ML²Tuner: Efficient Code Tuning via Multi-Level Machine Learning Models

2024/11/16 by Jeongwoo Cha, Cha, JooHyoung, Munyoung Lee +9
Computer Science · #Computational Physics and Python Applications #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2411.10764

openalex publication_date 2024/11/16 · openalex created_date 2024/11/21 · openalex updated_date 2026/07/28

Abstract

The increasing complexity of deep learning models necessitates specialized hardware and software optimizations, particularly for deep learning accelerators. Existing autotuning methods often suffer from prolonged tuning times due to profiling invalid configurations, which can cause runtime errors. We introduce ML²Tuner, a multi-level machine learning tuning technique that enhances autotuning efficiency by incorporating a validity prediction model to filter out invalid configurations and an advanced performance prediction model utilizing hidden features from the compilation process. Experimental results on an extended VTA accelerator demonstrate that ML²Tuner achieves equivalent performance improvements using only 12.3% of the samples required with a similar approach as TVM and reduces invalid profiling attempts by an average of 60.8%, Highlighting its potential to enhance autotuning performance by filtering out invalid configurations

Related

• MLtuner: System Support for Automatic Machine Learning Tuning
• Tuning the Tuner: Introducing Hyperparameter Optimization for Auto-Tuning
• Introducing Instruction-Accurate Simulators for Performance Estimation of Autotuning Workloads
• A Deep-Learning-Aided Pipeline for Efficient Post-Silicon Tuning
• TVM: An Automated End-to-End Optimizing Compiler for Deep Learning