Declarative Programming Languages (DPLs) apply a process model of Horn claun es such as PARLOG[8] or a reduction model of A-calculus such as SML[7] and are) in principle, well suited to multiprocessor implemelltation....Declarative Programming Languages (DPLs) apply a process model of Horn claun es such as PARLOG[8] or a reduction model of A-calculus such as SML[7] and are) in principle, well suited to multiprocessor implemelltation. However, the performance of a parallel declarative program can be impaired by a mismatch between the parallelism available in an application and the parallelism available in the architecture. A particularly attractive solution is to automatically match the parallelism of the program to the parallelism of the target hardware as a compilation step. In this paper) we present an optimizillg compilation technique called granularity analysis which identi fies and removes excess parallelism that would degrade performance. The main steps are: an analysis of the flow of data to form an attributed call graph between function (or predicate) arguments; and an asymptotic estimation of granularity of a function (or predicate) to generate approximate grain size. Compiled procedure calls can be annotated with grain size and a task scheduler can make scheduling decisions with the classilication scheme of grains to control parallelism at runtime. The resulting granularity analysis scheme is suitable for exploiting adaptive parallelism of declarative programming languages on multiprocessors.展开更多
文摘Declarative Programming Languages (DPLs) apply a process model of Horn claun es such as PARLOG[8] or a reduction model of A-calculus such as SML[7] and are) in principle, well suited to multiprocessor implemelltation. However, the performance of a parallel declarative program can be impaired by a mismatch between the parallelism available in an application and the parallelism available in the architecture. A particularly attractive solution is to automatically match the parallelism of the program to the parallelism of the target hardware as a compilation step. In this paper) we present an optimizillg compilation technique called granularity analysis which identi fies and removes excess parallelism that would degrade performance. The main steps are: an analysis of the flow of data to form an attributed call graph between function (or predicate) arguments; and an asymptotic estimation of granularity of a function (or predicate) to generate approximate grain size. Compiled procedure calls can be annotated with grain size and a task scheduler can make scheduling decisions with the classilication scheme of grains to control parallelism at runtime. The resulting granularity analysis scheme is suitable for exploiting adaptive parallelism of declarative programming languages on multiprocessors.
