QuickSched: Task-based parallelism with dependencies and conflicts

TL;DR

QuickSched is an open-source C library that enhances task-based parallel programming by incorporating task conflicts and dependencies, enabling efficient execution and scaling on multi-core shared-memory systems.

Contribution

It introduces a novel conflict-aware task scheduling scheme using lockable hierarchical resources, extending standard dependency-only models.

Findings

Performs well on 64-core systems

Scales efficiently for QR decomposition

Effective for Barnes-Hut tree code

Abstract

This paper describes QuickSched, a compact and efficient Open-Source C-language library for task-based shared-memory parallel programming. QuickSched extends the standard dependency-only scheme of task-based programming with the concept of task conflicts, i.e.~sets of tasks that can be executed in any order, yet not concurrently. These conflicts are modelled using exclusively lockable hierarchical resources. The scheduler itself prioritizes tasks along the critical path of execution and is shown to perform and scale well on a 64-core parallel shared-memory machine for two example problems: A tiled QR decomposition and a task-based Barnes-Hut tree code.