SISAL 1. 2: An alternative to FORTRAN for shared memory multiprocessors
The acquisition of parallel processors in the scientific community is increasing, but the difficulties of programming parallel machines persist. Two approaches have emerged: automatic parallelizing compilers for extant languages, and new languages that provide an easier-to-use and cleaner parallel programming model. Unfortunately most new languages have acquired a reputation for inefficiency because of their semantics. This paper compares the performance of SISAL 1.2, an applicative language for parallel numerical computations, and FORTRAN using the Livermore Loops. We show that applicative programs when compiled using a set of powerful yet simple optimization techniques can achieve execution speeds comparable to FORTRAN, and can effectively exploit shared memory multiprocessors. 16 refs., 2 figs., 2 tabs.
- Research Organization:
- Lawrence Livermore National Lab., CA (USA)
- Sponsoring Organization:
- DOE/ER
- DOE Contract Number:
- W-7405-ENG-48
- OSTI ID:
- 7020404
- Report Number(s):
- UCRL-102263-Rev.1; CONF-9006101--1-Rev.1; ON: DE90005181
- Country of Publication:
- United States
- Language:
- English
Similar Records
SISAL 1.2: high-performance applicative computing [Book Chapter]
On the implementation of applicative on shared-memory, MIMD multiprocessors. [SISAL]