Title :
Architecture-independent scientific programming in data parallel C: three case studies
Author :
Hatcher, Philip J. ; Quinn, Michael J. ; Anderson, Ray J. ; Lapadula, Anthony J. ; Seevers, Bradley K. ; Bennett, Andrew F.
Author_Institution :
Dept. of Comput. Sci., Univ. of New Hampshire, Durham, NH, USA
Abstract :
Dataparallel C is a SIMD programming language suitable for solving many problems arising in science and engineering. We have developed compilers that translate Dataparallel C programs into C code that can be compiled and executed on multicomputers and multiprocessors. We describe the Dataparallel C programming language, the implementation of three scientific programs in Dataparallel C, and the performance of the compiled programs on three MIMD computers: the Intel iPSC/2, the nCUBE 3200, and the Sequent Symmetry S81. These case studies-an ocean circulation model, the "shallow-water" atmospheric model, and the Sharks World model-illustrate that nontrivial SIMD programs can achieve good speedup on MIMD computers and still be portable.
Keywords :
C language; parallel programming; program compilers; programming languages; Intel iPSC/2; MIMD computers; SIMD programming language; Sequent Symmetry S81; architecture-independent scientific programming; compiled programs; compilers; data parallel C; dataparallel C programming language; dataparallel C programs; nCUBE 3200; nontrivial SIMD programs; ocean circulation model; shallow-water atmospheric model; sharks world model; Computer languages; Computer science; Concurrent computing; Data engineering; Electronic switching systems; Microwave integrated circuits; Oceans; Parallel processing; Parallel programming; Programming profession;
Conference_Titel :
Supercomputing, 1991. Supercomputing '91. Proceedings of the 1991 ACM/IEEE Conference on
Conference_Location :
Albuquerque, NM
Print_ISBN :
0-89791-459-7
DOI :
10.1145/125826.125945