FPGA based Adaptive Hardware Acceleration for Multiple Deep Learning Tasks

Yufan Lu, Xiaojun Zhai, Sangeet Saha, Shoaib Ehsan, Klaus D. McDonald-Maier

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Machine learning, and in particular deep learning (DL), has seen strong success in a wide variety of applications, e.g. object detection, image classification and self-driving. However, due to the limitations on hardware resources and power consumption, there are many challenges to deploy deep learning algorithms on resource-constrained mobile and embedded systems, especially for systems running multiple DL algorithms for a variety of tasks. In this paper, an adaptive hardware resource management system, implemented on field-programmable gate arrays (FPGAs), is proposed to dynamically manage the on-chip hardware resources (e.g. LUTs, BRAMs and DSPs) to adapt to a variety of tasks. Using dynamic function exchange (DFX) technology, the system can dynamically allocate hardware resources to deploy deep learning units (DPUs) so as to balance the requirements, performance and power consumption of the deep learning applications. The prototype is implemented on the Xilinx Zynq UltraScale+ series chips. The experiment results indicate that the proposed scheme significantly improves the computing efficiency of the resource-constrained systems under various experimental scenarios. Compared to the baseline, the proposed strategy consumes 38% and 82% of power in low working load cases and high working load cases, respectively. Typically, the proposed system can save approximately 75.8% of energy.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE 14th International Symposium on Embedded Multicore/Many-Core Systems-on-Chip, MCSoC 2021
EditorsRandall S. Bilof
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages204-209
Number of pages6
ISBN (Electronic)9781665438605
ISBN (Print)9781728187525
DOIs
Publication statusPublished - 20 Dec 2021
Externally publishedYes
Event14th IEEE International Symposium on Embedded Multicore/Many-Core Systems-on-Chip - Singapore, Singapore
Duration: 20 Dec 202123 Dec 2021
Conference number: 14

Publication series

NameProceedings - 2021 IEEE 14th International Symposium on Embedded Multicore/Many-Core Systems-on-Chip, MCSoC 2021

Conference

Conference14th IEEE International Symposium on Embedded Multicore/Many-Core Systems-on-Chip
Abbreviated titleMCSoC 2021
Country/TerritorySingapore
CitySingapore
Period20/12/2123/12/21

Fingerprint

Dive into the research topics of 'FPGA based Adaptive Hardware Acceleration for Multiple Deep Learning Tasks'. Together they form a unique fingerprint.

Cite this