pMatlab Parallel Matlab Library

Abstract

MATLAB has emerged as one of the languages most commonly used by scientists and engineers for technical computing, with ~1,000,000 users worldwide. The compute intensive nature of technical computing means that many MATLAB users have codes that can significantly benefit from the increased performance offered by parallel computing. pMatlab (www.ll.mit.edu/pMatlab) provides this capability by implementing Parallel Global Array Semantics (PGAS) using standard operator overloading techniques. The core data structure in pMatlab is a distributed numerical array whose distribution onto multiple processors is specified with a map construct. Communication operations between distributed arrays are abstracted away from the user and pMatlab transparently supports redistribution between any block-cyclic-overlapped distributions up to four dimensions. pMatlab is built on top of the MatlabMPI communication library (www.ll.mit.edu/MatlabMPI) and runs on any combination of heterogeneous systems that support MATLAB, which includes Windows, Linux, MacOSX, and SunOS. Performance is validated by implementing the HPC Challenge benchmark suite and comparing pMatlab performance with the equivalent C+MPI codes. These results indicate that pMatlab can often achieve comparable performance to C+MPI at usually 1/10th the code size. Finally, we present implementation data collected from a sample of 10 real pMatlab applications drawn from the ~100 users at MIT Lincoln Laboratory. These data indicate that users are typically able to go from a serial code to a well performing pMatlab code in about 3 hours while changing less than 1% of their code.