Abstract
Modern web browsers are required to execute many complex, compute-intensive applications, mostly written in JavaScript. With widespread adoption of heterogeneous processors, re- cent JavaScript-based data-parallel programming models, such as River Trail and WebCL, support multiple types of processing elements including CPUs and GPUS. However, significant performance gains are still left on the table since the program kernel runs on only one compute device, typ- ically selected at kernel invocation. This paper proposes a new framework for efficient work sharing between CPU and GPU for data-parallel JavaScript workloads. The work shar- ing scheduler partitions the input data into smaller chunks and dynamically dispatches them to both CPU and GPU for concurrent execution. For four data-parallel programs, our framework improves performance by up to 65% with a geometric mean speedup of 33% over GPU-only execution.
Original language | English |
---|---|
Title of host publication | WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web |
Publisher | Association for Computing Machinery, Inc |
Pages | 357-358 |
Number of pages | 2 |
ISBN (Electronic) | 9781450327459 |
DOIs | |
Publication status | Published - 2014 Apr 7 |
Event | 23rd International Conference on World Wide Web, WWW 2014 - Seoul, Korea, Republic of Duration: 2014 Apr 7 → 2014 Apr 11 |
Publication series
Name | WWW 2014 Companion - Proceedings of the 23rd International Conference on World Wide Web |
---|
Other
Other | 23rd International Conference on World Wide Web, WWW 2014 |
---|---|
Country/Territory | Korea, Republic of |
City | Seoul |
Period | 14/4/7 → 14/4/11 |
Bibliographical note
Publisher Copyright:© Copyright 2014 by the International World Wide Web Conferences Steering Committee.
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Software