• Home
  • Search
  • Automatically Tuning Parallel and Parallelized Programs
  • Open Access IconOpen Access
  • Cite Icon18
  • https://doi.org/10.1007/978-3-642-13374-9_9Copy DOI Icon

Automatically Tuning Parallel and Parallelized Programs

  • Jan 1, 2010
  • Chirag Dave +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Abstract In today’s multicore era, parallelization of serial code is essential in order to exploit the architectures’ performance potential. Parallelization, especially of legacy code, however, proves to be a challenge as manual efforts must either be directed towards algorithmic modifications or towards analysis of computationally intensive sections of code for the best possible parallel performance, both of which are difficult and time-consuming. Automatic parallelization uses sophisticated compile-time techniques in order to identify parallelism in serial programs, thus reducing the burden on the program developer. Similar sophistication is needed to improve the performance of hand-parallelized programs. A key difficulty is that optimizing compilers are generally unable to estimate the performance of an application or even a program section at compile-time, and so the task of performance improvement invariably rests with the developer. Automatic tuning uses static analysis and runtime performance metrics to determine the best possible compile-time approach for optimal application performance. This paper describes an offline tuning approach that uses a source-to-source parallelizing compiler, Cetus, and a tuning framework to tune parallel application performance. The implementation uses an existing, generic tuning algorithm called Combined Elimination to study the effect of serializing parallelizable loops based on measured whole program execution time, and provides a combination of parallel loops as an outcome that ensures to equal or improve performance of the original program. We evaluated our algorithm on a suite of hand-parallelized C benchmarks from the SPEC OMP2001 and NAS Parallel benchmarks and provide two sets of results. The first ignores hand-parallelized loops and only tunes application performance based on Cetus-parallelized loops. The second set of results considers the tuning of additional parallelism in hand-parallelized code. We show that our implementation always performs near-equal or better than serial code while tuning only Cetus-parallelized loops and equal to or better than hand-parallelized code while tuning additional parallelism.KeywordsTuning MethodParallel LoopAutomatic TuningSerial ExecutionAutomatic ParallelizationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Similar Papers
  • Book Chapter
  • Citations31

Models for Advancing PRAM and Other Algorithms into Parallel Programs for a PRAM-On-Chip Platform

  • Dec 20, 2007
  • Bryant Lee +2
  • Research Article
  • Citations3

Synchronous Deterministic Parallel Programming for Multi-Cores with ForeC

  • Jun 26, 2023
  • ACM Transactions on Programming Languages and Systems
  • Eugene Yip +3
  • Dissertation

A Machine Learning and Compiler-based Approach to Automatically Parallelize Serial Programs Using OpenMP

  • Oct 01, 2011
  • Nam Quang Lam
  • Research Article

Parallelization of SPEC OMP benchmark programs with HPF and evaluation of their performances

  • Dec 01, 2006
  • Journal of Plasma Physics
  • Hitoshi Sakagami +1
  • Research Article
  • Citations6

PETRA: Performance Evaluation Tool for Modern Parallelizing Compilers

  • Mar 19, 2014
  • International Journal of Parallel Programming
  • Dheya Mustafa +1
  • Research Article
  • Citations48

The NAS Parallel Benchmarks for evaluating C++ parallel programming frameworks on shared-memory architectures

  • Jul 19, 2021
  • Future Generation Computer Systems
  • Júnior Löff +6
  • Research Article
  • Citations11

The Neural Basis of Parallel Saccade Programming: An fMRI Study

  • Nov 01, 2011
  • Journal of Cognitive Neuroscience
  • Yanbo Hu +1
  • Research Article
  • Citations18

Predicting HPC parallel program performance based on LLVM compiler

  • Dec 27, 2016
  • Cluster Computing
  • Weizhe Zhang +2
  • Conference Article
  • Citations16

The ForeC Synchronous Deterministic Parallel Programming Language for Multicores

  • Sep 01, 2016
  • Eugene Yip +3
  • Research Article

Interaction with the User in the SAPFOR System

  • Mar 22, 2021
  • Russian Digital Libraries Journal
  • Nikita Andreevich Kataev
  • Conference Article
  • Citations3

Compiler for a simplified programming language aiming on Multi Core Students' Experimental Processor

  • Dec 01, 2015
  • Y M R D Wepathana +2
  • Research Article
  • Citations7

GPU-based collision analysis between a multi-body system and numerous particles

  • Apr 01, 2013
  • Journal of Mechanical Science and Technology
  • Hye-Young Jung +2
  • PDF
  • Conference Article
  • Citations2

SPLENDID: Supporting Parallel LLVM-IR Enhanced Natural Decompilation for Interactive Development

  • Mar 25, 2023
  • Zujun Tan +7
  • Conference Article
  • Citations7

DEEP: a development environment for parallel programs

  • Mar 30, 1998
  • B.Q Brode +1
  • Research Article
  • Citations3

Intermediate Representations for Explicitly Parallel Programs

  • May 25, 2021
  • ACM Computing Surveys
  • Adilla Susungi +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.