Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Best of 2016 Recommended by Editor Recommended by Reviewer Recommended by Reader
Search
Data-driven concurrency for high performance computing
Matheou G., Evripidou P.  ACM Transactions on Architecture and Code Optimization 14 (4): 1-26, 2017. Type: Article
Date Reviewed: Aug 30 2018

Fine-grained dataflow computing creates circumstances that technologies, particularly hardware technologies, have difficulty handling. However, techniques like coarsening computational grain and substituting software for hardware, as described in this paper, can help realize the promises of dataflow computing. The reported results show that these techniques deliver respectable and responsive performance with effective and efficient utilization.

Data-driven multithreading models coarse-grained computations. Schedulers and a distributed shared memory (DSM) model over multinode, multicore high-performance computing (HPC) systems model dataflow architectures. Programs are explicit thread sets with specialized thread types supporting distributed recursive computations. The thread-core mapping is static, and threads are scheduled dynamically when other threads have computed all required input. The DSM abstraction provides inter-thread communication, along with message passing for selected special cases and lower level matters.

Evaluation was comprehensive across HPC architectures, system capabilities (a custom network interface versus the message passing interface), algorithms, and competing HPC systems. The results of most combinations are respectable to impressive, showing good scalability over small problem sizes and high core counts. Extracting program parallelism is more explicit than it is in hardware-supported dataflow computing, but is consonant with other thread-based HPC computing paradigms.

The system described is a continuation of prior work. For most people, reading this paper will be like joining an ongoing conversation. Prior knowledge of distributed and high-performance computing is necessary and somewhat helpful, but mapping the myriad details presented into general-level knowledge requires ample and judicious assumptions, which slows down reading. The writing is solid, and the bibliography is fulsome but selective.

Reviewer:  R. Clayton Review #: CR146225 (1811-0566)
Bookmark and Share
  Reviewer Selected
Editor Recommended
 
 
Distributed Architectures (C.1.4 ... )
 
 
Distributed Programming (D.1.3 ... )
 
 
Performance of Systems (C.4 )
 
Would you recommend this review?
yes
no
Other reviews under "Distributed Architectures": Date
Data-driven concurrency for high performance computing
Matheou G., Evripidou P.  ACM Transactions on Architecture and Code Optimization 14(4): 1-26, 2017. Type: Article, Reviews: (2 of 2)
Oct 8 2018
Husky: towards a more efficient and expressive distributed computing framework
Yang F., Li J., Cheng J.  Proceedings of the VLDB Endowment 9(5): 420-431, 2016. Type: Article
Feb 7 2017
Computing in social networks
Giurgiu A., Guerraoui R., Huguenin K., Kermarrec A.  Information and Computation 2343-16, 2014. Type: Article
Feb 5 2015
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright © 2000-2018 ThinkLoud, Inc.
Terms of Use
| Privacy Policy