A comparative study of static and profile-based heuristics for inlining-Reference-Cited by-同舟云学术

A comparative study of static and profile-based heuristics for inlining

Published:2000-07 Issue:7 Volume:35 Page:52-64
ISSN:0362-1340
Container-title:ACM SIGPLAN Notices
language:en
Short-container-title:SIGPLAN Not.

Author:

Arnold Matthew¹,Fink Stephen²,Sarkar Vivek²,Sweeney Peter F.²

Affiliation:

1. Department of Computer Science, Rutgers, The State University of NJ

2. IBM Thomas J. Watson Research Center, P.O. Box 704, Yorktown Heights, NY

Abstract

In this paper, we present a comparative study of static and profile-based heuristics for inlining. Our motivation for this study is to use the results to design the best inlining algorithm that we can for the Jalapeño dynamic optimizing compiler for Java [6]. We use a well-known approximation algorithm for the KNAPSACK problem as a common “meta-algorithm” for the inlining heuristics studied in this paper. We present performance results for an implementation of these inlining heuristics in the Jalapeño dynamic optimizing compiler. Our performance results show that the inlining heuristics studied in this paper can lead to significant speedups in execution time (up to 1.68x) even with modest limits on code size expansion (at most 10%).

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design,Software

Link

https://dl.acm.org/doi/pdf/10.1145/351403.351416

Reference17 articles.

1. Implementing jalapeño in Java

2. Exploiting hardware performance counters with flow and context sensitive profiling

3. Aggressive inlining

Cited by 14 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Optimization-Aware Compiler-Level Event Profiling;ACM Transactions on Programming Languages and Systems;2023-06-26

2. Understanding and exploiting optimal function inlining;Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems;2022-02-22

3. Using machine learning to predict the code size impact of duplication heuristics in a dynamic compiler;Proceedings of the 18th ACM SIGPLAN International Conference on Managed Programming Languages and Runtimes;2021-09-29

4. Enhancing the Effectiveness of Inlining in Automatic Parallelization;International Journal of Parallel Programming;2021-08-06

5. PIBE: practical kernel control-flow hardening with profile-guided indirect branch elimination;Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems;2021-04-17