Kvik: A task based middleware with composable scheduling policies (2009.05504v1)

Abstract: In this paper we present Kvik: an implementation of a task-based "middleware" for shared memory parallel programming in the Rust language built on top of the Rayon library. We devise a system allowing several task-splitting schedulers to be finely tuned by the end users. Among these, we propose an implementation of an adaptive scheduler reducing tasks creations (splits) to bare minimum by linking tasks splitting to steal requests. Another important scheduler that allows turning computations into sequences of parallel operations is described. This operator proves itself particularly useful for interruptible computations. We exhibit different code examples well suited for different types of schedulers. We conclude our work with a set of benchmarks making heavy use of composability. In particular we present a parallel stable sort implementation with up to 1.5x more speedup when compared to the state-of-the-art parallel sorting implementation.