Instruction-set architecture exploration of VLIW aSIPs using a genetic algorithm

R. Jordans; L. Jozwiak; H. Corporaal

doi:10.1109/MECO.2014.6862720

Instruction-set architecture exploration of VLIW aSIPs using a genetic algorithm

R. Jordans, L. Jozwiak, H. Corporaal

Electronic Systems

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

14 Citations (Scopus)

Abstract

Genetic algorithms are commonly used for automatically solving complex design problem because exploration using genetic algorithms can consistently deliver good results when the algorithm is given a long enough run-time. However, the exploration time for problems with huge design spaces can be very long, often making exploration using a genetic algorithm practically infeasible. In this work, we present a genetic algorithm for exploring the instruction-set architecture of VLIW ASIPs and demonstrate its effectiveness by comparing it to two heuristic algorithms. We present several optimizations to the genetic algorithm configuration, and demonstrate how caching of intermediate compilation and simulation results can reduce the exploration time by an order of magnitude.

Original language	English
Title of host publication	Proceedings on the 3rd Mediterranean Conference on Embedded Computing (MECO), 15-19 June 2014, Budva, Montenegro
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	32-35
ISBN (Print)	978-1-4799-4827-7
DOIs	https://doi.org/10.1109/MECO.2014.6862720
Publication status	Published - 2014
Event	3rd Mediterranean Conference on Embedded Computing, MECO 2014 - Budva, Montenegro Duration: 15 Jun 2014 → 19 Jun 2014 Conference number: 3

Conference

Conference	3rd Mediterranean Conference on Embedded Computing, MECO 2014
Abbreviated title	MECO 2014
Country/Territory	Montenegro
City	Budva
Period	15/06/14 → 19/06/14

Access to Document

10.1109/MECO.2014.6862720

Cite this

@inproceedings{64a35e92443444e8904b115e86c26943,

title = "Instruction-set architecture exploration of VLIW aSIPs using a genetic algorithm",

abstract = "Genetic algorithms are commonly used for automatically solving complex design problem because exploration using genetic algorithms can consistently deliver good results when the algorithm is given a long enough run-time. However, the exploration time for problems with huge design spaces can be very long, often making exploration using a genetic algorithm practically infeasible. In this work, we present a genetic algorithm for exploring the instruction-set architecture of VLIW ASIPs and demonstrate its effectiveness by comparing it to two heuristic algorithms. We present several optimizations to the genetic algorithm configuration, and demonstrate how caching of intermediate compilation and simulation results can reduce the exploration time by an order of magnitude.",

author = "R. Jordans and L. Jozwiak and H. Corporaal",

year = "2014",

doi = "10.1109/MECO.2014.6862720",

language = "English",

isbn = "978-1-4799-4827-7",

pages = "32--35",

booktitle = "Proceedings on the 3rd Mediterranean Conference on Embedded Computing (MECO), 15-19 June 2014, Budva, Montenegro",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "3rd Mediterranean Conference on Embedded Computing, MECO 2014, MECO 2014 ; Conference date: 15-06-2014 Through 19-06-2014",

}

Jordans, R, Jozwiak, L & Corporaal, H 2014, Instruction-set architecture exploration of VLIW aSIPs using a genetic algorithm. in Proceedings on the 3rd Mediterranean Conference on Embedded Computing (MECO), 15-19 June 2014, Budva, Montenegro. Institute of Electrical and Electronics Engineers, Piscataway, pp. 32-35, 3rd Mediterranean Conference on Embedded Computing, MECO 2014, Budva, Montenegro, 15/06/14. https://doi.org/10.1109/MECO.2014.6862720

Instruction-set architecture exploration of VLIW aSIPs using a genetic algorithm. / Jordans, R.; Jozwiak, L.; Corporaal, H.
Proceedings on the 3rd Mediterranean Conference on Embedded Computing (MECO), 15-19 June 2014, Budva, Montenegro. Piscataway: Institute of Electrical and Electronics Engineers, 2014. p. 32-35.

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

TY - GEN

T1 - Instruction-set architecture exploration of VLIW aSIPs using a genetic algorithm

AU - Jordans, R.

AU - Jozwiak, L.

AU - Corporaal, H.

N1 - Conference code: 3

PY - 2014

Y1 - 2014

N2 - Genetic algorithms are commonly used for automatically solving complex design problem because exploration using genetic algorithms can consistently deliver good results when the algorithm is given a long enough run-time. However, the exploration time for problems with huge design spaces can be very long, often making exploration using a genetic algorithm practically infeasible. In this work, we present a genetic algorithm for exploring the instruction-set architecture of VLIW ASIPs and demonstrate its effectiveness by comparing it to two heuristic algorithms. We present several optimizations to the genetic algorithm configuration, and demonstrate how caching of intermediate compilation and simulation results can reduce the exploration time by an order of magnitude.

AB - Genetic algorithms are commonly used for automatically solving complex design problem because exploration using genetic algorithms can consistently deliver good results when the algorithm is given a long enough run-time. However, the exploration time for problems with huge design spaces can be very long, often making exploration using a genetic algorithm practically infeasible. In this work, we present a genetic algorithm for exploring the instruction-set architecture of VLIW ASIPs and demonstrate its effectiveness by comparing it to two heuristic algorithms. We present several optimizations to the genetic algorithm configuration, and demonstrate how caching of intermediate compilation and simulation results can reduce the exploration time by an order of magnitude.

U2 - 10.1109/MECO.2014.6862720

DO - 10.1109/MECO.2014.6862720

M3 - Conference contribution

SN - 978-1-4799-4827-7

SP - 32

EP - 35

BT - Proceedings on the 3rd Mediterranean Conference on Embedded Computing (MECO), 15-19 June 2014, Budva, Montenegro

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 3rd Mediterranean Conference on Embedded Computing, MECO 2014

Y2 - 15 June 2014 through 19 June 2014

ER -

Instruction-set architecture exploration of VLIW aSIPs using a genetic algorithm

Abstract

Conference

Access to Document

Fingerprint

Cite this