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

0b11569f · Chao Liu · e8d3a0fb · fa9a0a5c · 0b11569f · 0b11569f
Commit 0b11569f authored Jul 01, 2022 by Chao Liu
20 changed files
--- 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
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8.cpp
--- a/library/src/utility/conv_util.cpp
+++ b/library/src/utility/conv_util.cpp
--- a/profiler/CMakeLists.txt
+++ b/profiler/CMakeLists.txt
--- a/profiler/include/data_type_enum.hpp
+++ b/profiler/include/data_type_enum.hpp