SAGA: Synthesis technique for guaranteed throughput NoC architectures

Krishnan Srinivasan, Karam S. Chatha

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

We present SAGA, a novel genetic algorithm (GA) based technique for synthesis of custom NoC architectures that support guaranteed throughput traffic. The technique accepts as input a communication trace graph, amount of data, period, and deadline for each trace, interconnection network architecture elements, and generates a custom NoC topology, and routing and schedule of the communication traces on the architecture. SAGA minimizes both the energy consumption and area of the design by solving a multi-objective optimization problem. We present a detailed analysis of the quality of the results and the solution times of the proposed technique by extensive experimentation with realistic benchmarks and comparisons with optimal MILP solutions. SAGA is able to generate solutions that are as good as the optimal solutions produced by the MILP formulation. Whereas the MILP formulation run time rises exponentially for even moderately sized graphs, SAGA generates solutions for large graphs in reasonable time.

Original languageEnglish (US)
Title of host publicationProceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC
Pages489-494
Number of pages6
Volume1
StatePublished - 2005
Event2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005 - Shanghai, China
Duration: Jan 18 2005Jan 21 2005

Other

Other2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005
CountryChina
CityShanghai
Period1/18/051/21/05

Fingerprint

Throughput
Communication
Multiobjective optimization
Network architecture
Energy utilization
Genetic algorithms
Topology
Network-on-chip

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Cite this

Srinivasan, K., & Chatha, K. S. (2005). SAGA: Synthesis technique for guaranteed throughput NoC architectures. In Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC (Vol. 1, pp. 489-494). [1466212]

SAGA : Synthesis technique for guaranteed throughput NoC architectures. / Srinivasan, Krishnan; Chatha, Karam S.

Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. Vol. 1 2005. p. 489-494 1466212.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Srinivasan, K & Chatha, KS 2005, SAGA: Synthesis technique for guaranteed throughput NoC architectures. in Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. vol. 1, 1466212, pp. 489-494, 2005 Asia and South Pacific Design Automation Conference, ASP-DAC 2005, Shanghai, China, 1/18/05.
Srinivasan K, Chatha KS. SAGA: Synthesis technique for guaranteed throughput NoC architectures. In Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. Vol. 1. 2005. p. 489-494. 1466212
Srinivasan, Krishnan ; Chatha, Karam S. / SAGA : Synthesis technique for guaranteed throughput NoC architectures. Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC. Vol. 1 2005. pp. 489-494
@inproceedings{d18982d00b28438dbeebaf8562596260,
title = "SAGA: Synthesis technique for guaranteed throughput NoC architectures",
abstract = "We present SAGA, a novel genetic algorithm (GA) based technique for synthesis of custom NoC architectures that support guaranteed throughput traffic. The technique accepts as input a communication trace graph, amount of data, period, and deadline for each trace, interconnection network architecture elements, and generates a custom NoC topology, and routing and schedule of the communication traces on the architecture. SAGA minimizes both the energy consumption and area of the design by solving a multi-objective optimization problem. We present a detailed analysis of the quality of the results and the solution times of the proposed technique by extensive experimentation with realistic benchmarks and comparisons with optimal MILP solutions. SAGA is able to generate solutions that are as good as the optimal solutions produced by the MILP formulation. Whereas the MILP formulation run time rises exponentially for even moderately sized graphs, SAGA generates solutions for large graphs in reasonable time.",
author = "Krishnan Srinivasan and Chatha, {Karam S.}",
year = "2005",
language = "English (US)",
isbn = "0780387368",
volume = "1",
pages = "489--494",
booktitle = "Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC",

}

TY - GEN

T1 - SAGA

T2 - Synthesis technique for guaranteed throughput NoC architectures

AU - Srinivasan, Krishnan

AU - Chatha, Karam S.

PY - 2005

Y1 - 2005

N2 - We present SAGA, a novel genetic algorithm (GA) based technique for synthesis of custom NoC architectures that support guaranteed throughput traffic. The technique accepts as input a communication trace graph, amount of data, period, and deadline for each trace, interconnection network architecture elements, and generates a custom NoC topology, and routing and schedule of the communication traces on the architecture. SAGA minimizes both the energy consumption and area of the design by solving a multi-objective optimization problem. We present a detailed analysis of the quality of the results and the solution times of the proposed technique by extensive experimentation with realistic benchmarks and comparisons with optimal MILP solutions. SAGA is able to generate solutions that are as good as the optimal solutions produced by the MILP formulation. Whereas the MILP formulation run time rises exponentially for even moderately sized graphs, SAGA generates solutions for large graphs in reasonable time.

AB - We present SAGA, a novel genetic algorithm (GA) based technique for synthesis of custom NoC architectures that support guaranteed throughput traffic. The technique accepts as input a communication trace graph, amount of data, period, and deadline for each trace, interconnection network architecture elements, and generates a custom NoC topology, and routing and schedule of the communication traces on the architecture. SAGA minimizes both the energy consumption and area of the design by solving a multi-objective optimization problem. We present a detailed analysis of the quality of the results and the solution times of the proposed technique by extensive experimentation with realistic benchmarks and comparisons with optimal MILP solutions. SAGA is able to generate solutions that are as good as the optimal solutions produced by the MILP formulation. Whereas the MILP formulation run time rises exponentially for even moderately sized graphs, SAGA generates solutions for large graphs in reasonable time.

UR - http://www.scopus.com/inward/record.url?scp=84861451458&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861451458&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84861451458

SN - 0780387368

SN - 9780780387362

VL - 1

SP - 489

EP - 494

BT - Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC

ER -