Data-parallel languages allow programmers to easily express parallel computations by means of high-level constructs. To reduce overheads, the compiler partitions the computations among the processors at compile-time, on the basis of the static data distribution suggested by the programmer. When exec
Towards a complete framework for parallel implementation of logic languages: the data parallel implementation of SEL
โ Scribed by Succi, Giancarlo; Uhrik, Carl
- Publisher
- John Wiley and Sons
- Year
- 1996
- Tongue
- English
- Weight
- 784 KB
- Volume
- 8
- Category
- Article
- ISSN
- 1040-3108
No coin nor oath required. For personal study only.
โฆ Synopsis
Although logic languages, due to their nnn-declarative nature, are widely proclaimed to be conducive in theory to parallel implementation, in fact there appears to be insufficient practical evidence to stimulate further developments in this field. The paper puts forward various complications which arise in assuming a solely process parallel approach as a possible explanation for this situation.
As an alternative, data parallelism is posited as an underutilized forte of logic programming.
The paper illustrates a data parallel implementation of a particular language called SEL which is based on sets. Thus, SET, (set equational language) is introduced as an example of logic language which lends itself to an efficient data parallel implementation. The strategy of this implementation assumes an abstract machine called SAM (set-oriented abstract machine) which is based on the WAM (Warren abstract machine). SAM serves as an intermediary between the SEL language and the target machine for the implementation, the Connection Machine. Finally, some preliminary benchmarks are presented.
๐ SIMILAR VOLUMES
## Abstract Many econometric problems can benefit from the application of parallel computing techniques, and recent advances in hardware and software have made such application feasible. There are a number of freely available software libraries that make it possible to write message passing paralle