Scheduling directives: Accelerating shared-memory many-core processor execution

摘要

We consider many-core processors with a task-graph oriented programming model, whereby scheduling constraints among tasks are decided offline, and are then enforced by the runtime system using dedicated hardware. Here, exposing and beneficially exploiting fine grain data and control parallelism is increasingly important. Therefore, high expressive power for stating such constraints/directives, along with the ability to implement them in fast, simple hardware, is critical for success. In this paper, we focus on the relationship among different duplicable (multi-instance) tasks, which are used to express and exploit data parallelism. We extend the conventional Start-After-Complete (precedence) constraint to also be usable between replicas of different such tasks rather than only between entire tasks, thereby increasing the exposable parallelism. Additionally, we propose the parameterized Start-After-Start constraint, which can be used to control the degree of "lockstep" among multiple such tasks, e.g., in order to improve cache performance when the tasks work on the same data. Also, we briefly describe several additional interesting directives. Finally, we show that the directives can be supported efficiently in hardware. Hypercore, a very efficient CREW PRAM-like shared-cache architecture, which is very challenging because it has extremely fast dispatching for basic constraints, is used in the discussion. However, the new directives have broader applicability. Having shown the possibility of simple implementation and indications of benefit, this motivates further exploration of these directives and their implementation in hardware, as well as their support by programming tools.