Ferianc, M;
Fan, H;
Chu, RSW;
Stano, J;
Luk, W;
(2020)
Improving Performance Estimation for FPGA-Based Accelerators for Convolutional Neural Networks.
In: Rincón, F and Barba, J and So, HKH and Diniz, P and Caba, J, (eds.)
Applied Reconfigurable Computing. Architectures, Tools, and Applications: 16th International Symposium, ARC 2020, Toledo, Spain, April 1–3, 2020, Proceedings.
(pp. pp. 3-13).
Springer: Cham, Switzerland.
Preview |
Text
2002.00190v1.pdf - Published Version Download (161kB) | Preview |
Abstract
Field-programmable gate array (FPGA) based accelerators are being widely used for acceleration of convolutional neural networks (CNNs) due to their potential in improving the performance and reconfigurability for specific application instances. To determine the optimal configuration of an FPGA-based accelerator, it is necessary to explore the design space and an accurate performance prediction plays an important role during the exploration. This work introduces a novel method for fast and accurate estimation of latency based on a Gaussian process parametrised by an analytic approximation and coupled with runtime data. The experiments conducted on three different CNNs on an FPGA-based accelerator on Intel Arria 10 GX 1150 demonstrated a 30.7% improvement in accuracy with respect to the mean absolute error in comparison to a standard analytic method in leave-one-out cross-validation.
Type: | Proceedings paper |
---|---|
Title: | Improving Performance Estimation for FPGA-Based Accelerators for Convolutional Neural Networks |
Event: | 16th International Symposium on Applied Reconfigurable Computing |
ISBN-13: | 978-3-030-44533-1 |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1007/978-3-030-44534-8 |
Publisher version: | https://doi.org/10.1007/978-3-030-44534-8 |
Language: | English |
Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
Keywords: | Field-programmable gate array, Deep learning, Convolutional neural network, Performance estimation, Gaussian process |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL SLASH UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of Arts and Humanities UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of Arts and Humanities > Dept of Information Studies |
URI: | https://discovery.ucl.ac.uk/id/eprint/10127333 |
![](/style/images/loading.gif)
![](/style/images/loading.gif)
![](/style/images/loading.gif)
![](/style/images/loading.gif)
Archive Staff Only
![]() |
View Item |