paper-with-me

홈 › Papers

VeriLocc: End-to-End Cross-Architecture Register Allocation via LLM

2025-06-20 · Lesheng Jin, Zhenyuan Ruan, Haohui Mai, Jingbo Shang

Modern GPUs evolve rapidly, yet production compilers still rely on hand-crafted register allocation heuristics that require substantial re-tuning for each hardware generation. We introduce VeriLocc, a framework that combines large language models (LLMs) with formal compiler techniques to enable generalizable and verifiable register allocation across GPU architectures. VeriLocc fine-tunes an LLM to translate intermediate representations (MIRs) into target-specific register assignments, aided by static analysis for cross-architecture normalization and generalization and a verifier-guided regeneration loop to ensure correctness. Evaluated on matrix multiplication (GEMM) and multi-head attention (MHA), VeriLocc achieves 85-99% single-shot accuracy and near-100% pass@100. Case study shows that VeriLocc discovers more performant assignments than expert-tuned libraries, outperforming rocBLAS by over 10% in runtime.

📄 PDF Abstract BibTeX arXiv:2506.17506

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Similar Papers 제목 키워드 기반

RL4ReAl: Reinforcement Learning for Register Allocation

2022-04-05 · S. VenkataKeerthy, Siddharth Jain, Anilava Kundu, Rohit Aggarwal 외

We aim to automate decades of research and experience in register allocation, leveraging machine learning. We tackle this problem by embedding a multi-agent reinforcement learning algorithm within LLVM, training it with …

Hierarchical Reinforcement LearningMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1

Deep Learning-based Hybrid Graph-Coloring Algorithm for Register Allocation

2019-12-08 · Dibyendu Das, Shahid Asghar Ahmad, Kumar Venkataramanan

Register allocation, which is a crucial phase of a good optimizing compiler, relies on graph coloring. Hence, an efficient graph coloring algorithm is of paramount importance. In this work we try to learn a good heuristi…

CPUDeep Learning

Reinforcement Learning for Graph Coloring: Understanding the Power and Limits of Non-Label Invariant Representations

2024-01-23 · Chase Cummins, Richard Veras

Register allocation is one of the most important problems for modern compilers. With a practically unlimited number of user variables and a small number of CPU registers, assigning variables to registers without conflict…

CPU

Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B

2026-08-24 · Defu Lin, Wenhui Chen, Ziyao Lin, Jianlin Chen 외 arxiv

Embodied multimodal agents must answer from growing observation streams under a fixed per-decision token budget. We formalize this constraint through four resource walls: a perceptual Shannon wall for bounded state, a ho…

Sampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Neural Combinatorial Optimization

2026-08-13 · Jinhyung Bae arxiv

Neural combinatorial optimization (NCO) solvers report the best of many sampled solutions per instance, and the sample count is, by convention, identical for every instance. Whether a non-uniform allocation of a fixed to…