J Supercomput (2014) 69:248–272
DOI 10.1007/s11227-014-1150-9
Evaluating the SAT problem on P systems for different
high-performance architectures
José M. Cecilia · José M. García ·
Ginés D. Guerrero · Manuel Ujaldón
Published online: 19 March 2014
© Springer Science+Business Media New York 2014
Abstract Membrane computing is an emergent research area studying the behav-
ior of living cells to define bio-inspired computing devices, also called P systems.
Such devices provide polynomial time solutions to NP-complete problems by trading
time for space. The efficient simulation of P systems poses three major challenging
issues: an intrinsic massive parallelism of P systems, an exponential computational
workspace, and a non-intensive floating point nature. This paper analyzes the sim-
ulation of a family of recognizer P systems with active membranes that solves the
satisfiability problem in linear time on three different architectures: a shared memory
multiprocessor, a distributed memory system, and a manycore graphics processing unit
(GPU). For an efficient handling of the exponential workspace created by the P sys-
tems computation, we enable different data policies on those architectures to increase
memory bandwidth and exploit data locality through tiling. Parallelism inherent to the
target P system is also managed on each architecture to demonstrate that GPUs offer
a valid alternative for high-performance computing at a considerably lower cost. Our
results lead to execution time improvements exceeding 310× and 78×, respectively,
for a much cheaper high-performance alternative.
J. M. Cecilia
Computer Science Department, Universidad Católica San Antonio (UCAM), 30107 Murcia, Spain
e-mail: jmcecilia@ucam.edu
J. M. García
Computer Engineering Department, University of Murcia, 30100 Murcia, Spain
e-mail: jmgarcia@ditec.um.es
G. D. Guerrero
National Lab for High Performance Computing (NLHPC), Center for Mathematical Modeling (CMM),
School of Engineering and Sciences, University of Chile, Santiago, Chile
e-mail: gguerrero@nlhpc.cl
M. Ujaldón (B )
Computer Architecture Department, University of Malaga, 29071 Malaga, Spain
e-mail: ujaldon@uma.es
123