Task Parallelism in Spar

In this paper we will give a small introduction to Spar, a programming language for semi-automatic parallel programming. Spar, a Java derivative is being developed as part of the Automap project, which aims to create completely automatic mappings for code and data at either compile time or runtime. We will present how Spar supports task-parallel programming and how it interacts with the user or the scheduler to define code mappings. 2 Introduction Issues that are of major importance in the design of parallel programming languages for distributedmemory systems include: ffl parallelizability, the extent to which parallelism can either be expressed by the user or deduced by the compiler such that problem parallelism is adequately captured. ffl programmability, the extent to which the user is relieved from programming the complex synchronizations required between concurrently executing tasks in order to retain correctness. ffl portability, the extent to which the program is machine-inde..