clean

cab8f2e5 · Jing Zhang · c20aabc3 · 9a17e7fb · cab8f2e5 · cab8f2e5
Commit cab8f2e5 authored Mar 14, 2022 by Jing Zhang
20 changed files
--- 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_second_call_f16_f16_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f16_f16_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f64.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f64_f64_f64.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_partial_reduce_f16_f16_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f16_f16_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f16_f32_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f16_f32_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f32_f32_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f32_f32_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f32_f64_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f32_f64_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f64_f64_f64.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_f64_f64_f64.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/profiler/CMakeLists.txt
+++ b/profiler/CMakeLists.txt