Chunking for Dynamic Linear Pipelines
-
Published:2019-12-31
Issue:4
Volume:16
Page:1-25
-
ISSN:1544-3566
-
Container-title:ACM Transactions on Architecture and Code Optimization
-
language:en
-
Short-container-title:ACM Trans. Archit. Code Optim.
Author:
Mastoras Aristeidis1ORCID,
Gross Thomas R.1
Affiliation:
1. ETH Zurich, Zurich, Switzerland
Abstract
Dynamic scheduling and dynamic creation of the pipeline structure are crucial for efficient execution of pipelined programs. Nevertheless, dynamic systems imply higher overhead than static systems. Therefore, chunking is the key to decrease the synchronization and scheduling overhead by grouping activities. We present a chunking algorithm for dynamic systems that handles dynamic linear pipelines, which allow the number and duration of stages to be determined at run-time. The evaluation on 44 cores shows that chunking brings the overhead of dynamic scheduling down to that of a static scheduler, and it enables efficient and scalable execution of fine-grained dynamic linear pipelines.
Funder
Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
Publisher
Association for Computing Machinery (ACM)
Subject
Hardware and Architecture,Information Systems,Software
Reference32 articles.
1. 2006. Standard Performance Evaluation Corporation (SPEC). Retrieved from: https://www.spec.org. 2006. Standard Performance Evaluation Corporation (SPEC). Retrieved from: https://www.spec.org.
2. 2015. Parallel BZIP2 (PBZIP2) Data Compression Software. Retrieved from: http://compression.ca/pbzip2. 2015. Parallel BZIP2 (PBZIP2) Data Compression Software. Retrieved from: http://compression.ca/pbzip2.
3. The PARSEC benchmark suite
4. Cilk
5. HELIX
Cited by
1 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