Compiling CNNs with Cain: focal-plane processing for robot navigation
File(s)
Published version
Author(s)
Type
Journal Article
Abstract
Focal-plane Sensor-processors (FPSPs) are a camera technology that enables low power, high frame rate computation in the image sensor itself, making them suitable for edge computation. To fit into the sensor array, FPSPs are highly resource-constrained, with limited instruction set and few registers - which makes developing complex algorithms difficult. In this work, we present Cain, a compiler for convolutional filters that targets SCAMP-5, a general-purpose FPSP. Cain generates code to evaluate multiple convolutional kernels at the same time. It generates code that avoids the need for hardware multipliers, while orchestrating the exploitation of common sub-terms—leading to a large reduction in instruction count compared to both straightforward and prior optimized approaches. We demonstrate the capability enabled by Cain on SCAMP-5 with robotic navigation for near-sensor high-speed and low-power computation, by using Cain to implement a neural network on the focal plane.
Date Issued
2022-09-10
Date Acceptance
2022-06-28
Citation
Autonomous Robots, 2022, 46, pp.893-910
ISSN
0929-5593
Publisher
Springer
Start Page
893
End Page
910
Journal / Book Title
Autonomous Robots
Volume
46
Copyright Statement
© The Author(s) 2022. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
License URL
Sponsor
Engineering & Physical Science Research Council (E
Engineering & Physical Science Research Council (EPSRC)
Identifier
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000852366900001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
Grant Number
PO: ERZ1820653
EP/P010040/1
Subjects
Science & Technology
Technology
Computer Science, Artificial Intelligence
Robotics
Computer Science
Convolution
SIMD
Image sensor
Analogue computing
Edge inference
Publication Status
Published
Date Publish Online
2022-09-10