MD_PARFOR
A Parallel MATLAB Function Using PARFOR

MD_PARFOR is a directory which illustrates how a MATLAB function using the PARFOR statement can be run in parallel.

The MATLAB program is a version of the MD molecular dynamics program. A single for statement in the compute function was replaced by a parfor. Also, the program was simplified so that it takes no input arguments (the former input quantities are hard-coded internally) and returns three numbers as function results, namely the values, at the final time step, of the potential energy, kinetic energy, and the relative energy error.

Thus, the basic function now has the form:

function [ pe, ke, e_lost ] = md_fun ( )

• pe, the potential energy at the final time step.
• ke, the kinetic energy at the final time step.
• e_lost, the relative error in the total energy.

Depending on the situation, the function could be executed in parallel:

• interactively, and locally, using the matlabpool command;
• indirectly, and locally, using the batch command;
• indirectly, and on the Ithaca cluster, using the batch command;
• indirectly, and on the FSU HPC cluster, using the fsuClusterMatlab command;

Related Data and Programs:

COLLATZ_PARFOR, a MATLAB program which seeks the maximum Collatz sequence between 1 and N, running in parallel using MATLAB's parfor feature.

HEATED_PLATE_PARFOR, a MATLAB program which solves the steady (time independent) heat equation in a 2D rectangular region, using MATLAB's parfor facility to run in parallel.

HELLO_PARFOR, a MATLAB program which prints out "Hello, world!" multiple times, using MATLAB's parfor command for parallel execution.

HIGH_CARD_PARFOR, a MATLAB program which uses the parfor statement to compute in parallel the statistics for a card game in which you are required to guess the location of the highest card.

MATLAB_PARALLEL, MATLAB programs which illustrate "local" parallel programming on a single computer with MATLAB's Parallel Computing Toolbox.

MATRIX_ASSEMBLE_PARFOR, a MATLAB program which demonstrates the parfor parallel programming feature by assembling the Hilbert matrix in a parallel loop.

MD, a MATLAB program which carries out a molecular dynamics simulation, and is intended as a starting point for implementing a parallel version.

ODE_SWEEP_PARFOR, a MATLAB program which demonstrates how the PARFOR command can be used to parallelize the computation of a grid of solutions to a parameterized system of ODE's.

PRIME_PARFOR, a MATLAB program which counts the number of primes between 1 and N; running in parallel using MATLAB's "PARFOR" feature.

QUAD_PARFOR, a MATLAB program which estimates an integral using quadrature; running in parallel using MATLAB's "PARFOR" feature.

SATISFY_PARFOR, a MATLAB program which demonstrates, for a particular circuit, an exhaustive search for solutions of the circuit satisfiability problem, running in parallel using MATLAB's "PARFOR" feature.

SPARSE_PARFOR, a MATLAB library which demonstrates how a sparse matrix can be constructed by evaluating individual blocks in parallel with the parfor command, and then assembled (on a single processor) using the sparse() command.

Reference:

The User's Guide for the Parallel Computing Toolbox is available at http://www.mathworks.com/access/helpdesk/help/pdf_doc/distcomp/distcomp.pdf

• Gaurav Sharma, Jos Martin,
  MATLAB: A Language for Parallel Computing,
  International Journal of Parallel Programming,
  Volume 37, Number 1, pages 3-36, February 2009.

Source Code:

• md_fun.m the function which performs the computations.

Examples and Tests:

MD_POOL runs the function locally and interactively.

• md_pool.m a script which uses the MATLABPOOL command to run the function locally and interactively.
• md_pool_output.txt the output file.

MD_BATCH runs the function locally and noninteractively.

• md_script.m a script which calls the function, necessary for the BATCH command.
• md_batch_local.m a script which uses the BATCH command to run the function indirectly and locally.
• md_batch_local_output.txt the output file.

MD_FSU runs the function remotely on the FSU HPC cluster.

• md_fsu.m a script which uses the fsuClusterMatlab command to run the function indirectly on the FSU HPC cluster.

MD_ITHACA runs the function remotely on the Virginia Tech Ithaca cluster.

• md_ithaca.m a script which runs the function on the Virginia Tech Ithaca cluster.

You can go up one level to the MATLAB source codes.