Title :
Compiling Parallel MATLAB for General Distributions using Telescoping Languages
Author :
Fletcher, M. ; McCosh, C. ; Guohua Jin ; Kennedy, Krista
Author_Institution :
Dept. of Comput. Sci., Rice Univ., Houston, TX, USA
Abstract :
Matlab is one of the most popular computer languages for technical and scientific programming. However, until recently, it has been limited to running on uniprocessors. One strategy for overcoming this limitation is to introduce global distributed arrays, with those arrays distributed across the processors of a parallel machine. In this paper, we describe the compilation technology we have designed for Matlab D, a distributed-array extension of Matlab. Our approach is distinguished by a two-phase compilation technology with support for a rich collection of data distributions. By precompiling array operations and communication steps into Fortran plus MPI, the time to compile an application using those operations is significantly reduced. This paper includes preliminary results that demonstrate that this approach can dramatically improve performance, scaling well to at least 32 processors.
Keywords :
FORTRAN; mathematics computing; parallel machines; Fortran plus MPI; Matlab D; computer languages; data distributions; general distributions; global distributed arrays; parallel Matlab; parallel machine; scientific programming; technical programming; telescoping languages; two-phase compilation technology; Bifurcation; Computer languages; Computer science; High level languages; Libraries; MATLAB; Parallel machines; Parallel processing; Parallel programming; Programming profession; Parallelizing compilers;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
1-4244-0727-3
DOI :
10.1109/ICASSP.2007.367289