Title :
Is SIMD enough for scientific and engineering applications on massively parallel computers?
Author :
Plimpton, Steve ; Dosanjh, Sudip ; Krall, Randy
Author_Institution :
Sandia Nat. Lab., Albuquerque, NM, USA
Abstract :
Some basic issues involved in matching an application to a distributed memory parallel machine are addressed. In particular, data communication and processor synchronization as they relate to MIMD (multiple instruction-multiple data) and SIMD (single-instruction-multiple data) architectures are discussed. To illustrate the differences, the authors describe the implementation and performance of several engineering and scientific applications that have been coded for both kinds of machines. They find that many problems are well suited to both architectures. However, when the natural parallelism in a simulation requires a loose synchronization between processors, the MIMD paradigm offers a greater programming flexibility than SIMD.<>
Keywords :
distributed memory systems; engineering computing; natural sciences computing; parallel architectures; parallel machines; parallel programming; MIMD; SIMD; data communication; distributed memory parallel machine; loose synchronization; massively parallel computers; multiple instruction-multiple data; natural parallelism; processor synchronization; programming flexibility; scientific applications; single-instruction-multiple data; Application software; Computational modeling; Concurrent computing; Electron beams; Laboratories; Parallel machines; Parallel programming; Physics computing; Sparse matrices; Supercomputers;
Conference_Titel :
Compcon Spring '92. Thirty-Seventh IEEE Computer Society International Conference, Digest of Papers.
Conference_Location :
San Francisco, CA, USA
Print_ISBN :
0-8186-2655-0
DOI :
10.1109/CMPCON.1992.186694
