mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-26 22:35:43 +00:00
f5293d253c
### Description The default thread count methodology by onnxruntime did not account for new upcoming Intel microarchitectures leading to a suboptimal thread count. Optimizing the thread count for new Intel microarchitectures reveal gains on the majority of models across datatypes and shows gains up to ~1.5x speedup. ### Motivation and Context Applications should run on Intel with the most performant thread configuration for the majority of models. With new microarchitectures, adjusting the thread count methodology is required to take advantage of their differences. <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> |
||
|---|---|---|
| .. | ||
| impl | ||
| inc | ||
| pch | ||
| FeatureValues.h | ||
| HardwareCoreEnumerator.cpp | ||
| HardwareCoreEnumerator.h | ||
| ImageFeatureDescriptor.cpp | ||
| ImageFeatureDescriptor.h | ||
| ImageFeatureValue.cpp | ||
| ImageFeatureValue.h | ||
| LearningModel.cpp | ||
| LearningModel.h | ||
| LearningModelBinding.cpp | ||
| LearningModelBinding.h | ||
| LearningModelDevice.cpp | ||
| LearningModelDevice.h | ||
| LearningModelEvaluationResult.cpp | ||
| LearningModelEvaluationResult.h | ||
| LearningModelSession.cpp | ||
| LearningModelSession.h | ||
| LearningModelSessionOptions.cpp | ||
| LearningModelSessionOptions.h | ||
| MapFeatureDescriptor.cpp | ||
| MapFeatureDescriptor.h | ||
| NumericData.cpp | ||
| SequenceFeatureDescriptor.cpp | ||
| SequenceFeatureDescriptor.h | ||
| StringData.cpp | ||
| TensorFeatureDescriptor.cpp | ||
| TensorFeatureDescriptor.h | ||
| VectorBackedBuffer.cpp | ||
| VectorBackedBuffer.h | ||