DOI QR코드

DOI QR Code

WebCL-based Very High Resolution Image Processing Technology

WebCL 기반 초고해상도 이미지 처리 기술

  • 조명진 (고려대학교 전기전자공학연구소) ;
  • 한영선 (경일대학교 전자공학과)
  • Received : 2013.08.07
  • Accepted : 2013.09.28
  • Published : 2013.10.30

Abstract

In this paper, we are going to describe the performance characteristic of very high resolution image processing with WebCL on the web environment. In order to evaluate the variance of the execution time by WebCL, we modified the Pixastic library, one of the most representative image processing libraries written in JavaScript, by using WebCL. We achieved a speedup of up to 4.2 times and 2.8 times on average against the original one for the image of 8K Ultra HD with the WebCL-based library.

본 논문에서는 웹 환경에서 WebCL을 이용한 초고해상도 이미지 처리 기법의 성능을 분석하고자 한다. WebCL로 인한 성능의 변화를 측정하고 평가하기 위해 자바스크립트로 작성된 대표적인 이미지 처리 라이브러리인 Pixastic 라이브러리를 WebCL 기반의 코드로 수정하였다. WebCL 기반 라이브러리는 8K Ultra HD의 이미지에서 기존 라이브러리 대비 최대 4.2배의 성능 향상을 얻을 수 있었으며 평균적으로 2.8배의 성능 향상을 얻을 수 있었다.

Keywords

References

  1. Hickson, Ian, and David Hyatt. HTML5: A Vocabulary and Associated APIs for HTML and XHTML, World Wide Web Consortium, W3C Working Draft Edition, 2011.
  2. 한성민, 손윤식, 이양선. "스마트 크로스 플랫폼을 위한 스마트 가상기계의 설계 및 구현," 멀티미디어학회논문지, 제16권, 제2호, pp. 190-197, 2013. https://doi.org/10.9717/kmms.2013.16.2.190
  3. Kessin and Zachary. Programming HTML5 Applications: Building Powerful Cross-Platform Environments in JavaScript, O'Reilly Media Inc., Sebastopol, CA, 2011.
  4. G. Richards, S. Lebresne, B. Burg, and J. Vitek, "An Analysis of The Dynamic Behavior of JavaScript Programs," Proc. of 2010 ACM SIGPLAN Conf. Programming Language Design and Impl., pp. 1-12, 2010.
  5. E. Fortuna, O. Anderson, L. Ceze, and S. Eggers, "A Limit Study of JavaScript Parallelism," IEEE Int. Symp. on Workload Characterization, pp. 1-10, 2010.
  6. P. Joshi, M. Bourges-Sevenier, K. Russell, and Z. Mo, "Graphics Programming for the Web," ACM SIGGRAPH 2012 Courses, pp. 8:1-8:75, 2012.
  7. M.D. Benedetto, F. Ponchio, F. Ganovelli, and R. Scopigno, "Spidergl: A JavaScript 3D Graphics Library for Next-Generation WWW," Proc. of the 15th Int. Conf. on Web 3D Tech., pp. 165-174, 2010.
  8. J.K. Martinsen and H. Grahn, "An Alternative Optimization Technique for JavaScript Engines," Proc. of the Third Swedish Workshop on Multicore Computing, pp. 155-160, 2010.
  9. M. Mehrara, H. Po-Chun, M. Samadi, and S. Mahlke, "Dynamic Parallelization of Java- Script Applications using an Ultra-Lightweight Speculation Mechanism," IEEE 17th Int. Symp. on High Performance Computer Architecture, pp. 87-98, 2011.
  10. I. Hickson, Web Workers, W3C Working Draft 01, http://dev.w3.org/html5/workers/, 2011.
  11. S. Herhut, R.L. Hudson, T. Shpeisman, and J. Sreeram, "Parallel Programming for the Web," Proc. of 4th USENIX Conf. Hot Topics in Parallelism, pp. 1-6, 2012.
  12. J. Sreeram, S. Herhut, R.L. Hudson, and T. Shpeisman, "Teaching Parallelism with River trail," Proc. of 2012 Workshop on Developing Competency in Parallelism: Techniques for Education and Training, pp. 1-8, 2012.
  13. Khronous Group, WebCL-Heterogeneous Parallel Computing in HTML5 Web Browsers, http://www.khronos.org/webcl/, 2011.
  14. Pixastic JavaScript Image Processing Library, http://www.pixastic.com/, 2011.
  15. M. Mehrara and S. Mahlke, "Dynamically Accelerating Client-side Web Applications through Decoupled Execution," Proc. of 9th IEEE/ACM Int. Symp. Code Generation and Optimization, pp. 74-84, 2011.
  16. Nokia Research, Nokia WebCL Extension for Firefox, http://webcl.nokiaresearch.com/, 2011.
  17. W. Jeon, T. Brutch, and S. Gibbs, "Webcl for Hardware-Accelerated Web Applications," Proc. of 2012 World Wide Web, 2012.
  18. Nvidia Corporation, Geforce GT 650m, http:// www.geforce.com/hardware/notebook-gpus/ geforce-gt-650m/, 2012.