| Autor: |
Saeed, Aamir, Erbad, Aiman Mahmood, Olsen, Rasmus Løvenstein |
| Jazyk: |
angličtina |
| Rok vydání: |
2015 |
| Zdroj: |
Saeed, A, Erbad, A M & Olsen, R L 2015, ' Context Aware Concurrent Execution Framework for Web Browser ', Paper presented at WWRF meeting 35, Copenhagen, Denmark, 14/10/2015-16/10/2015 . |
| Popis: |
Computing hungry multimedia web applications need to efficiently utilize the device resources. HTML5 web workers is a non-sharing concurrency platform that enables multimedia web application to utilize the available multi-core hardware. HTML5 web workers are implemented by major browser vendors to facilitate concurrent execution in web clients and enhance the quality of ambitious web applications. The concurrent execution in web workers allows parallel processing using available cores at the expense of communication overhead and extra computation. The benefits of concurrent execution can be maximized by balancing load across workers/CPU cores. This work presents load-balancing algorithms between web workers using parameters such as scheduler throughput, computation priority and game entity locality. An award-winning web-based multimedia game (raptjs.com) is used to test the performance of the load balance algorithms. The preliminary results indicate that the performance of game improved with effective load-balancing across web workers. Three load balancing algorithm were developed on top of DOHA, an open source JavaScript execution layer for multimedia applications. The load between web workers is transferred between web workers via serialized objects. The application performance is measured by measuring the jitter and the number of frames per second. The results showed improvement in performance with lower jitter and high FPS. These techniques can be used by developers to improve the application design giving end users better perceived quality of experience for demanding multimedia web based applications. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
