Optimizing irregular computations on SIMD machines: A case study

John S. Conery; Michael Lynch; Tommy Hovland

Optimizing irregular computations on SIMD machines: A case study

John S. Conery
, Michael Lynch
, Tommy Hovland

Research output: Contribution to conference › Paper › peer-review

Abstract

Data-parallel computations with regular structure - fixed data size and predictable control patterns - can be implemented efficiently on SIMD architectures. However many large applications have irregular structure, either data sets that vary in size as the computation progresses or control structures that select different subsets of the processors at each stage of the computation. In this paper we describe a stochastic biology simulation and some of the methods we used to improve its performance on the MasPar MP-1104. We present a simple model for evaluating the performance of a data parallel application and use the model to improve the performance of the simulator.

Original language	English (US)
Pages	222-230
Number of pages	9
State	Published - Jan 1 1995
Externally published	Yes
Event	Proceedings of the 5th Symposium on the Frontiers of Massively Parallel Computation - McLean, VA, USA Duration: Feb 6 1995 → Feb 9 1995

Other

Other	Proceedings of the 5th Symposium on the Frontiers of Massively Parallel Computation
City	McLean, VA, USA
Period	2/6/95 → 2/9/95

ASJC Scopus subject areas

Hardware and Architecture

Cite this

@conference{ea5d1a095902466b9bf4f5556a72b686,

title = "Optimizing irregular computations on SIMD machines: A case study",

abstract = "Data-parallel computations with regular structure - fixed data size and predictable control patterns - can be implemented efficiently on SIMD architectures. However many large applications have irregular structure, either data sets that vary in size as the computation progresses or control structures that select different subsets of the processors at each stage of the computation. In this paper we describe a stochastic biology simulation and some of the methods we used to improve its performance on the MasPar MP-1104. We present a simple model for evaluating the performance of a data parallel application and use the model to improve the performance of the simulator.",

author = "Conery, \{John S.\} and Michael Lynch and Tommy Hovland",

year = "1995",

month = jan,

day = "1",

language = "English (US)",

pages = "222--230",

note = "Proceedings of the 5th Symposium on the Frontiers of Massively Parallel Computation ; Conference date: 06-02-1995 Through 09-02-1995",

}

TY - CONF

T1 - Optimizing irregular computations on SIMD machines

T2 - Proceedings of the 5th Symposium on the Frontiers of Massively Parallel Computation

AU - Conery, John S.

AU - Lynch, Michael

AU - Hovland, Tommy

PY - 1995/1/1

Y1 - 1995/1/1

N2 - Data-parallel computations with regular structure - fixed data size and predictable control patterns - can be implemented efficiently on SIMD architectures. However many large applications have irregular structure, either data sets that vary in size as the computation progresses or control structures that select different subsets of the processors at each stage of the computation. In this paper we describe a stochastic biology simulation and some of the methods we used to improve its performance on the MasPar MP-1104. We present a simple model for evaluating the performance of a data parallel application and use the model to improve the performance of the simulator.

AB - Data-parallel computations with regular structure - fixed data size and predictable control patterns - can be implemented efficiently on SIMD architectures. However many large applications have irregular structure, either data sets that vary in size as the computation progresses or control structures that select different subsets of the processors at each stage of the computation. In this paper we describe a stochastic biology simulation and some of the methods we used to improve its performance on the MasPar MP-1104. We present a simple model for evaluating the performance of a data parallel application and use the model to improve the performance of the simulator.

UR - https://www.scopus.com/pages/publications/0029196641

UR - https://www.scopus.com/pages/publications/0029196641#tab=citedBy

M3 - Paper

AN - SCOPUS:0029196641

SP - 222

EP - 230

Y2 - 6 February 1995 through 9 February 1995

ER -

Optimizing irregular computations on SIMD machines: A case study

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this