More Web Proxy on the site http://driver.im/

research-article

Characterizing and predicting the I/O performance of HPC applications using a parameterized synthetic benchmark

Authors:

Hongzhang Shan,

John ShalfAuthors Info & Claims

SC '08: Proceedings of the 2008 ACM/IEEE conference on Supercomputing

Article No.: 42, Pages 1 - 12

Published: 15 November 2008 Publication History

Abstract

The unprecedented parallelism of new supercomputing platforms poses tremendous challenges to achieving scalable performance for I/O intensive applications. Performance assessments using traditional I/O system and component benchmarks are difficult to relate back to application I/O requirements. However, the complexity of full applications motivates development of simpler synthetic I/O benchmarks as proxies to the full application. In this paper we examine the I/O requirements of a range of HPC applications and describe how the LLNL IOR synthetic benchmark was chosen as suitable proxy for the diverse workload. We show a procedure for selecting IOR parameters to match the I/O patterns of the selected applications and show it can accurately predict the I/O performance of the full applications. We conclude that IOR is an effective replacement for full-application I/O benchmarks and can bridge the gap of understanding that typically exists between stand-alone benchmarks and the full applications they intend to model.

References

[1]

K. Antypas, A. C. Calder, A. Dubey, R. Fisher, M. K. Ganapathy, J. B. Gallagher, L. B. Reid, K. Reid, K. Riley, D. Sheeler, and N. Taylor. Scientific applications on the massively parallel BG/L machines. http://ww1.ucmss.com/books/LFS/CSREA2006/PDP4125.pdf.

[2]

J. Borrill, L. Oliker, J. Shalf, and H. Shan. Investigation of leading HPC I/O performance using a scientific-application derived benchmark. In Proc. SC2007: High performance computing, networking, and storage conference, 2007.

Digital Library

[3]

A. Ching, A. Choudhary, W. Liao, R. Ross, and W. Gropp. Efficient structured data access in parallel file systems. In Cluster 2003 Conference, Dec 4, 2003.

[4]

FLASH3 code. http://flash.uchicago.edu/.

[5]

FLASH2 io-benchmark. http://www.astro.sunysb.edu/mzingale/software/.

[6]

High-performance I/O. http://cholera.ece.northwestern.edu/~aching/research_webpage/hpio.html.

[7]

The ASCI I/O stress benchmark. https://computing.llnl.gov/?set=code&page=sio_downloads.

[8]

IOzone file system benchmark. http://www.iozone.org.

[9]

MADBench2. https://crd.lbl.gov/~borrill/MADbench2/.

[10]

R. McDougall and J. Mauro. FileBench. http://www.solarisinternals.com/si/tools/filebench.

[11]

The PIORAW Test. http://www.nersc.gov/nusers/systems/bassi/code_profiles.php.

[12]

R. Rabenseifner and A. E. Koniges. Effective file-I/O bandwidth benchmark. In European Conference on Parallel Processing (Euro-Par), Aug 29-Sep 1, 2000.

Digital Library

[13]

H. Shan and J. Shalf. Using IOR to analyze the I/O performance of HPC platforms. In Cray Users Group Meeting (CUG) 2007, Seattle, Washington, May 7--10, 2007.

[14]

SPIOBENCH: Streaming Parallel I/O Benchmark. http://www.nsf.gov/pubs/2006/nsf0605/spiobench.tar.gz, 2005.

[15]

MPI-Tile-I/O. http://www-unix.mcs.anl.gov/pio-benchmark/.

[16]

VORPAL, versatile plasma simulation code. http://www.txcorp.com/products/VORPAL/.

[17]

P. Wong and R. F. Wijngaart. NAS parallel benchmarks I/O version 2.4. In Technical Report NAS-03-002, Computer Sciences Corporation, NASA Arms Research Center, Moffett Field, CA 94035--1000, Jan, 2003.

Cited By

Bez JKarimi APaul AXie BByna SCarns POral SWang FHanley JWeissman JChandra AGavrilovska ATiwari D(2022)Access Patterns and Performance Behaviors of Multi-layer Supercomputer I/O Subsystems under Production LoadProceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing10.1145/3502181.3531461(43-55)Online publication date: 27-Jun-2022
https://dl.acm.org/doi/10.1145/3502181.3531461
Kim SSim AWu KByna SSon YEom HParashar MVlassov VIrwin DMohror K(2020)Towards HPC I/O Performance Prediction through Large-scale Log AnalysisProceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing10.1145/3369583.3392678(77-88)Online publication date: 23-Jun-2020
https://dl.acm.org/doi/10.1145/3369583.3392678
Kumar SPetruzza SUsher WPascucci V(2019)Spatially-aware Parallel I/O for Particle DataProceedings of the 48th International Conference on Parallel Processing10.1145/3337821.3337875(1-10)Online publication date: 5-Aug-2019
https://dl.acm.org/doi/10.1145/3337821.3337875
Show More Cited By

Index Terms

Characterizing and predicting the I/O performance of HPC applications using a parameterized synthetic benchmark

Recommendations

Modeling and Predicting Disk I/O Time of HPC Applications
HPCMP-UGC '10: Proceedings of the 2010 DoD High Performance Computing Modernization Program Users Group Conference

Understanding input/output (I/O) performance in high performance computing (HPC) is becoming increasingly important as the gap between the performance of computation and I/O widens. In this paper we propose a methodology to predict an application's disk ...
Analyzing commercial processor performance numbers for predicting performance of applications of interest
SIGMETRICS '07: Proceedings of the 2007 ACM SIGMETRICS international conference on Measurement and modeling of computer systems

Current practice in benchmarking commercial computer systems is to run a number of industry-standard benchmarks and to report performance numbers. The huge amount of machines and the large number of benchmarks for which performance numbers are published ...
Analyzing commercial processor performance numbers for predicting performance of applications of interest
SIGMETRICS '07 Conference Proceedings

Current practice in benchmarking commercial computer systems is to run a number of industry-standard benchmarks and to report performance numbers. The huge amount of machines and the large number of benchmarks for which performance numbers are published ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

SC '08: Proceedings of the 2008 ACM/IEEE conference on Supercomputing

November 2008

739 pages

ISBN:9781424428359

Conference Chair:
Patricia Teller

Sponsors

SIGARCH: ACM Special Interest Group on Computer Architecture
IEEE-CS: Computer Society

Publisher

IEEE Press

Publication History

Published: 15 November 2008

Check for updates

Qualifiers

Research-article

Funding Sources

U.S. Department of Energy

Conference

SC '08

Sponsor:

SIGARCH
IEEE-CS

SC '08: International Conference for High Performance Computing, Networking, Storage and Analysis

November 15 - 21, 2008

Texas, Austin

Acceptance Rates

SC '08 Paper Acceptance Rate 59 of 277 submissions, 21%;

Overall Acceptance Rate 1,516 of 6,373 submissions, 24%

Upcoming Conference

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

34
Total Citations
View Citations
847
Total Downloads

Downloads (Last 12 months)7
Downloads (Last 6 weeks)1

Reflects downloads up to 03 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Bez JKarimi APaul AXie BByna SCarns POral SWang FHanley JWeissman JChandra AGavrilovska ATiwari D(2022)Access Patterns and Performance Behaviors of Multi-layer Supercomputer I/O Subsystems under Production LoadProceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing10.1145/3502181.3531461(43-55)Online publication date: 27-Jun-2022
https://dl.acm.org/doi/10.1145/3502181.3531461
Kim SSim AWu KByna SSon YEom HParashar MVlassov VIrwin DMohror K(2020)Towards HPC I/O Performance Prediction through Large-scale Log AnalysisProceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing10.1145/3369583.3392678(77-88)Online publication date: 23-Jun-2020
https://dl.acm.org/doi/10.1145/3369583.3392678
Kumar SPetruzza SUsher WPascucci V(2019)Spatially-aware Parallel I/O for Particle DataProceedings of the 48th International Conference on Parallel Processing10.1145/3337821.3337875(1-10)Online publication date: 5-Aug-2019
https://dl.acm.org/doi/10.1145/3337821.3337875
Sung HBang JSim AWu KEom HKim JSim A(2019)Understanding Parallel I/O Performance Trends Under Various HPC ConfigurationsProceedings of the ACM Workshop on Systems and Network Telemetry and Analytics10.1145/3322798.3329258(29-36)Online publication date: 17-Jun-2019
https://dl.acm.org/doi/10.1145/3322798.3329258
Behzad BByna SPrabhat Snir M(2019)Optimizing I/O Performance of HPC Applications with AutotuningACM Transactions on Parallel Computing10.1145/33092055:4(1-27)Online publication date: 8-Mar-2019
https://dl.acm.org/doi/10.1145/3309205
Dickson JWright SMaheswaran SHerdmant AMiller MJarvis S(2016)Replicating HPC I/O workloads with proxy applicationsProceedings of the 1st Joint International Workshop on Parallel Data Storage & Data Intensive Scalable Computing Systems10.5555/3019046.3019049(13-18)Online publication date: 13-Nov-2016
https://dl.acm.org/doi/10.5555/3019046.3019049
Isaila FCarretero JRoss RVarela CCastro HBarrios C(2016)CLARISSEProceedings of the 16th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing10.1109/CCGrid.2016.24(346-355)Online publication date: 16-May-2016
https://dl.acm.org/doi/10.1109/CCGrid.2016.24
Gunasekaran ROral SHill JMiller RWang FLeverman DButt ALofstead J(2015)Comparative I/O workload characterization of two leadership class storage clustersProceedings of the 10th Parallel Data Storage Workshop10.1145/2834976.2834985(31-36)Online publication date: 15-Nov-2015
https://dl.acm.org/doi/10.1145/2834976.2834985
Luo XMueller FCarns PJenkins JLatham RRoss RSnyder S(2015)HPC I/O trace extrapolationProceedings of the 4th Workshop on Extreme Scale Programming Tools10.1145/2832106.2832108(1-6)Online publication date: 15-Nov-2015
https://dl.acm.org/doi/10.1145/2832106.2832108
Snyder SCarns PLatham RMubarak MRoss RCarothers CBehzad BLuu HByna SPrabhat Jarvis SWright SHammond S(2015)Techniques for modeling large-scale HPC I/O workloadsProceedings of the 6th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing Systems10.1145/2832087.2832091(1-11)Online publication date: 15-Nov-2015
https://dl.acm.org/doi/10.1145/2832087.2832091
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents