IDEAL: Image DEnoising AcceLerator

Mostafa Mahmoud, Bojian Zheng, Alberto Delmás Lascorz, Felix Heide, Jonathan Assouline, Paul Boucher, Emmanuel Onzon, Andreas Moshovos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Computational imaging pipelines (CIPs) convert the raw output of imaging sensors into the high-quality images that are used for further processing. This work studies how Block-Matching and 3D filtering (BM3D), a state-of-the-art denoising algorithm can be implemented to meet the demands of user-interactive (UI) applications. Denoising is the most computationally demanding stage of a CIP taking more than 95% of time on a highly-optimized software implementation [29].We analyze the performance and energy consumption of optimized software implementations on three commodity platforms and find that their performance is inadequate. Accordingly, we consider two alternatives: a dedicated accelerator, and running recently proposed Neural Network (NN) based approximations of BM3D [9, 27] on an NN accelerator. We develop Image DEnoising AcceLerator(IDEAL), a hardware BM3D accelerator which incorporates the following techniques: 1) a novel software-hardware optimization, Matches Reuse (MR), that exploits typical image content to reduce the computations needed by BM3D, 2) prefetching and judicious use of on-chip buffering to minimize execution stalls and off-chip bandwidth consumption, 3) a careful arrangement of specialized computing blocks, and 4) data type precision tuning. Over a dataset of images with resolutions ranging from 8 megapixel (MP) and up to 42MP, IDEAL is 11, 352× and 591× faster than high-end general-purpose (CPU) and graphics processor (GPU) software implementations with orders of magnitude better energy eficiency. Even when the NN approximations of BM3D are run on the DaDianNao [14] high-end hardware NN accelerator, IDEAL is 5.4× faster and 3.95× more energy efficient.

Original languageEnglish (US)
Title of host publicationMICRO 2017 - 50th Annual IEEE/ACM International Symposium on Microarchitecture Proceedings
PublisherIEEE Computer Society
Pages82-95
Number of pages14
ISBN (Electronic)9781450349529
DOIs
StatePublished - Oct 14 2017
Event50th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2017 - Cambridge, United States
Duration: Oct 14 2017Oct 18 2017

Publication series

NameProceedings of the Annual International Symposium on Microarchitecture, MICRO
VolumePart F131207

Other

Other50th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2017
CountryUnited States
CityCambridge
Period10/14/1710/18/17

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture

Keywords

  • Accelerator
  • Computational imaging
  • Image denoising
  • Neural networks

Fingerprint Dive into the research topics of 'IDEAL: Image DEnoising AcceLerator'. Together they form a unique fingerprint.

  • Cite this

    Mahmoud, M., Zheng, B., Lascorz, A. D., Heide, F., Assouline, J., Boucher, P., Onzon, E., & Moshovos, A. (2017). IDEAL: Image DEnoising AcceLerator. In MICRO 2017 - 50th Annual IEEE/ACM International Symposium on Microarchitecture Proceedings (pp. 82-95). (Proceedings of the Annual International Symposium on Microarchitecture, MICRO; Vol. Part F131207). IEEE Computer Society. https://doi.org/10.1145/3123939.3123941