Optimization and Performance Modeling of Stencil Computations on Modern Microprocessors

PDF Version Also Available for Download.

Description

Stencil-based kernels constitute the core of many important scientific applications on blockstructured grids. Unfortunately, these codes achieve a low fraction of peak performance, due primarily to the disparity between processor and main memory speeds. In this paper, we explore the impact of trends in memory subsystems on a variety of stencil optimization techniques and develop performance models to analytically guide our optimizations. Our work targets cache reuse methodologies across single and multiple stencil sweeps, examining cache-aware algorithms as well as cache-oblivious techniques on the Intel Itanium2, AMD Opteron, and IBM Power5. Additionally, we consider stencil computations on the heterogeneous multicore ... continued below

Creation Information

Datta, Kaushik; Kamil, Shoaib; Williams, Samuel; Oliker, Leonid; Shalf, John & Yelick, Katherine June 1, 2007.

Context

This article is part of the collection entitled: Office of Scientific & Technical Information Technical Reports and was provided by UNT Libraries Government Documents Department to Digital Library, a digital repository hosted by the UNT Libraries. It has been viewed 12 times . More information about this article can be viewed below.

Who

People and organizations associated with either the creation of this article or its content.

Publisher

Provided By

UNT Libraries Government Documents Department

Serving as both a federal and a state depository library, the UNT Libraries Government Documents Department maintains millions of items in a variety of formats. The department is a member of the FDLP Content Partnerships Program and an Affiliated Archive of the National Archives.

Contact Us

What

Descriptive information to help identify this article. Follow the links below to find similar items on the Digital Library.

Description

Stencil-based kernels constitute the core of many important scientific applications on blockstructured grids. Unfortunately, these codes achieve a low fraction of peak performance, due primarily to the disparity between processor and main memory speeds. In this paper, we explore the impact of trends in memory subsystems on a variety of stencil optimization techniques and develop performance models to analytically guide our optimizations. Our work targets cache reuse methodologies across single and multiple stencil sweeps, examining cache-aware algorithms as well as cache-oblivious techniques on the Intel Itanium2, AMD Opteron, and IBM Power5. Additionally, we consider stencil computations on the heterogeneous multicore design of the Cell processor, a machine with an explicitly managed memory hierarchy. Overall our work represents one of the most extensive analyses of stencil optimizations and performance modeling to date. Results demonstrate that recent trends in memory system organization have reduced the efficacy of traditional cache-blocking optimizations. We also show that a cache-aware implementation is significantly faster than a cache-oblivious approach, while the explicitly managed memory on Cell enables the highest overall efficiency: Cell attains 88% of algorithmic peak while the best competing cache-based processor achieves only 54% of algorithmic peak performance.

Source

  • Journal Name: SIAM Review (SIREV) Journal; Journal Volume: 51; Journal Issue: 10; Conference: To come; Related Information: Journal Publication Date: 2009

Language

Item Type

Identifier

Unique identifying numbers for this article in the Digital Library or other systems.

  • Report No.: LBNL-63192
  • Grant Number: DE-AC02-05CH11231
  • Office of Scientific & Technical Information Report Number: 961524
  • Archival Resource Key: ark:/67531/metadc933702

Collections

This article is part of the following collection of related materials.

Office of Scientific & Technical Information Technical Reports

Reports, articles and other documents harvested from the Office of Scientific and Technical Information.

Office of Scientific and Technical Information (OSTI) is the Department of Energy (DOE) office that collects, preserves, and disseminates DOE-sponsored research and development (R&D) results that are the outcomes of R&D projects or other funded activities at DOE labs and facilities nationwide and grantees at universities and other institutions.

What responsibilities do I have when using this article?

When

Dates and time periods associated with this article.

Creation Date

  • June 1, 2007

Added to The UNT Digital Library

  • Nov. 13, 2016, 7:26 p.m.

Description Last Updated

  • Nov. 18, 2016, 3:04 p.m.

Usage Statistics

When was this article last used?

Yesterday: 0
Past 30 days: 1
Total Uses: 12

Interact With This Article

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

International Image Interoperability Framework

IIF Logo

We support the IIIF Presentation API

Datta, Kaushik; Kamil, Shoaib; Williams, Samuel; Oliker, Leonid; Shalf, John & Yelick, Katherine. Optimization and Performance Modeling of Stencil Computations on Modern Microprocessors, article, June 1, 2007; Berkeley, California. (digital.library.unt.edu/ark:/67531/metadc933702/: accessed September 25, 2018), University of North Texas Libraries, Digital Library, digital.library.unt.edu; crediting UNT Libraries Government Documents Department.