A Scalable, Heterogeneous Hardware Platform for Accelerated AIoT based on Microservers
Kapitel i bok, 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.

performance classification.

deep learning

FPGA

microserver

accelerator

energy-efficiency

IoT

(far) edge-computing

machine learning

AIoT

Författare

René Griessl

Universität Bielefeld

Florian Porrmann

Universität Bielefeld

Nils Kucza

Universität Bielefeld

K. Mika

Universität Bielefeld

Jens Hagemeyer

Universität Bielefeld

Martin Kaiser

Universität Bielefeld

Mario Porrmann

Universität Osnabrück

M. Tassemeier

Universität Osnabrück

M. Flottmann

Universität Osnabrück

Fareed Mohammad Qararyah

Chalmers, Data- och informationsteknik, Datorteknik

Muhammad Waqar Azhar

Chalmers, Data- och informationsteknik, Datorteknik

Pedro Petersen Moura Trancoso

Chalmers, Data- och informationsteknik, Datorteknik

D. Odman

EmbeDL AB

K. Gugala

ANTMICRO AB

G. Latosinski

ANTMICRO AB

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)

Europeiska kommissionen (EU) (EC/H2020/957197), 2020-11-01 -- 2023-10-31.

Ämneskategorier

Data- och informationsvetenskap

Elektroteknik och elektronik

DOI

10.13052/rp-9788770040266

Mer information

Senast uppdaterat

2023-10-13