Search papers, labs, and topics across Lattice.
This paper introduces an online reinforcement learning (RL) approach to improve the high-performance computing (HPC) code generation capabilities of large language models (LLMs) by using runtime performance (GFLOPS) on a supercomputer as a direct reward signal. They propose a Staged Quality-Diversity (SQD) algorithm that progressively varies optimization techniques to encourage diverse learning. The authors trained Qwen2.5 Coder 14B on a double-precision matrix multiplication task using Group Relative Policy Optimization (GRPO), demonstrating improved HPC code generation.
Forget synthetic benchmarks – this work trains LLMs to write faster HPC code by directly rewarding GFLOPS measured on a real supercomputer.
Large language models (LLMs) have demonstrated strong code generation capabilities, yet the runtime performance of generated code is not guaranteed, and there have been few attempts to train LLMs using runtime performance as a reward in the HPC domain. We propose an online reinforcement learning approach that executes LLM-generated code on a supercomputer and directly feeds back the measured runtime performance (GFLOPS) as a reward. We further introduce a Staged Quality-Diversity (SQD) algorithm that progressively varies the permitted optimization techniques on a per-problem basis, enabling the model to learn code optimization from diverse perspectives. We build a distributed system connecting a GPU training cluster with a CPU benchmarking cluster, and train Qwen2.5 Coder 14B on a double-precision matrix multiplication task using Group Relative Policy Optimization (GRPO). Through two experiments, we show that reinforcement learning combining runtime performance feedback with staged optimization can improve the HPC code generation capability of LLMs.
