benchmarks.SaturnNPU.scripts.plot_npu_coverage
Source: benchmarks/SaturnNPU/scripts/plot_npu_coverage.py
benchmarks.SaturnNPU.scripts.plot_npu_coverage
Generate useful plots for SmolVLA NPU kernel decomposition.
Only generates plots that are actually informative
- Pareto coverage — which kernels to implement first
- Per-PyTorch-layer op decomposition — what each layer becomes
- Cross-level flow diagram — how ops transform through compilation
Usage
python scripts/plot_npu_coverage.py benchmarks/SaturnNPU/smolvla_graph_manifest.json --layer-trace benchmarks/SaturnNPU/layer_decomposition.json --output-dir benchmarks/SaturnNPU/plots/
plot_cross_level_flow(manifest, output_dir)
Flow diagram: PyTorch ops -> Linalg/Input -> Global-Opt.
plot_layer_decomposition(trace_data, output_dir)
Stacked bar: what ops each PyTorch layer type decomposes into.
plot_pareto(manifest, output_dir)
Which kernels to implement first by FLOP impact.