Scheduling parallel programs by work stealing with private deques

Author:

Acar Umut A.1,Chargueraud Arthur2,Rainey Mike3

Affiliation:

1. Carnegie Mellon University, Pittsburgh, USA

2. Inria Saclay, Paris, France

3. Max Planck Institute for Software Systems, Kaiserslautern, Germany

Abstract

Work stealing has proven to be an effective method for scheduling parallel programs on multicore computers. To achieve high performance, work stealing distributes tasks between concurrent queues, called deques, which are assigned to each processor. Each processor operates on its deque locally except when performing load balancing via steals. Unfortunately, concurrent deques suffer from two limitations: 1) local deque operations require expensive memory fences in modern weak-memory architectures, 2) they can be very difficult to extend to support various optimizations and flexible forms of task distribution strategies needed many applications, e.g., those that do not fit nicely into the divide-and-conquer, nested data parallel paradigm. For these reasons, there has been a lot recent interest in implementations of work stealing with non-concurrent deques, where deques remain entirely private to each processor and load balancing is performed via message passing. Private deques eliminate the need for memory fences from local operations and enable the design and implementation of efficient techniques for reducing task-creation overheads and improving task distribution. These advantages, however, come at the cost of communication. It is not known whether work stealing with private deques enjoys the theoretical guarantees of concurrent deques and whether they can be effective in practice. In this paper, we propose two work-stealing algorithms with private deques and prove that the algorithms guarantee similar theoretical bounds as work stealing with concurrent deques. For the analysis, we use a probabilistic model and consider a new parameter, the branching depth of the computation. We present an implementation of the algorithm as a C++ library and show that it compares well to Cilk on a range of benchmarks. Since our approach relies on private deques, it enables implementing flexible task creation and distribution strategies. As a specific example, we show how to implement task coalescing and steal-half strategies, which can be important in fine-grain, non-divide-and-conquer algorithms such as graph algorithms, and apply them to the depth-first-search problem.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Graphics and Computer-Aided Design,Software

Reference43 articles.

1. Umut A. Acar Arthur Charguéraud and Mike Rainey. Technical report associated with the present paper. http://arthur.chargueraud.org/research/2013/ppopp/full.pdf Umut A. Acar Arthur Charguéraud and Mike Rainey. Technical report associated with the present paper. http://arthur.chargueraud.org/research/2013/ppopp/full.pdf

2. Umut A. Acar Guy E. Blelloch and Robert D. Blumofe. The data locality of work stealing. Theory of Computing Systems (TOCS) 35(3):321--347 2002. Umut A. Acar Guy E. Blelloch and Robert D. Blumofe. The data locality of work stealing. Theory of Computing Systems (TOCS) 35(3):321--347 2002.

3. Thread scheduling for multiprogrammed multiprocessors

4. The Natural Work-Stealing Algorithm is Stable

Cited by 61 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Work Assisting: Linking Task-Parallel Work Stealing with Data-Parallel Self Scheduling;Proceedings of the 10th ACM SIGPLAN International Workshop on Libraries, Languages and Compilers for Array Programming;2024-06-20

2. Brief Announcement: Work Stealing through Partial Asynchronous Delegation;Proceedings of the 36th ACM Symposium on Parallelism in Algorithms and Architectures;2024-06-17

3. ABSS: An Adaptive Batch-Stream Scheduling Module for Dynamic Task Parallelism on Chiplet-based Multi-Chip Systems;ACM Transactions on Parallel Computing;2024-03-11

4. SCoOL - Scalable Common Optimization Library;2023 IEEE 30th International Conference on High Performance Computing, Data, and Analytics (HiPC);2023-12-18

5. A parallel particle swarm optimization framework based on a fork-join thread pool using a work-stealing mechanism;Applied Soft Computing;2023-09

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3