Scheduling in the context of parallel systems is often thought of in terms of assigning tasks in a program to processors, so as to minimize the makespan. This formulation assumes that the processors are dedicated to the program in question. But when the parallel system is shared by a number of users, this is not necessarily the case. In the context of multiprogrammed parallel machines, scheduling refers to the execution of threads from competing programs. This is an operating system issue, involved with resource allocation, not a program development issue. Scheduling schemes for multiprogrammed parallel systems can be classified as one or two leveled. Single-level scheduling combines the allocation of processing power with the decision of which thread will use it. Two level scheduling decouples the two issues: first, processors are allocated to the job, and then the job's threads are scheduled using this pool of processors. The processors of a parallel system can be shared i...

Published in collaboration with the

. This paper considers the issue of dynamic task control in the context of a parallel Haskell implementation on the GRIP multiprocessor. For the first time, we report the effect of our task control strategies on task granularity, as measured in terms of dynamic heap allocations. This gives a concrete means of measuring the effectiveness of these strategies other than wall-clock timings, which are notoriously uninformative. 1 Introduction Compared with most conventional approaches to parallel programming, it is comparatively easy to write parallel functional programs. Deadlock is impossible. Because programs are deterministic, they may be debugged on sequential hardware. Programs can be highly scalable, running without change on different processor configurations or even architectures. However this flexibility places a high load on the functional compiler and runtime system. Our approach is to exploit parallelism which is notionally fairly fine-grained, but which can be dynamically com...