -4,7 +4,8 @@ set(GEMM_MULTI_ABD_INSTANCES)
 list(APPEND GEMM_MULTI_ABD_INSTANCES 
 	device_gemm_xdl_multi_abd_bias_gelu_bf16_i8_bf16_mk_kn_mn_v1_instance.cpp
 	device_gemm_xdl_multi_abd_bias_gelu_bf16_i8_bf16_mk_nk_mn_v1_instance.cpp
-	device_gemm_xdl_multi_abd_bias_gelu_bf16_i8_bf16_km_kn_mn_v1_instance.cpp
+
+	device_gemm_xdl_multi_abd_multiply_bias_gelu_bf16_i8_bf16_mk_kn_mn_v1_instance.cpp
 	)

 add_instance_library(device_gemm_multi_abd_instance ${GEMM_MULTI_ABD_INSTANCES})
--- 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
--- a/library/src/tensor_operation_instance/gpu/gemm_multi_abd/device_gemm_xdl_multi_abd_bf16_i8_bf16_mk_nk_mn_common.hpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multi_abd/device_gemm_xdl_multi_abd_bf16_i8_bf16_mk_nk_mn_common.hpp
--- a/library/src/tensor_operation_instance/gpu/gemm_multi_abd/device_gemm_xdl_multi_abd_bias_gelu_bf16_i8_bf16_mk_kn_mn_v1_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multi_abd/device_gemm_xdl_multi_abd_bias_gelu_bf16_i8_bf16_mk_kn_mn_v1_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm_multi_abd/device_gemm_xdl_multi_abd_bias_gelu_bf16_i8_bf16_mk_nk_mn_v1_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_multi_abd/device_gemm_xdl_multi_abd_bias_gelu_bf16_i8_bf16_mk_nk_mn_v1_instance.cpp