Merge remote-tracking branch 'origin/develop' into cpu_avx2

b79df771 · carlushuang · 05d38218 · 63914743 · b79df771 · b79df771
Commit b79df771 authored Jul 12, 2022 by carlushuang
20 changed files
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/gemm/device_gemm_xdl_splitk_f32_f32_f32_mk_nk_mn_instance.cpp
--- 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_xdl_f16_f16_f16_km_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_km_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_kn_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/grouped_gemm/device_grouped_gemm_xdl_f16_f16_f16_mk_nk_mn_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/normalization/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/normalization/device_softmax_f16_f16_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_softmax_f16_f16_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/normalization/device_softmax_f32_f32_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/normalization/device_softmax_f32_f32_instance.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8.cpp