Portable and architecture independent parallel performance tuning using BSP

S. A. Jarvis; J. M.D. Hill; C. J. Siniolakis; V. P. Vasilev

doi:10.1016/S0167-8191(02)00160-6

Portable and architecture independent parallel performance tuning using BSP

S. A. Jarvis^*, J. M.D. Hill, C. J. Siniolakis, V. P. Vasilev

^*Corresponding author for this work

Engineering and Physical Sciences

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

A call-graph profiling tool has been designed and implemented to analyse the efficiency of programs written in BSPlib. This tool highlights computation and communication imbalance in parallel programs, exposing portions of program code which are amenable to improvement. A unique feature of this profiler is that it uses the bulk synchronous parallel cost model, thus providing a mechanism for portable and architecture-independent parallel performance tuning. In order to test the capabilities of the model on a real-world example, the performance characteristics of an SQL query processing application are investigated on a number of different parallel architectures.

Original language	English
Pages (from-to)	1587-1609
Number of pages	23
Journal	Parallel Computing
Volume	28
Issue number	11
DOIs	https://doi.org/10.1016/S0167-8191(02)00160-6
Publication status	Published - Nov 2002

Keywords

Bulk synchronous parallel
Profiling
Program efficiency

ASJC Scopus subject areas

Software
Theoretical Computer Science
Hardware and Architecture
Computer Networks and Communications
Computer Graphics and Computer-Aided Design
Artificial Intelligence

Access to Document

10.1016/S0167-8191(02)00160-6

Cite this

@article{fccf56388dea446ba0b25802c39c26ff,

title = "Portable and architecture independent parallel performance tuning using BSP",

abstract = "A call-graph profiling tool has been designed and implemented to analyse the efficiency of programs written in BSPlib. This tool highlights computation and communication imbalance in parallel programs, exposing portions of program code which are amenable to improvement. A unique feature of this profiler is that it uses the bulk synchronous parallel cost model, thus providing a mechanism for portable and architecture-independent parallel performance tuning. In order to test the capabilities of the model on a real-world example, the performance characteristics of an SQL query processing application are investigated on a number of different parallel architectures.",

keywords = "Bulk synchronous parallel, Profiling, Program efficiency",

author = "Jarvis, {S. A.} and Hill, {J. M.D.} and Siniolakis, {C. J.} and Vasilev, {V. P.}",

year = "2002",

month = nov,

doi = "10.1016/S0167-8191(02)00160-6",

language = "English",

volume = "28",

pages = "1587--1609",

journal = "Parallel Computing",

issn = "0167-8191",

publisher = "Elsevier",

number = "11",

}

TY - JOUR

T1 - Portable and architecture independent parallel performance tuning using BSP

AU - Jarvis, S. A.

AU - Hill, J. M.D.

AU - Siniolakis, C. J.

AU - Vasilev, V. P.

PY - 2002/11

Y1 - 2002/11

N2 - A call-graph profiling tool has been designed and implemented to analyse the efficiency of programs written in BSPlib. This tool highlights computation and communication imbalance in parallel programs, exposing portions of program code which are amenable to improvement. A unique feature of this profiler is that it uses the bulk synchronous parallel cost model, thus providing a mechanism for portable and architecture-independent parallel performance tuning. In order to test the capabilities of the model on a real-world example, the performance characteristics of an SQL query processing application are investigated on a number of different parallel architectures.

AB - A call-graph profiling tool has been designed and implemented to analyse the efficiency of programs written in BSPlib. This tool highlights computation and communication imbalance in parallel programs, exposing portions of program code which are amenable to improvement. A unique feature of this profiler is that it uses the bulk synchronous parallel cost model, thus providing a mechanism for portable and architecture-independent parallel performance tuning. In order to test the capabilities of the model on a real-world example, the performance characteristics of an SQL query processing application are investigated on a number of different parallel architectures.

KW - Bulk synchronous parallel

KW - Profiling

KW - Program efficiency

UR - http://www.scopus.com/inward/record.url?scp=0036828252&partnerID=8YFLogxK

U2 - 10.1016/S0167-8191(02)00160-6

DO - 10.1016/S0167-8191(02)00160-6

M3 - Article

AN - SCOPUS:0036828252

SN - 0167-8191

VL - 28

SP - 1587

EP - 1609

JO - Parallel Computing

JF - Parallel Computing

IS - 11

ER -

Portable and architecture independent parallel performance tuning using BSP

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this