saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-06-27 03:11:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/onnxruntime/test/framework
History
Changming Sun 6b89c7ad04
Let mlas use session thread pool (#1609) 
1.Let mlas use session thread pool
2.Remove onnxruntime_USE_MLAS cmake option
3. Remove the win32 thread pool code inside mlas

mlas will:

1.use ort thread pool if it get passed in
2.use openmp if the threadpool parameter is nullptr
3.run single threaded if the threadpool parameter is nullptr and openmp is disabled.
2019-08-16 13:21:15 -07:00
..
cuda Remove memory copy between TensorRT and CUDA (#1561) 2019-08-08 19:31:39 -07:00
inference_session_without_environment move environment.h/cc from framework to session project/folder. (#1241) 2019-06-17 18:01:21 -07:00
allocation_planner_test.cc Let mlas use session thread pool (#1609) 2019-08-16 13:21:15 -07:00
allocator_test.cc Move CopyTensor out of IExecutionProvider interface. (#1268) 2019-07-11 14:49:20 -07:00
bfc_arena_test.cc Initial bootstrap commit. 2018-11-19 16:48:22 -08:00
data_types_test.cc Use cmath instead of math.h for fabs (#1217) 2019-06-13 10:58:49 +10:00
dummy_allocator.cc Various optimizations to reduce the setup and device copying cost outside of the call to ExecuteGraph. (#470) 2019-02-20 12:12:17 +10:00
dummy_allocator.h Various optimizations to reduce the setup and device copying cost outside of the call to ExecuteGraph. (#470) 2019-02-20 12:12:17 +10:00
dummy_provider.cc Various optimizations to reduce the setup and device copying cost outside of the call to ExecuteGraph. (#470) 2019-02-20 12:12:17 +10:00
dummy_provider.h Move CopyTensor out of IExecutionProvider interface. (#1268) 2019-07-11 14:49:20 -07:00
execution_frame_test.cc Let mlas use session thread pool (#1609) 2019-08-16 13:21:15 -07:00
float_16_test.cc Cleanup naming of test input to use .onnx for models. (#1337) 2019-07-04 13:10:29 +10:00
inference_session_test.cc Serialize optimized onnx model (#1470) 2019-08-12 18:43:40 -07:00
insert_cast_transformer_test.cc Fix bug in the transformer that removes unnecessary Cast nodes where it was re-processing removed nodes leading to multiple calls to RemoveNode for the same node. (#1291) 2019-06-25 15:17:08 +10:00
local_kernel_registry_test.cc Cleanup naming of test input to use .onnx for models. (#1337) 2019-07-04 13:10:29 +10:00
math_test.cc Let mlas use session thread pool (#1609) 2019-08-16 13:21:15 -07:00
mem_pattern_planner_test.cc Initial bootstrap commit. 2018-11-19 16:48:22 -08:00
memcpy_transformer_test.cc Fix bug in TransformerMemcpy (#1413) 2019-07-19 13:54:08 -07:00
model_builder_utils.h Initial bootstrap commit. 2018-11-19 16:48:22 -08:00
op_kernel_test.cc Move CopyTensor out of IExecutionProvider interface. (#1268) 2019-07-11 14:49:20 -07:00
opaque_kernels_test.cc Remove unnecessary casts from OrtValue to MLValue(#1051) 2019-05-17 07:52:59 -07:00
parallel_executor_test.cc Rename Tensor.Size() to Tensor.SizeInBytes() (#1502) 2019-07-26 14:15:53 -07:00
path_lib_test.cc Remove an unnecessary check in GetDirNameFromFilePath function (#616) 2019-03-17 23:55:25 -07:00
session_state_test.cc Let mlas use session thread pool (#1609) 2019-08-16 13:21:15 -07:00
shape_inference_test.cc Document the Graph header files and cleanup some issues. (#42) 2018-11-28 08:42:11 -08:00
sparse_kernels_test.cc Rename Tensor.Size() to Tensor.SizeInBytes() (#1502) 2019-07-26 14:15:53 -07:00
tensor_test.cc Support large model(>2GB) (#520) 2019-03-05 21:27:12 -08:00
tensorutils_test.cc Support large model(>2GB) (#520) 2019-03-05 21:27:12 -08:00
test_main.cc move environment.h/cc from framework to session project/folder. (#1241) 2019-06-17 18:01:21 -07:00
test_tensor_loader.cc Remove unneeded C APIs + some refactoring. (#1555) 2019-08-07 11:05:29 -07:00
test_utils.cc Remove memory copy between TensorRT and CUDA (#1561) 2019-08-08 19:31:39 -07:00
test_utils.h Don't create implicit input for outer scope value if there is a subgraph input with the same name. (#1186) 2019-08-02 07:23:41 +10:00
TestAllocatorManager.cc Remove memory copy between TensorRT and CUDA (#1561) 2019-08-08 19:31:39 -07:00
TestAllocatorManager.h Abbreviate ONNXRuntime as Ort in all of our public APIs (#175) 2018-12-14 14:54:23 -08:00