• Home
  • Search
  • Structure-driven optimizations for amorphous data-parallel programs
  • Open Access IconOpen Access
  • Cite Icon4
  • https://doi.org/10.1145/1837853.1693457Copy DOI Icon

Structure-driven optimizations for amorphous data-parallel programs

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Irregular algorithms are organized around pointer-based data structures such as graphs and trees, and they are ubiquitous in applications. Recent work by the Galois project has provided a systematic approach for parallelizing irregular applications based on the idea of optimistic or speculative execution of programs. However, the overhead of optimistic parallel execution can be substantial. In this paper, we show that many irregular algorithms have structure that can be exploited and present three key optimizations that take advantage of algorithmic structure to reduce speculative overheads. We describe the implementation of these optimizations in the Galois system and present experimental results to demonstrate their benefits. To the best of our knowledge, this is the first system to exploit algorithmic structure to optimize the execution of irregular programs.

Similar Papers
  • Conference Article
  • Citations13

Scheduling Issues in Optimistic Parallelization

  • Jan 01, 2007
  • Milind Kulkarni +1
  • Conference Article
  • Citations70

Scheduling strategies for optimistic parallel execution of irregular programs

  • Jun 14, 2008
  • Milind Kulkarni +6
  • Research Article
  • Citations5

SPMD execution of programs with pointer-based data structures on distributed-memory machines

  • Oct 01, 1992
  • Journal of Parallel and Distributed Computing
  • Rajiv Gupta
  • Conference Article
  • Citations460

Optimistic parallelism requires abstractions

  • Jun 10, 2007
  • Milind Kulkarni +5
  • Conference Article
  • Citations27

Analysis of TCP and DTN Retransmission Algorithms in Presence of Channel Disruptions

  • Jul 20, 2009
  • Carlo Caini +4
  • Conference Article
  • Citations16

Dynamic pointer alignment

  • Jun 21, 1997
  • Xingbin Zhang +1
  • Conference Article

Data-parallel abstractions for irregular programs

  • May 05, 2008
  • Keshav K Pingali
  • Conference Article
  • Citations2

Parallelizing irregular algorithms

  • Oct 21, 2011
  • Pedro Monteiro +2
  • Research Article
  • Citations86

Optimistic parallelism requires abstractions

  • Jun 10, 2007
  • ACM SIGPLAN Notices
  • Milind Kulkarni +5
  • Research Article
  • Citations2466

Bounds on Multiprocessing Timing Anomalies

  • Mar 01, 1969
  • SIAM Journal on Applied Mathematics
  • R L Graham
  • Research Article
  • Citations43

How much parallelism is there in irregular applications?

  • Feb 14, 2009
  • ACM SIGPLAN Notices
  • Milind Kulkarni +4
  • Conference Article
  • Citations153

How much parallelism is there in irregular applications?

  • Feb 14, 2009
  • Milind Kulkarni +4
  • Research Article
  • Citations11

Scaling Runtimes for Irregular Algorithms to Large-Scale NUMA Systems

  • Aug 01, 2015
  • Computer
  • Andrew Lenharth +1
  • Research Article
  • Citations1

Dynamic pointer alignment

  • Jun 21, 1997
  • ACM SIGPLAN Notices
  • Xingbin Zhang +1
  • Research Article
  • Citations11

Ddbx-LPP: A dynamic software tool for debugging asynchronous distributed algorithms on loosely coupled parallel processors

  • Jul 01, 1993
  • Journal of Systems and Software
  • Mariano G Fernandez +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.