Performance Evaluation of Chapel’s Task Parallel Features

Michele Weiland; Thom Haddow

Performance Evaluation of Chapel’s Task Parallel Features

Michele Weiland
, Thom Haddow

School of Physics and Astronomy

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

Abstract

Chapel, Cray’s new parallel programming language, is specifically designed to provide built-in support for high-level task and data parallelism. This paper investigates the performance of the task parallel features offered by Chapel, using benchmarks such as N-Queens and Strassen’s algorithm, on a range of different architectures, including a multi-core Linux system, an SMP cluster and MPP.

Original language	English
Publication status	Published - May 2009
Event	Cray User Group (CUG) 2009 - Atlanta, United States Duration: 4 May 2009 → 7 May 2009

Conference

Conference	Cray User Group (CUG) 2009
Country/Territory	United States
City	Atlanta
Period	4/05/09 → 7/05/09

Cite this

@conference{fffd01487ff24080b484cf96c84b3703,

title = "Performance Evaluation of Chapel{\textquoteright}s Task Parallel Features",

abstract = "Chapel, Cray{\textquoteright}s new parallel programming language, is specifically designed to provide built-in support for high-level task and data parallelism. This paper investigates the performance of the task parallel features offered by Chapel, using benchmarks such as N-Queens and Strassen{\textquoteright}s algorithm, on a range of different architectures, including a multi-core Linux system, an SMP cluster and MPP.",

author = "Michele Weiland and Thom Haddow",

year = "2009",

month = may,

language = "English",

note = "Cray User Group (CUG) 2009 ; Conference date: 04-05-2009 Through 07-05-2009",

}

TY - CONF

T1 - Performance Evaluation of Chapel’s Task Parallel Features

AU - Weiland, Michele

AU - Haddow, Thom

PY - 2009/5

Y1 - 2009/5

N2 - Chapel, Cray’s new parallel programming language, is specifically designed to provide built-in support for high-level task and data parallelism. This paper investigates the performance of the task parallel features offered by Chapel, using benchmarks such as N-Queens and Strassen’s algorithm, on a range of different architectures, including a multi-core Linux system, an SMP cluster and MPP.

AB - Chapel, Cray’s new parallel programming language, is specifically designed to provide built-in support for high-level task and data parallelism. This paper investigates the performance of the task parallel features offered by Chapel, using benchmarks such as N-Queens and Strassen’s algorithm, on a range of different architectures, including a multi-core Linux system, an SMP cluster and MPP.

M3 - Other

T2 - Cray User Group (CUG) 2009

Y2 - 4 May 2009 through 7 May 2009

ER -

Performance Evaluation of Chapel’s Task Parallel Features

Abstract

Conference

Fingerprint

Cite this