Mlgoperf An Ml Guided Inliner To Optimize Performance

# MLGOPerf: An ML Guided Inliner to Optimize Performance

**arXiv ID:** 2207.08389
**Authors:** Amir H. Ashouri, Mostafa Elhoushi, Yuzhe Hua, Xiang Wang, Muhammad Asif Manzoor, Bryan Chan, Yaoqing Gao
**Published:** 2022-07-18T05:47:29Z
**Abstract:**
For the past 25 years, we have witnessed an extensive application of Machine Learning to the Compiler space; the selection and the phase-ordering problem. However, limited works have been upstreamed into the state-of-the-art compilers, i.e., LLVM, to seamlessly integrate the former into the optimization pipeline of a compiler to be readily deployed by the user. MLGO was among the first of such projects and it only strives to reduce the code size of a binary with an ML-based Inliner using Reinforcement Learning.
  This paper presents MLGOPerf; the first end-to-end framework capable of optimizing performance using LLVM's ML-Inliner. It employs a secondary ML model to generate rewards used for training a retargeted Reinforcement learning agent, previously used as the primary model by MLGO. It does so by predicting the post-inlining speedup of a function under analysis and it enables a fast training framework for the primary model which otherwise wouldn't be practical. The experimental results show MLGOPerf is able to gain up to 1.8% and 2.2% with respect to LLVM's optimization at O3 when trained for performance on SPEC CPU2006 and Cbench benchmarks, respectively. Furthermore, the proposed approach provides up to 26% increased opportunities to autotune code regions for our benchmarks which can be translated into an additional 3.7% speedup value.

## Skill Description

This skill is generated from the arXiv paper: MLGOPerf: An ML Guided Inliner to Optimize Performance (2207.08389).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2207.08389](http://arxiv.org/abs/2207.08389v2)