Experiments with Parallelising Numerical Applications
		via DESOLibraries (extended abstract)

		   Olav Beckmann and Paul H J Kelly

	      Department of Computing, Imperial College
		 180 Queen's Gate, London SW7 2BZ, UK
		       {ob3,phjk}@doc.ic.ac.uk

			     In PCW '97:
       Proceedings of the Seventh Parallel Computing Workshop,
      Department of Computer Science, ANU, Canberra, Australia,
		     e-mail pcw97@cap.anu.edu.au,
			September 25-26, 1997.


			       Abstract
			       --------

DESOLibraries are  ``delayed evaluation,  self-optimising''   parallel
libraries of  numerical   routines. The   aim is  to   allow users  to
parallelise computationally expensive parts  of numerical programs  by
simply linking with  a  parallel  rather  than  sequential  library of
subroutines.   The library  performs  interprocedural data   placement
optimisation  at runtime, which requires  the  optimiser itself to  be
very efficient.  This paper outlines the techniques  we use to achieve
this and describes the current  state  of our implementation. We  show
performance results  for an implementation   of the conjugate gradient
iterative solver on the AP1000 that uses our library.