EPSRC logo

Details of Grant 

EPSRC Reference: GR/K85704/01
Title: FEEDBACK-GUIDED AFFINITY LOOP SCHEDULING FOR MULTIPROCESSORS
Principal Investigator: Gurd, Professor JR
Other Investigators:
Freeman, Dr TL
Researcher Co-Investigators:
Project Partners:
Department: Computer Science
Organisation: Victoria University of Manchester, The
Scheme: Standard Research (Pre-FEC)
Starts: 01 October 1996 Ends: 31 May 1999 Value (£): 105,490
EPSRC Research Topic Classifications:
Parallel Computing
EPSRC Industrial Sector Classifications:
Related Grants:
Panel History:  
Summary on Grant Application Form
Many scientific applications, perhaps involving the numerical solution in time of a parabolic PDE or the iterative solution of a non-linear elliptic PDE, consist of (an) inherently sequential outer loop(s) and one, or more, parallelisable inner loops over a regular grid. To efficiently exploit a parallel machine for such problems it is necessary to maintain a balanced load over the parrallelisable inner loops, without sacrificing the data locality of the computations of these inner loops. To our knowledge there are no load balancing algorithms that address successfully this tension between maintaining a balanced load and maintaining data locality. We propose to design and analyse algorithms to solve this particular load balance problem. Initially we will consider the case of a single parallel loop, after which we will address more complicated scenarios, including nested parallel loops and multiple parallel loops separated by synchronisation points.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Summary
Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:  
Further Information:  
Organisation Website: