Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Neural Network Inference on Pixel 4
Loading...
17.5
Baseline Latency (ms)
Fine-Grained CPU-GPU Co-Execution
14.22
36.36
58.5
80.64
Oct 24, 2025
Baseline Latency (ms)
Individual Ops Latency (ms)
Individual Ops Speedup
End-to-End Latency (ms)
End-to-End Speedup
Updated 5mo ago
Evaluation Results
Method
Method
Links
Baseline Latency (ms)
Individual Ops Latency (ms)
Individual Ops Speedup
End-to-End Latency (ms)
End-to-End Speedup
Fine-Grained CPU-GPU Co-Execution
Neural Network=ResNet-...
2025.10
17.5
11
1.59
11.4
1.54
Fine-Grained CPU-GPU Co-Execution
Neural Network=ResNet-...
2025.10
37.5
22.2
1.69
22.5
1.67
Fine-Grained CPU-GPU Co-Execution
Neural Network=VGG16,...
2025.10
83.3
70.8
1.18
73
1.14
Fine-Grained CPU-GPU Co-Execution
Neural Network=Incepti...
2025.10
99.5
59.1
1.68
61.5
1.62
Feedback
Search any
task
Search any
task