Abstract
We have parallelized a FORTRAN two-dimensional hydrodynamic Flux Corrected Transport (FCT) code for astrophysical applications, using CSTools on a Meiko Computing Surface hosted by a SUN 4/370 workstation and fully integrated in a Unix/Ultrix Local Area Network. The processor topology maps the domain decomposition and message exchanges are required between adjacent processors. We have developed and used a library of high-level network and communication routines, based on CSTools primitives, and applicable to other parallel codes. We adopted a master-slave paradigm, and code parallelization took around twelve man hours. On a standard hydrodynamic problem we obtain a parallel efficiency above 90%, on arrays up to four 20 MHz T800 transputers, and performances in the range of several Mflops on Meiko boards with faster Intel 1860 processors.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.