Optimizing Bandwidth Limited Problems Using One-SidedCommunication and Overlap

PDF Version Also Available for Download.

Description

Partitioned Global Address Space languages like Unified Parallel C (UPC) are typically valued for their expressiveness, especially for computations with fine-grained random accesses. In this paper we show that the one-sided communication model used in these languages also has a significant performance advantage for bandwidth-limited applications. We demonstrate this benefit through communication microbenchmarks and a case-study that compares UPC and MPI implementations of the NAS Fourier Transform (FT) benchmark. Our optimizations rely on aggressively overlapping communication with computation but spreading communication events throughout the course of the local computation. This alleviates the potential communication bottleneck that occurs when the communication ... continued below

Creation Information

Bell, Christian; Bonachea, Dan; Nishtala, Rajesh & Yelick, Katherine October 14, 2005.

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. 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

Partitioned Global Address Space languages like Unified Parallel C (UPC) are typically valued for their expressiveness, especially for computations with fine-grained random accesses. In this paper we show that the one-sided communication model used in these languages also has a significant performance advantage for bandwidth-limited applications. We demonstrate this benefit through communication microbenchmarks and a case-study that compares UPC and MPI implementations of the NAS Fourier Transform (FT) benchmark. Our optimizations rely on aggressively overlapping communication with computation but spreading communication events throughout the course of the local computation. This alleviates the potential communication bottleneck that occurs when the communication is packed into a single phase (e.g., the large all-to-all in a multidimensional FFT). Even though the new algorithms require more messages for the same total volume of data, the resulting overlap leads to speedups of over 1.75x and 1.9x for the two-sided and one-sided implementations, respectively, when compared to the default NAS Fortran/MPI release. Our best one-sided implementations show an average improvement of 15 percent over our best two-sided implementations. We attribute this difference to the lower software overhead of one-sided communication, which is partly fundamental to the semantic difference between one-sided and two-sided communication. Our UPC results use the Berkeley UPC compiler with the GASNet communication system, and demonstrate the portability and scalability of that language and implementation, with performance approaching 0.5TFlop/s on the FT benchmark running on 512 processors.

Source

  • IPDPS 2006, Rhodes Island, Greece, Tuesday, 25April - Saturday, 29 April 2006

Language

Item Type

Identifier

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

  • Report No.: LBNL--59207
  • Grant Number: DE-AC02-05CH11231
  • Office of Scientific & Technical Information Report Number: 891353
  • Archival Resource Key: ark:/67531/metadc883373

Collections

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

Office of Scientific & Technical Information Technical Reports

What responsibilities do I have when using this article?

When

Dates and time periods associated with this article.

Creation Date

  • October 14, 2005

Added to The UNT Digital Library

  • Sept. 21, 2016, 2:29 a.m.

Description Last Updated

  • Sept. 30, 2016, 12:29 p.m.

Usage Statistics

When was this article last used?

Congratulations! It looks like you are the first person to view this item online.

Interact With This Article

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

Citations, Rights, Re-Use

Bell, Christian; Bonachea, Dan; Nishtala, Rajesh & Yelick, Katherine. Optimizing Bandwidth Limited Problems Using One-SidedCommunication and Overlap, article, October 14, 2005; Berkeley, California. (digital.library.unt.edu/ark:/67531/metadc883373/: accessed August 23, 2017), University of North Texas Libraries, Digital Library, digital.library.unt.edu; crediting UNT Libraries Government Documents Department.