Allan Snavely
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Allan Snavely has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Adolfy Hoisie
Los Alamos National Laboratory, Los Alamos, NM, USA
1 shared publication - Anshu Dubey
Argonne National Laboratory
1 shared publication Beth Simon
San Diego Supercomputer Center
1 shared publication- Boyana Norris
University of Oregon, Eugene, OR, USA
1 shared publication - Bronis R. de Supinski
Lawrence Livermore National Laboratory, Livermore, USA
1 shared publication - C. Mendes
University of Illinois at Urbana-Champaign, IL, USA
1 shared publication
Latest Publications
- 26 June 2009
- Published by Office of Scientific and Technical Information (OSTI)
Modeling the Office of Science Ten Year Facilities Plan: The PERI Architecture Tiger Team
The Performance Engineering Institute (PERI) originally proposed a tiger team activity as a mechanism to target significant effort optimizing key Office of Science applications, a model that was successfully realized with the assistance of two JOULE metric teams. However, the Office of Science requested a new focus beginning in 2008: assistance in forming its ten year facilities plan. To meet this request, PERI formed the Architecture Tiger Team, which is modeling the performance of key science applications on future architectures, with S3D, FLASH and GTC chosen as the first application targets. In this activity, we have measured the performance of these applications on current systems in order to understand their baseline performance and to ensure that our modeling activity focuses on the right versions and inputs of the applications. We have applied a variety of modeling techniques to anticipate the performance of these applications on a range of anticipated systems. While our initial findings predict that Office of Science applications will continue to perform well on future machines from major hardware vendors, we have also encountered several areas in which we must extend our modeling techniques in order to fulfill our mission accurately and completely. In addition, we anticipate thatmore » models of a wider range of applications will reveal critical differences between expected future systems, thus providing guidance for future Office of Science procurement decisions, and will enable DOE applications to exploit machines in future facilities fully.« less
- 26 June 2009
- Published by Office of Scientific and Technical Information (OSTI)
Modeling the Office of Science Ten Year Facilities Plan: The PERI Architecture Tiger Team
The Performance Engineering Institute (PERI) originally proposed a tiger team activity as a mechanism to target significant effort optimizing key Office of Science applications, a model that was successfully realized with the assistance of two JOULE metric teams. However, the Office of Science requested a new focus beginning in 2008: assistance in forming its ten year facilities plan. To meet this request, PERI formed the Architecture Tiger Team, which is modeling the performance of key science applications on future architectures, with S3D, FLASH and GTC chosen as the first application targets. In this activity, we have measured the performance of these applications on current systems in order to understand their baseline performance and to ensure that our modeling activity focuses on the right versions and inputs of the applications. We have applied a variety of modeling techniques to anticipate the performance of these applications on a range of anticipated systems. While our initial findings predict that Office of Science applications will continue to perform well on future machines from major hardware vendors, we have also encountered several areas in which we must extend our modeling techniques in order to fulfill our mission accurately and completely. In addition, we anticipate thatmore » models of a wider range of applications will reveal critical differences between expected future systems, thus providing guidance for future Office of Science procurement decisions, and will enable DOE applications to exploit machines in future facilities fully.« less
- 28 February 2006
- Published by Elsevier in Future Generation Computer Systems
- Vol. 22 (3) , 291-292
Special section: Large-scale system performance modeling and analysis
- 28 February 2006
- Published by Elsevier in Future Generation Computer Systems
- Vol. 22 (3) , 291-292
Special section: Large-scale system performance modeling and analysis
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 293-300
Measuring the Performance and Reliability of Production Computational Grids
In this work we report on data gathered via a deployment of a monitoring and benchmarking infrastructure on two production grid platforms, TeraGrid and Geon. Our result show that these production grids are rather unavailable, with success rates for benchmark and application runs between 55% and 80%. We also found that performance fluctuation was in the 50% range, expectedly mostly due to batch schedulers. We also investigate whether the execution time of a typical grid application can be predicated based on previous runs of simple benchmarks. Perhaps surprisingly, we find that application execution time can be predicted with a relative error as low as 9%
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 293-300
Measuring the Performance and Reliability of Production Computational Grids
In this work we report on data gathered via a deployment of a monitoring and benchmarking infrastructure on two production grid platforms, TeraGrid and Geon. Our result show that these production grids are rather unavailable, with success rates for benchmark and application runs between 55% and 80%. We also found that performance fluctuation was in the 50% range, expectedly mostly due to batch schedulers. We also investigate whether the execution time of a typical grid application can be predicated based on previous runs of simple benchmarks. Perhaps surprisingly, we find that application execution time can be predicted with a relative error as low as 9%
- Open Access
- 1 December 2005
- Published by Association for Computing Machinery (ACM) in ACM SIGARCH Computer Architecture News
- Vol. 33 (5) , 33-38
ALITER
Binary instrumentation tools are very useful for collecting traces of program events. Common uses for such traces include trace-driven simulation and performance modeling. However commonly available general-purpose instrumentation tools are inefficient for capturing fine-grained events as for example a sequence of dynamic memory addresses. We introduce ALITER, an asynchronous lightweight instrumentation tool for event recording which is extremely light in terms of tracing overhead as compared to commonly available binary instrumentation tools. The tool creates a buffer in the instrumented code space and inlines buffer maintenance instructions into the instrumented code. User supplied analysis routines are only invoked when the buffer is fairly full. This approach, i. e. having a user code space buffer managed under ALITER's control, ensures that most control transfers between user code and instrumentation code are eliminated. In addition, storing events to the buffer and checking buffer status are implemented very cheaply. Thus traditional sources of tracing overheads are greatly reduced. Overall we report less than a 2-fold slowdown to collect memory traces of the selected benchmarks; this contrasts with tens and even hundreds of fold slowdown using generally available instrumentation tools.
- 1 December 2005
- Published by Association for Computing Machinery (ACM) in ACM SIGARCH Computer Architecture News
- Vol. 33 (5) , 33-38
Open AccessALITER
Binary instrumentation tools are very useful for collecting traces of program events. Common uses for such traces include trace-driven simulation and performance modeling. However commonly available general-purpose instrumentation tools are inefficient for capturing fine-grained events as for example a sequence of dynamic memory addresses. We introduce ALITER, an asynchronous lightweight instrumentation tool for event recording which is extremely light in terms of tracing overhead as compared to commonly available binary instrumentation tools. The tool creates a buffer in the instrumented code space and inlines buffer maintenance instructions into the instrumented code. User supplied analysis routines are only invoked when the buffer is fairly full. This approach, i. e. having a user code space buffer managed under ALITER's control, ensures that most control transfers between user code and instrumentation code are eliminated. In addition, storing events to the buffer and checking buffer status are implemented very cheaply. Thus traditional sources of tracing overheads are greatly reduced. Overall we report less than a 2-fold slowdown to collect memory traces of the selected benchmarks; this contrasts with tens and even hundreds of fold slowdown using generally available instrumentation tools.