Combining evolutionary algorithms and deep learning for hardware/software interface optimization

Lorenzo Servadei; Edoardo Mosca; Michael Werner; Volkan Esen; Robert Wille; Wolfgang Ecker

doi:10.1109/MLCAD48534.2019.9142090

Combining evolutionary algorithms and deep learning for hardware/software interface optimization

Lorenzo Servadei, Edoardo Mosca, Michael Werner, Volkan Esen, Robert Wille, Wolfgang Ecker

Computation, Information and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

With the advancement of Internet of Things, the cost of System-on-Chips (in terms of area, performance, etc.) becomes increasingly relevant for realizing affordable as well as performant devices. Although System-on-Chips are very diverse with respect to specifications and requirements, some components are ubiquitous. One of them is the Hardware/Software Interface, which serves for controlling communication and interconnected functionalities between Hardware and Software. Motivated by their common use, the implementation of optimized interfaces towards certain costs (in terms of area, performance, etc.) becomes a central problem in the design of embedded systems. In this work we introduce a novel optimization method for minimizing the cost of Hardware/Software Interfaces using Convolutional Neural Networks coupled with Evolutionary Algorithms.

Original language	English
Title of host publication	2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728157580
DOIs	https://doi.org/10.1109/MLCAD48534.2019.9142090
State	Published - Sep 2019
Event	1st ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2019 - Canmore, Canada Duration: 3 Sep 2019 → 4 Sep 2019

Publication series

Name	2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019

Conference

Conference	1st ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2019
Country/Territory	Canada
City	Canmore
Period	3/09/19 → 4/09/19

Keywords

Deep Learning
Evolutionary Algorithms
Hardware/Software Interface Optimization
Machine Learning

Access to Document

10.1109/MLCAD48534.2019.9142090

Cite this

Servadei, L., Mosca, E., Werner, M., Esen, V., Wille, R., & Ecker, W. (2019). Combining evolutionary algorithms and deep learning for hardware/software interface optimization. In 2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019 Article 9142090 (2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MLCAD48534.2019.9142090

@inproceedings{20f417e52437474497e5da9d2816f7cf,

title = "Combining evolutionary algorithms and deep learning for hardware/software interface optimization",

abstract = "With the advancement of Internet of Things, the cost of System-on-Chips (in terms of area, performance, etc.) becomes increasingly relevant for realizing affordable as well as performant devices. Although System-on-Chips are very diverse with respect to specifications and requirements, some components are ubiquitous. One of them is the Hardware/Software Interface, which serves for controlling communication and interconnected functionalities between Hardware and Software. Motivated by their common use, the implementation of optimized interfaces towards certain costs (in terms of area, performance, etc.) becomes a central problem in the design of embedded systems. In this work we introduce a novel optimization method for minimizing the cost of Hardware/Software Interfaces using Convolutional Neural Networks coupled with Evolutionary Algorithms.",

keywords = "Deep Learning, Evolutionary Algorithms, Hardware/Software Interface Optimization, Machine Learning",

author = "Lorenzo Servadei and Edoardo Mosca and Michael Werner and Volkan Esen and Robert Wille and Wolfgang Ecker",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 1st ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2019 ; Conference date: 03-09-2019 Through 04-09-2019",

year = "2019",

month = sep,

doi = "10.1109/MLCAD48534.2019.9142090",

language = "English",

series = "2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019",

}

Servadei, L, Mosca, E, Werner, M, Esen, V, Wille, R & Ecker, W 2019, Combining evolutionary algorithms and deep learning for hardware/software interface optimization. in 2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019., 9142090, 2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019, Institute of Electrical and Electronics Engineers Inc., 1st ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2019, Canmore, Canada, 3/09/19. https://doi.org/10.1109/MLCAD48534.2019.9142090

Combining evolutionary algorithms and deep learning for hardware/software interface optimization. / Servadei, Lorenzo; Mosca, Edoardo; Werner, Michael et al.
2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 9142090 (2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Combining evolutionary algorithms and deep learning for hardware/software interface optimization

AU - Servadei, Lorenzo

AU - Mosca, Edoardo

AU - Werner, Michael

AU - Esen, Volkan

AU - Wille, Robert

AU - Ecker, Wolfgang

PY - 2019/9

Y1 - 2019/9

N2 - With the advancement of Internet of Things, the cost of System-on-Chips (in terms of area, performance, etc.) becomes increasingly relevant for realizing affordable as well as performant devices. Although System-on-Chips are very diverse with respect to specifications and requirements, some components are ubiquitous. One of them is the Hardware/Software Interface, which serves for controlling communication and interconnected functionalities between Hardware and Software. Motivated by their common use, the implementation of optimized interfaces towards certain costs (in terms of area, performance, etc.) becomes a central problem in the design of embedded systems. In this work we introduce a novel optimization method for minimizing the cost of Hardware/Software Interfaces using Convolutional Neural Networks coupled with Evolutionary Algorithms.

AB - With the advancement of Internet of Things, the cost of System-on-Chips (in terms of area, performance, etc.) becomes increasingly relevant for realizing affordable as well as performant devices. Although System-on-Chips are very diverse with respect to specifications and requirements, some components are ubiquitous. One of them is the Hardware/Software Interface, which serves for controlling communication and interconnected functionalities between Hardware and Software. Motivated by their common use, the implementation of optimized interfaces towards certain costs (in terms of area, performance, etc.) becomes a central problem in the design of embedded systems. In this work we introduce a novel optimization method for minimizing the cost of Hardware/Software Interfaces using Convolutional Neural Networks coupled with Evolutionary Algorithms.

KW - Deep Learning

KW - Evolutionary Algorithms

KW - Hardware/Software Interface Optimization

KW - Machine Learning

UR - https://www.scopus.com/pages/publications/85091996305

U2 - 10.1109/MLCAD48534.2019.9142090

DO - 10.1109/MLCAD48534.2019.9142090

M3 - Conference contribution

AN - SCOPUS:85091996305

T3 - 2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019

BT - 2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2019

Y2 - 3 September 2019 through 4 September 2019

ER -

Servadei L, Mosca E, Werner M, Esen V, Wille R , Ecker W. Combining evolutionary algorithms and deep learning for hardware/software interface optimization. In 2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 9142090. (2019 ACM/IEEE 1st Workshop on Machine Learning for CAD, MLCAD 2019). doi: 10.1109/MLCAD48534.2019.9142090

Combining evolutionary algorithms and deep learning for hardware/software interface optimization

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this