skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Science Driven Supercomputing Architectures: AnalyzingArchitectural Bottlenecks with Applications and Benchmark Probes

Abstract

There is a growing gap between the peak speed of parallelcomputing systems and the actual delivered performance for scientificapplications. In general this gap is caused by inadequate architecturalsupport for the requirements of modern scientific applications, ascommercial applications and the much larger market they represent, havedriven the evolution of computer architectures. This gap has raised theimportance of developing better benchmarking methodologies tocharacterize and to understand the performance requirements of scientificapplications, to communicate them efficiently to influence the design offuture computer architectures. This improved understanding of theperformance behavior of scientific applications will allow improvedperformance predictions, development of adequate benchmarks foridentification of hardware and application features that work well orpoorly together, and a more systematic performance evaluation inprocurement situations. The Berkeley Institute for Performance Studieshas developed a three-level approach to evaluating the design of high endmachines and the software that runs on them: 1) A suite of representativeapplications; 2) A set of application kernels; and 3) Benchmarks tomeasure key system parameters. The three levels yield different type ofinformation, all of which are useful in evaluating systems, and enableNSF and DOE centers to select computer architectures more suited forscientific applications. The analysis will further allow the centers toengage vendors in discussion of strategies tomore » alleviate the presentarchitectural bottlenecks using quantitative information. These mayinclude small hardware changes or larger ones that may be out interest tonon-scientific workloads. Providing quantitative models to the vendorsallows them to assess the benefits of technology alternatives using theirown internal cost-models in the broader marketplace, ideally facilitatingthe development of future computer architectures more suited forscientific computations. The three levels also come with vastly differentinvestments: the benchmarking efforts require significant rewriting toeffectively use a given architecture, which is much more difficult onfull applications than on smaller benchmarks.« less

Authors:
; ; ; ; ; ;
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Director. Office of Science. Office of AdvancedScientific Computing Research
OSTI Identifier:
890678
Report Number(s):
LBNL-58914
R&D Project: KX1310; BnR: KJ0102000
DOE Contract Number:  
DE-AC02-05CH11231
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS; HPC Petaflop computing

Citation Formats

Kamil, S, Yelick, K, Kramer, W T, Oliker, L, Shalf, J, Shan, H, and Strohmaier, E. Science Driven Supercomputing Architectures: AnalyzingArchitectural Bottlenecks with Applications and Benchmark Probes. United States: N. p., 2005. Web. doi:10.2172/890678.
Kamil, S, Yelick, K, Kramer, W T, Oliker, L, Shalf, J, Shan, H, & Strohmaier, E. Science Driven Supercomputing Architectures: AnalyzingArchitectural Bottlenecks with Applications and Benchmark Probes. United States. https://doi.org/10.2172/890678
Kamil, S, Yelick, K, Kramer, W T, Oliker, L, Shalf, J, Shan, H, and Strohmaier, E. 2005. "Science Driven Supercomputing Architectures: AnalyzingArchitectural Bottlenecks with Applications and Benchmark Probes". United States. https://doi.org/10.2172/890678. https://www.osti.gov/servlets/purl/890678.
@article{osti_890678,
title = {Science Driven Supercomputing Architectures: AnalyzingArchitectural Bottlenecks with Applications and Benchmark Probes},
author = {Kamil, S and Yelick, K and Kramer, W T and Oliker, L and Shalf, J and Shan, H and Strohmaier, E},
abstractNote = {There is a growing gap between the peak speed of parallelcomputing systems and the actual delivered performance for scientificapplications. In general this gap is caused by inadequate architecturalsupport for the requirements of modern scientific applications, ascommercial applications and the much larger market they represent, havedriven the evolution of computer architectures. This gap has raised theimportance of developing better benchmarking methodologies tocharacterize and to understand the performance requirements of scientificapplications, to communicate them efficiently to influence the design offuture computer architectures. This improved understanding of theperformance behavior of scientific applications will allow improvedperformance predictions, development of adequate benchmarks foridentification of hardware and application features that work well orpoorly together, and a more systematic performance evaluation inprocurement situations. The Berkeley Institute for Performance Studieshas developed a three-level approach to evaluating the design of high endmachines and the software that runs on them: 1) A suite of representativeapplications; 2) A set of application kernels; and 3) Benchmarks tomeasure key system parameters. The three levels yield different type ofinformation, all of which are useful in evaluating systems, and enableNSF and DOE centers to select computer architectures more suited forscientific applications. The analysis will further allow the centers toengage vendors in discussion of strategies to alleviate the presentarchitectural bottlenecks using quantitative information. These mayinclude small hardware changes or larger ones that may be out interest tonon-scientific workloads. Providing quantitative models to the vendorsallows them to assess the benefits of technology alternatives using theirown internal cost-models in the broader marketplace, ideally facilitatingthe development of future computer architectures more suited forscientific computations. The three levels also come with vastly differentinvestments: the benchmarking efforts require significant rewriting toeffectively use a given architecture, which is much more difficult onfull applications than on smaller benchmarks.},
doi = {10.2172/890678},
url = {https://www.osti.gov/biblio/890678}, journal = {},
number = ,
volume = ,
place = {United States},
year = {Mon Sep 26 00:00:00 EDT 2005},
month = {Mon Sep 26 00:00:00 EDT 2005}
}