A Scalable, Heterogeneous Hardware Platform for Accelerated AIoT based on Microservers
Book chapter, 2023
Performance and energy efficiency are key aspects of next-generation AIoT hardware. This chapter presents a scalable, heterogeneous hardware platform for accelerated AIoT based on microserver technology. It integrates several accelerator platforms based on technologies like CPUs, embedded GPUs, FPGAs, or specialized ASICs, supporting the full range of the cloud−edgeIoT continuum. The modular microserver approach enables the integrationof different, heterogeneous accelerators into one platform. Benchmarking the various accelerators takes performance, energy efficiency, and accuracy into account. The results provide a solid overview of available accelerator
solutions and guide hardware selection for AIoT applications from the far edge to the cloud.
solutions and guide hardware selection for AIoT applications from the far edge to the cloud.
performance classification.
deep learning
FPGA
microserver
accelerator
energy-efficiency
IoT
(far) edge-computing
machine learning
AIoT
Author
René Griessl
Bielefeld University
Florian Porrmann
Bielefeld University
Nils Kucza
Bielefeld University
K. Mika
Bielefeld University
Jens Hagemeyer
Bielefeld University
Martin Kaiser
Bielefeld University
Mario Porrmann
Osnabrück University
M. Tassemeier
Osnabrück University
M. Flottmann
Osnabrück University
Fareed Mohammad Qararyah
Chalmers, Computer Science and Engineering (Chalmers), Computer Engineering (Chalmers)
Muhammad Waqar Azhar
Chalmers, Computer Science and Engineering (Chalmers), Computer Engineering (Chalmers)
Pedro Petersen Moura Trancoso
Chalmers, Computer Science and Engineering (Chalmers), Computer Engineering (Chalmers)
D. Odman
EmbeDL AB
K. Gugala
ANTMICRO Ltd
G. Latosinski
ANTMICRO Ltd
Shaping the Future of IoT with Edge Intelligence How Edge Computing Enables the Next Generation of IoT Applications
179-196
9788770040273 (ISBN)
Very Efficient Deep Learning in IOT (VEDLIoT)
European Commission (EC) (EC/H2020/957197), 2020-11-01 -- 2023-10-31.
Subject Categories
Computer and Information Science
Electrical Engineering, Electronic Engineering, Information Engineering
DOI
10.13052/rp-9788770040266