Abstract
Focal-plane Sensor-processors (FPSPs) are a camera technology that enable low power, high frame rate computation, making them suitable for edge computation. Unfortunately, these devices’ limited instruction sets and registers make developing complex algorithms difficult. In this work, we present Cain, an open-source compiler that targets SCAMP-5, a general-purpose FPSP – which generates code from multiple convolutional kernels. As an example, given the convolutional kernels for an MNIST digit recognition neural network, Cain produces code that is half as long, when compared to the other available compilers for SCAMP-5.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Single-entry matrix. Not to be confused with identity matrix.
- 2.
References
Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation OSDI 16, pp. 265–283 (2016)
Barthels, H., Psarras, C., Bientinesi, P.: Linnea: Automatic generation of efficient linear algebra programs (2019). https://arxiv.org/pdf/1912.12924.pdf
Bose, L., Chen, J., Carey, S.J., Dudek, P., Mayol-Cuevas, W.: Visual odometry for pixel processor arrays. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4614–4622 (October 2017)
Bose, L., Chen, J., Carey, S.J., Dudek, P., Mayol-Cuevas, W.: A camera that CNNs: towards embedded neural networks on pixel processor arrays. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1335–1344 (2019)
Carey, S.J., Barr, D.R.W., Wang, B., Lopich, A., Dudek, P.: Locating high speed multiple objects using a SCAMP-5 vision-chip. In: 2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, pp. 1–2 (August 2012)
Carey, S.J., Lopich, A., Barr, D.R.W., Wang, B., Dudek, P.: A 100,000 fps vision sensor with embedded 535GOPS/W \(256\times 256\) SIMD processor array. In: 2013 Symposium on VLSI Circuits, pp. C182–C183 (2013)
Chandra, A., Chattopadhyay, S.: Design of hardware efficient FIR filter: a review of the state-of-the-art approaches. Eng. Sci. Technol. Int. J. 19(1), 212–226 (2016)
Chen, J.: scamp5 kernel api macro analog.hpp file reference (January 2020). https://scamp.gitlab.io/scamp5d_doc/scamp5__kernel__api__macro__analog_8hpp.html
Chen, Y.H., Krishna, T., Emer, J.S., Sze, V.: Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J. Solid-State Circuits 52(1), 127–138 (2016)
Debrunner, T., Saeedi, S., Bose, L., Davison, A.J., Kelly, P.H.J.: Camera tracking on focal-plane sensor-processor arrays (2019)
Debrunner, T., Saeedi, S., Kelly, P.H.J.: AUKE: automatic kernel code generation for an analogue SIMD focal-plane sensor-processor array. ACM Trans. Archit. Code Optim. 15(4), 59:1–59:26 (2019)
Guillard, B.: CNNs-on-FPSPs (May 2019). https://github.com/brouwa/CNNs-on-FPSPs/tree/c6b5c51839e9e3c453681e5b0a3e3ef541ba3cce
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Martel, J.: Unconventional Processing with Unconventional Visual Sensing. Ph.D. thesis, Institut National des Sciences Appliquées de Lyon (2019)
Martel, J.N.P., Müller, L.K., Carey, S.J., Dudek, P., Wetzstein, G.: Neural sensors: learning pixel exposures for HDR imaging and video compressive sensing with programmable sensors. IEEE Trans. Pattern Anal. Mach. Intell. 42(7), 1642–1653 (2020)
Murai, R., Saeedi, S., Kelly, P.H.J.: BIT-VO: visual odometry at 300 FPS using Binary features from the focal plane. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020)
Saeedi, S., Bodin, B., Wagstaff, H., et al.: Navigating the landscape for real-time localization and mapping for robotics and virtual and augmented reality. Proc. IEEE 106(11), 2020–2039 (2018)
Stow, E.: Automatic Code Generation for Simultaneous Convolutional Kernels on Cellular Processor Arrays. Master’s thesis, Imperial College London (2020). http://edstow.co.uk/pub/2020/MEngThesis.pdf
Stow, E., Murai, R.: ed741/cain: 3.0-experiments.1 (August 2020). https://doi.org/10.5281/zenodo.3975615
Wong, M.Z., Guillard, B., Murai, R., Saeedi, S., Kelly, P.H.J.: AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane Sensor Processors. arXiv preprint arXiv:2006.01765 (2020)
XIMEA: xiB - PCI Express Cameras with high speed and resolution. https://www.ximea.com/pci-express-camera/pci-express-camera
Zarándy, Á.: Focal-Plane Sensor-Processor Chips. SpringerLink : Bücher, Springer, New York (2011). https://doi.org/10.1007/978-1-4419-6475-5
Acknowledgements
We would like to thank Piotr Dudek, Stephen J. Carey, and Jianing Chen at the University of Manchester for kindly providing access to SCAMP-5, and their support in our work. This work was partially supported by the EPSRC, grant reference EP/P010040/1.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Stow, E., Murai, R., Saeedi, S., Kelly, P.H.J. (2022). Cain: Automatic Code Generation for Simultaneous Convolutional Kernels on Focal-plane Sensor-processors. In: Chapman, B., Moreira, J. (eds) Languages and Compilers for Parallel Computing. LCPC 2020. Lecture Notes in Computer Science(), vol 13149. Springer, Cham. https://doi.org/10.1007/978-3-030-95953-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-95953-1_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95952-4
Online ISBN: 978-3-030-95953-1
eBook Packages: Computer ScienceComputer Science (R0)