Accelerating Transfer-Learning-Based Autotuning with Predictive LLVM IR Performance Ranking

2026-09-14

AI Summary

本文提出了一种基于机器学习的LLVM IR性能排序方法，通过转移学习减少自动调优中的评估次数，提高了高性能计算系统的调优效率。

Abstract

As the complexity of High Performance Computing (HPC) ecosys- tems continually increases, achieving optimal performance becomes a challenge. Traditional performance autotuning techniques pro- vide promising means to navigate this complexity, these techniques remain computationally intensive and require many evaluations to find optimal configurations. This work proposes an autotuning framework that designs a machine learning-based ensemble LLVM Intermediate Representa- tion (IR) ranker, Neural Configuration Scorer (NCS). NCS ranks the performance of IRs sampled by a transfer-learning-based autotuner, improving the efficiency of the tuning process by reducing tuning overheads and circumventing subpar evaluations. By leveraging knowledge from related tasks, we are able to effectively exploit the transfer relationship to access high-performing configurations in fewer samples than traditional techniques that rely upon itera- tive refinement. Our framework can achieve similar performance improvements as state-of-the-art autotuning techniques with up to 61.67% fewer evaluations, averaging 27.85% fewer evaluations across various HPC benchmarks.

Problem

• High Performance Computing
• autotuning
• performance optimization

Innovation

• machine learning-based ensemble
• LLVM IR performance ranking
• transfer-learning-based autotuning
• Neural Configuration Scorer (NCS)
• performance autotuning