Performance prediction for random write reductions: A case study in modeling shared memory programs

Ruoming Jin; Gagan Agrawal

doi:10.1145/511334.511350

Performance prediction for random write reductions: A case study in modeling shared memory programs

Ruoming Jin, Gagan Agrawal

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

6 Scopus citations

Abstract

A new application for parallel performance prediction was identified. A detailed analytical model for predicting performance and choosing the best parallelization strategy was developed. The resultant model effectively captures the impact of memory hierarchy as well as the factors that limit parallelism.

Original language	English (US)
Pages	117-128
Number of pages	12
DOIs	https://doi.org/10.1145/511334.511350 https://doi.org/10.1145/511399.511350
State	Published - 2002
Externally published	Yes
Event	ACM SIGMETRICS 2002 International Conference on Measurement and Modeling of Computer Systems - Marina Del Rey, CA, United States Duration: Jun 15 2002 → Jun 19 2002

Conference

Conference	ACM SIGMETRICS 2002 International Conference on Measurement and Modeling of Computer Systems
Country/Territory	United States
City	Marina Del Rey, CA
Period	6/15/02 → 6/19/02

ASJC Scopus subject areas

Software
Hardware and Architecture
Computer Networks and Communications

Access to Document

http://portal.acm.org/citation.cfm?doid=511334.511350

Cite this

Jin, R & Agrawal, G 2002, 'Performance prediction for random write reductions: A case study in modeling shared memory programs', Paper presented at ACM SIGMETRICS 2002 International Conference on Measurement and Modeling of Computer Systems, Marina Del Rey, CA, United States, 6/15/02 - 6/19/02 pp. 117-128. https://doi.org/10.1145/511334.511350, https://doi.org/10.1145/511399.511350

@conference{0e571f3e8f0e438a881b48dea4e60a8b,

title = "Performance prediction for random write reductions: A case study in modeling shared memory programs",

abstract = "A new application for parallel performance prediction was identified. A detailed analytical model for predicting performance and choosing the best parallelization strategy was developed. The resultant model effectively captures the impact of memory hierarchy as well as the factors that limit parallelism.",

author = "Ruoming Jin and Gagan Agrawal",

year = "2002",

doi = "10.1145/511334.511350",

language = "English (US)",

pages = "117--128",

note = "ACM SIGMETRICS 2002 International Conference on Measurement and Modeling of Computer Systems ; Conference date: 15-06-2002 Through 19-06-2002",

}

TY - CONF

T1 - Performance prediction for random write reductions

T2 - ACM SIGMETRICS 2002 International Conference on Measurement and Modeling of Computer Systems

AU - Jin, Ruoming

AU - Agrawal, Gagan

PY - 2002

Y1 - 2002

N2 - A new application for parallel performance prediction was identified. A detailed analytical model for predicting performance and choosing the best parallelization strategy was developed. The resultant model effectively captures the impact of memory hierarchy as well as the factors that limit parallelism.

AB - A new application for parallel performance prediction was identified. A detailed analytical model for predicting performance and choosing the best parallelization strategy was developed. The resultant model effectively captures the impact of memory hierarchy as well as the factors that limit parallelism.

UR - http://www.scopus.com/inward/record.url?scp=0036036749&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036036749&partnerID=8YFLogxK

U2 - 10.1145/511334.511350

DO - 10.1145/511334.511350

M3 - Paper

SP - 117

EP - 128

Y2 - 15 June 2002 through 19 June 2002

ER -

Performance prediction for random write reductions: A case study in modeling shared memory programs

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this