Context Aware Concurrent Execution Framework for Web Browsers

Aamir Saeed, Aiman Erbad, Rasmus Løvenstein Olsen

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

Computing hungry multimedia web applications need to efficiently utilize all the resources of a device. HTML5 web workers is a non-sharing concurrency platform that enables multimedia web application to utilize the available multicore 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 entities locality. An award-winning web-based multimedia game (raptjs.com) is used to evaluate the performance of load balancing algorithms. The preliminary results indicated that the performance of game improved with the proposed load-balancing across web workers. The load balancing algorithms 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. Effects of load transfer between on the overall application performance was measured by analyzing jitter and number of frames per second. Load balancing algorithms and load transfer mechanism can be used by developers to improve the application design, and giving end users better perceived quality of experience for demanding multimedia web based applications.
OriginalsprogEngelsk
Artikelnummer010
TidsskriftNordic and Baltic Journal of Information and Communications Technologies
Vol/bind2016
Udgave nummer1
Sider (fra-til)185-208
ISSN1902-097X
DOI
StatusUdgivet - 2016

Fingerprint

Web browsers
Resource allocation
Jitter
World Wide Web
Program processors
Throughput
Hardware
Communication
Processing

Citer dette

@article{f83abf38424548238a46db3a59f46f40,
title = "Context Aware Concurrent Execution Framework for Web Browsers",
abstract = "Computing hungry multimedia web applications need to efficiently utilize all the resources of a device. HTML5 web workers is a non-sharing concurrency platform that enables multimedia web application to utilize the available multicore 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 entities locality. An award-winning web-based multimedia game (raptjs.com) is used to evaluate the performance of load balancing algorithms. The preliminary results indicated that the performance of game improved with the proposed load-balancing across web workers. The load balancing algorithms 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. Effects of load transfer between on the overall application performance was measured by analyzing jitter and number of frames per second. Load balancing algorithms and load transfer mechanism can be used by developers to improve the application design, and giving end users better perceived quality of experience for demanding multimedia web based applications.",
author = "Aamir Saeed and Aiman Erbad and Olsen, {Rasmus L{\o}venstein}",
year = "2016",
doi = "10.13052/nbjict1902-097X.2016.010",
language = "English",
volume = "2016",
pages = "185--208",
journal = "Nordic and Baltic Journal of Information and Communications Technologies",
issn = "1902-097X",
publisher = "Nord I C T",
number = "1",

}

Context Aware Concurrent Execution Framework for Web Browsers. / Saeed, Aamir; Erbad, Aiman; Olsen, Rasmus Løvenstein.

I: Nordic and Baltic Journal of Information and Communications Technologies, Bind 2016, Nr. 1, 010, 2016, s. 185-208.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Context Aware Concurrent Execution Framework for Web Browsers

AU - Saeed, Aamir

AU - Erbad, Aiman

AU - Olsen, Rasmus Løvenstein

PY - 2016

Y1 - 2016

N2 - Computing hungry multimedia web applications need to efficiently utilize all the resources of a device. HTML5 web workers is a non-sharing concurrency platform that enables multimedia web application to utilize the available multicore 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 entities locality. An award-winning web-based multimedia game (raptjs.com) is used to evaluate the performance of load balancing algorithms. The preliminary results indicated that the performance of game improved with the proposed load-balancing across web workers. The load balancing algorithms 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. Effects of load transfer between on the overall application performance was measured by analyzing jitter and number of frames per second. Load balancing algorithms and load transfer mechanism can be used by developers to improve the application design, and giving end users better perceived quality of experience for demanding multimedia web based applications.

AB - Computing hungry multimedia web applications need to efficiently utilize all the resources of a device. HTML5 web workers is a non-sharing concurrency platform that enables multimedia web application to utilize the available multicore 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 entities locality. An award-winning web-based multimedia game (raptjs.com) is used to evaluate the performance of load balancing algorithms. The preliminary results indicated that the performance of game improved with the proposed load-balancing across web workers. The load balancing algorithms 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. Effects of load transfer between on the overall application performance was measured by analyzing jitter and number of frames per second. Load balancing algorithms and load transfer mechanism can be used by developers to improve the application design, and giving end users better perceived quality of experience for demanding multimedia web based applications.

U2 - 10.13052/nbjict1902-097X.2016.010

DO - 10.13052/nbjict1902-097X.2016.010

M3 - Journal article

VL - 2016

SP - 185

EP - 208

JO - Nordic and Baltic Journal of Information and Communications Technologies

JF - Nordic and Baltic Journal of Information and Communications Technologies

SN - 1902-097X

IS - 1

M1 - 010

ER -