ARC: a metacomputing environment for clusters augmented with reconfigurable hardware

Healy, Philip; Morrison, John
September 2012
Journal of Supercomputing;Sep2012, Vol. 61 Issue 3, p743
Academic Journal
The addition of reconfigurable hardware (FPGAs) to the nodes of Beowulf-style clusters has the potential to accelerate a variety of parallel applications through a combination of parallel programming and reconfigurable computing techniques. However, making efficient use of the computational resources available places a significant burden on the application developer due to the lack of support for reconfigurable computing and task heterogeneity in standard message-passing libraries. This paper describes Accessible Reconfigurable Computing (ARC), a metacomputing environment designed to address these issues. The architecture, implementation, and operation of the system are described in detail.


Related Articles

  • Beowulf Supercomputers: Scope and Trends.  // AIP Conference Proceedings;2007, Vol. 888 Issue 1, p412 

    A correction to the article "Beowulf Supercomputers: Scope and Trends," which appeared in the March 17, 2005 issue is presented.

  • High performance data clustering: a comparative analysis of performance for GPU, RASC, MPI, and OpenMP implementations. Yang, Luobin; Chiu, Steve; Liao, Wei-Keng; Thomas, Michael // Journal of Supercomputing;Oct2014, Vol. 70 Issue 1, p284 

    Compared to Beowulf clusters and shared-memory machines, GPU and FPGA are emerging alternative architectures that provide massive parallelism and great computational capabilities. These architectures can be utilized to run compute-intensive algorithms to analyze ever-enlarging datasets and...

  • Reconfigurable Reduced Delay Universal Adder. TYAGI, MOHIT; SINGH, SAMENDER; KHARE, KAVITA // International Journal of Engineering Science & Technology;2011, Vol. 3 Issue 5, p4465 

    This paper introduces a novel architecture for least latency universal adder using pipeline and parallel computing technique. The proposed architecture implemented in reconfigurable technology as a run time reconfigurable unit. The proposed 32-bit Universal adder design and compared with...

  • BACK to the Future. Farber, Rob // Scientific Computing;Nov2008 Supplement, p6 

    No abstract available.

  • CFS LUSTRE TECHNOLOGY INTEGRATED INTO HP SFS.  // Mainframe Computing;Jan2005, Vol. 18 Issue 1, pN.PAG 

    Reports on the integration of the Lustre technology from Medford, Massachusetts-based Cluster File Systems Inc. in the HP StorageWorks Scalable File Share (HP SFS) product, as of January 2005. Reason of cluster users for implementing HP SFS; Features of the HP SFS product; Background on...

  • Build-It-Yourself Systems Deliver High-Performance at Ultralow Cost. Cohen, Jarrett // R&D Magazine;Mar99, Vol. 41 Issue 3, p30 

    Focuses on Beowulf class systems, supercomputers built out of mass-market parts. How Thomas Sterling and Don Becker of the National Aeronautics and Space Administration's Goddard Space Flight Center started the Beowulf concept; Features of the Linux operating system used in Beowulf clusters;...

  • PARALLEL IMPLEMENTATIONS OF 1-D FAST FOURIER TRANSFORM WITHOUT INTERPROCESSOR COMMUNICATION. Namneh, R. A.; Pan, W. D.; Yoo, S.-M. // International Journal of Computers & Applications;2007, Vol. 29 Issue 2, p180 

    Computing 1-D Fast Fourier Transform (FFT) using the conventional 4-step FFT on parallel computers requires intensive all-to-all communication, which can adversely affect the performance of FFT. In this paper, we present 2-step-no-communication and 3-step-no-communication algorithms, which are...

  • Cluster idea gives new life to old PCs. Koucky, Sherri; Mraz, Stephen // Machine Design;09/21/2000, Vol. 72 Issue 18, p46 

    Focuses on the demonstration that will be made by MSC.Software on a Beowulf clustering technique which will harness old personal computers (PCs) at the Second Worldwide Automotive Conference in October 2000. Background information on the clustering technique; Comments from Jay Clark, a computer...

  • PyACTS: A Python Based Interface to ACTS Tools and Parallel Scientific Applications. Drummond, L.; Galiano, Vicente; Migall�n, Violeta; Penad�s, Jose // International Journal of Parallel Programming;Feb2009, Vol. 37 Issue 1, p58 

    Many computational applications rely heavily on numerical linear algebra operations. A good number of these applications are data and computation intensive that need to run in high performance computing environments. The ACTS Collection brings robust and high-end software tools to the hands of...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics