Paper Info
Title
JAWS: a JavaScript framework for adaptive CPU-GPU work sharing
Abstract
This paper introduces jAWS, a JavaScript framework for adaptive work sharing between CPU and GPU for data-parallel workloads. Unlike conventional heterogeneous parallel programming environments for JavaScript, which use only one compute device when executing a single kernel, jAWS accelerates kernel execution by exploiting both devices to realize full performance potential of heterogeneous multicores. jAWS employs an efficient work partitioning algorithm that finds an optimal work distribution between the two devices without requiring offline profiling. The jAWS runtime provides shared arrays for multiple parallel contexts, hence eliminating extra copy overhead for input and output data. Our preliminary evaluation with both CPU-friendly and GPU-friendly benchmarks demonstrates that jAWS provides good load balancing and efficient data communication between parallel contexts, to significantly outperform best single-device execution.
Year
DOI
Venue
2015
10.1145/2688500.2688525
PPOPP
Keywords
Field
DocType
gpu,data parallelism,concurrent programming,scheduler,web browser,multi-core,heterogeneity,work sharing,language classifications,javascript,multi core
Kernel (linear algebra),Programming language,Web browser,Profiling (computer programming),Load balancing (computing),Computer science,Parallel computing,Input/output,Data parallelism,Multi-core processor,JavaScript,Distributed computing
Conference
Volume
Issue
ISSN
50
8
0362-1340
Citations 
PageRank 
References 
3
0.42
2
Authors
7
Name
Order
Citations
PageRank
Xianglan Piao141.11
Channoh Kim2132.29
Young-Hwan Oh3198.43
Huiying Li430.42
Jincheon Kim530.42
Hanjun Kim610811.11
Jae W. Lee760752.37