Premium
Vectorization of a classical trajectory code on a floating point systems, Inc. Model 164 attached processor
Author(s) -
Kraus Wayne A.,
Wagner Albert F.
Publication year - 1986
Publication title -
journal of computational chemistry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.907
H-Index - 188
eISSN - 1096-987X
pISSN - 0192-8651
DOI - 10.1002/jcc.540070215
Subject(s) - vectorization (mathematics) , code (set theory) , computer science , trajectory , parallel computing , floating point , point (geometry) , computational science , algorithm , physics , mathematics , programming language , geometry , set (abstract data type) , astronomy
A triatomic classical trajectory code has been modified by extensive vectorization of the algorithms to achieve much improved performance on an FPS 164 attached processor. Extensive timings on both the FPS 164 and a VAX 11/780 with floating point accelerator are presented as a function of the number of trajectories simultaneously run. The timing tests involve a potential energy surface of the LEPS variety and trajectories with 1000 time steps. The results indicate that vectorization results in timing improvements on both the VAX and the FPS. For larger numbers of trajectories run simultaneously, up to a factor of 25 improvement in speed occurs between VAX and FPS vectorized code.