SyncAI.news, a Varaisys broadcasting
GraphPass: A Study of Graph Neural Networks for Compiler Pass Selection
MS

Mohammed Saqlain

· 1 min read

ResearcharXiv cs.LG

GraphPass: A Study of Graph Neural Networks for Compiler Pass Selection

arXiv:2611.19821v1 Announce Type: new Abstract: Compiler pass selection is usually governed by fixed pipelines (-O2, -O3) or hand-written heuristics. We study whether a graph neural network (GNN) over a program's control-flow graph (CFG) can select among a fixed menu of five pass sequences in a single forward pass. GraphPass encodes each CFG with a graph attention (GAT) or graph convolutional (GCN) encoder and classifies it into one of the five sequences. On a synthetic benchmark of 5,000 generated CFGs in five program families, both encoders agree with the benchmark's reference label on about 92% of held-out programs, versus 68.4% for a hand-written rule-based heuristic and 85% for a flat MLP. An edge ablation indicates that this gain comes from per-block processing rather than from CFG edges: a GCN given the same basic-block features with all edges removed scores 95.0%, versus 92.2% with the true CFG. In this benchmark the label is determined by the program family, so the task amounts to family recognition. Real-compiler speedup is not measured. Inference costs O(|V| + |E|) per CFG, measured at 1.7 ms for a typical program and about 0.8 s for a 100,000-block graph on one CPU core.

Original source

This story was published by arXiv cs.LG and written by Mohammed Saqlain. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News