Merge remote-tracking branch 'origin/develop' into gelu

b238662a · Chao Liu · 7279e123 · e579c9e5 · b238662a · b238662a
Commit b238662a authored May 25, 2022 by Chao Liu
20 changed files
--- a/library/src/tensor_operation_instance/gpu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/gemm/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_f32_f32_f32_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_dl_i8_i8_i8_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_c_shuffle_int8_int8_int8_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/reduce/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f16_f16_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f16_f16_f16.cpp