Neural Network Inference on OnePlus 11
8.5Baseline Latency (ms)Fine-Grained CPU-GPU Co-Execution
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Fine-Grained CPU-GPU Co-ExecutionNeural Network=ResNet-18, CPU Threads=32025.10 | 8.5 | 6.6 | 1.29 | 6.8 | 1.25 | |
| Fine-Grained CPU-GPU Co-ExecutionNeural Network=ResNet-34, CPU Threads=32025.10 | 17.6 | 13.5 | 1.31 | 13.8 | 1.27 | |
| Fine-Grained CPU-GPU Co-ExecutionNeural Network=VGG16, CPU Threads=32025.10 | 27.4 | 25.3 | 1.09 | 26.2 | 1.05 | |
| Fine-Grained CPU-GPU Co-ExecutionNeural Network=Inception-v3, CPU Threads=32025.10 | 44.2 | 36.2 | 1.22 | 37.8 | 1.17 |