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

b238662a · Chao Liu · 7279e123 · e579c9e5 · 7279e123 · 7279e123
Commit b238662a authored May 25, 2022 by Chao Liu
20 changed files
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_b16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_f32_f32_b16.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_blockwise_second_call_i32_i32_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_i32_i32_i8.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_i8_i8_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_second_call_i8_i8_i8.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_b16_f32_b16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_b16_f32_b16.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_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_multiblock_partial_reduce_i8_i32_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_i8_i32_i8.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_i8_i8_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_partial_reduce_i8_i8_i8.cpp
--- a/profiler/CMakeLists.txt
+++ b/profiler/CMakeLists.txt
--- a/profiler/include/profile_gemm_impl.hpp
+++ b/profiler/include/profile_gemm_impl.hpp
--- a/profiler/include/profile_reduce_impl.hpp
+++ b/profiler/include/profile_reduce_impl.hpp
--- a/profiler/src/profile_batched_gemm.cpp
+++ b/profiler/src/profile_batched_gemm.cpp
--- a/profiler/src/profile_batched_gemm_reduce.cpp
+++ b/profiler/src/profile_batched_gemm_reduce.cpp