Enhancing the Effectiveness of Inlining in Automatic Parallelization

Enhancing the Effectiveness of Inlining in Automatic Parallelization
复制标题

增强自动并行化中内联的有效性

DOI:
10.1007/s10766-021-00722-1
复制
发表时间:
2022
影响因子:
1.5
通讯作者:
Psarris, Kleanthis
Psarris, Kleanthis
中科院分区:
计算机科学4区
文献类型:
--
作者:
Guo, Jichi;Yi, Qing;Psarris, Kleanthis

文献摘要

参考文献

相似文献

多核架构的出现使得优化编译器必须自动提取由驻留在不同文件中的许多子例程组成的大型科学应用程序的并行性。内联是一种众所周知的技术,可用于消除程序边界并实现更积极的循环并行化。然而,传统的内联不能应用于没有源代码的外部库,并且当过度应用时,会因代码过于复杂而降低编译器优化的有效性。本文重点介绍了我们在使用 Polaris 优化编译器应用传统内联与自动循环并行化相结合时遇到的一些障碍,并提出了一种新方法,即基于注释的内联,以有效克服这些障碍。我们的实验结果表明,基于注释的内联方法可以消除传统内联的负面影响,同时增强 PERFECT 基准套件中大多数应用程序的过程间并行化的有效性。
The emergence of multi-core architectures makes it essential for optimizing compilers to automatically extract parallelism for large scientific applications composed of many subroutines residing in different files. Inlining is a well-known technique which can be used to erase procedural boundaries and enable more aggressive loop parallelization. However, conventional inlining cannot be applied to external libraries where the source code is not available, and when overly applied, it can degrade the effectiveness of compiler optimizations due to excessive code complexity. This paper highlights some obstacles we encountered while applying conventional inlining combined with automatic loop parallelization using the Polaris optimizing compiler and presents a new approach, annotation-based inlining, to effectively overcome these obstacles. Our experimental results show that the annotation-based inlining approach can eliminate negative impact of conventional inlining while enhancing the effectiveness of interprocedural parallelization for a majority of applications from the PERFECT benchmark suite.
DOI: --
发表时间: 2006
期刊: ACM-SIGPLAN Symposium on Programming Language Design and Implementation
影响因子: --
作者:
Spyridon Triantafyllis;Matthew J. Bridges;Easwaran Raman;Guilherme Ottoni;David I. August
通讯作者: David I. August
快速有效的程序内联
DOI: --
发表时间: 1997
期刊: Sensors Applications Symposium
影响因子: --
作者:
Oscar Waddell;R. Dybvig
通讯作者: R. Dybvig
统一的过程间并行性检测
DOI: --
发表时间: 2001
影响因子: 1.5
作者:
J. Hoeflinger;Y. Paek;K. Yi
通讯作者: K. Yi
用于改进多粒并行性的选择性内联扩展
DOI: --
发表时间: 2004
期刊: Parallel and Distributed Computing and Networks
影响因子: --
作者:
J. Shirako;Kouhei Nagasawa;K. Ishizaka;M. Obata;H. Kasahara
通讯作者: H. Kasahara
在分布式内存多计算机上利用数据和功能并行性的框架
DOI: --
发表时间: 1994
期刊:
影响因子: --
作者:
S. Ramaswamy;S. Sapatnekar;P. Banerjee
通讯作者: P. Banerjee