DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Hardware Execution Time Prediction for Neural Network Layers

Osterwind, Adrian and Droste-Rehling, Julian and Vemparala, Manoj Rohit and Helms, Domenik (2022) Hardware Execution Time Prediction for Neural Network Layers. In: Workshops of ECML PKDD 2022, pp. 582-593. Springer Nature Switzerland. ITEM 2022, 19.10.2022-19.10.2022, Grenoble, Frankreich. doi: 10.1007/978-3-031-23618-1_39. ISBN 978-3-031-23617-4.

[img] PDF - Only accessible within DLR bis 1 January 2024

Official URL: https://link.springer.com/chapter/10.1007/978-3-031-23618-1_39


Abstract. We present an estimation methodology, accurately predicting the execution time for a given embedded Artificial Intelligence (AI) accelerator and a neural network (NN) under analysis. The timing prediction is implemented as a python library called Model of Neural Network Execution Time (MONNET) and is able to perform its predictions analyzing the Keras description of an NN under test within milliseconds. This enables several techniques to design NNs for embedded hardware. Designers can avoid training networks which could be functionally sufficient but will likely fail the timing requirements. The technique can also be included into automated network architecture search algorithms, enabling exact hardware execution times to become one contributor to the search’s target function. In order to perform precise estimations for a target hardware, each new hardware needs to undergo an initial automatic characterization process, using tens of thousands of different small NNs. This process may need several days, depending on the hardware. We tested our methodology for the Intel Neural Compute Stick 2, where we could achieve an root mean squared percentage error (RMSPE) below 21 % for a large range of industry relevant NNs from vision processing.

Item URL in elib:https://elib.dlr.de/188922/
Document Type:Conference or Workshop Item (Speech)
Additional Information:Acknowledgment This publication was created as part of the research project KI Delta Learning (project number: 19A19013K) funded by the Federal Ministry for Economic Affairs and Energy (BMWi) on the basis of a decision by the German Bundestag. The publication was published by Springer AG
Title:Hardware Execution Time Prediction for Neural Network Layers
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Osterwind, AdrianUNSPECIFIEDhttps://orcid.org/0000-0002-0752-8698UNSPECIFIED
Droste-Rehling, JulianSiemens AG (Bremen)UNSPECIFIEDUNSPECIFIED
Helms, DomenikUNSPECIFIEDhttps://orcid.org/0000-0001-7326-200XUNSPECIFIED
Journal or Publication Title:Workshops of ECML PKDD 2022
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In ISI Web of Science:No
Page Range:pp. 582-593
Publisher:Springer Nature Switzerland
Series Name:Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Keywords:Execution time · Prediction · Neural Networks · Analytical Model.
Event Title:ITEM 2022
Event Location:Grenoble, Frankreich
Event Type:Workshop
Event Dates:19.10.2022-19.10.2022
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:other
DLR - Research area:Transport
DLR - Program:V - no assignment
DLR - Research theme (Project):V - no assignment
Location: Oldenburg
Institutes and Institutions:Institute of Systems Engineering for Future Mobility > System Evolution and Operation
Deposited By: Osterwind, Adrian
Deposited On:25 Oct 2022 11:46
Last Modified:29 Mar 2023 00:52

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.