Convolution engine
Authors:
Open Access
- 23 June 2013
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 24-35
Abstract
This paper focuses on the trade-off between flexibility and efficiency in specialized computing. We observe that specialized units achieve most of their efficiency gains by tuning data storage and compute structures and their connectivity to the data-flow and data-locality patterns in the kernels. Hence, by identifying key data-flow patterns used in a domain, we can create efficient engines that can be programmed and reused across a wide range of applications. We present an example, the Convolution Engine (CE), specialized for the convolution-like data-flow that is common in computational photography, image processing, and video processing applications. CE achieves energy efficiency by capturing data reuse patterns, eliminating data transfer overheads, and enabling a large number of operations per memory access. We quantify the tradeoffs in efficiency and flexibility and demonstrate that CE is within a factor of 2-3x of the energy and area efficiency of custom units optimized for a single kernel. CE improves energy and area efficiency by 8-15x over a SIMD engine for most applications.Keywords
Funding Information
- Defense Advanced Research Projects Agency (HR0011-11-C-0007)
This publication has 21 references indexed in Scilit:
- GPUWattch2013
- Avoiding game over2012
- The FrankencameraACM Transactions on Graphics, 2010
- Computational Photography2009
- An adaptive color plane interpolation method based on edge detectionJournal of Electronics (China), 2007
- SURF: Speeded Up Robust Features2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- High dynamic range imaging2004
- Digital photography with flash and no-flash image pairsACM Transactions on Graphics, 2004
- Xtensa: a configurable and extensible processorIEEE Micro, 2000