Route packets, not wires: on-chip inteconnection networks
Proceedings of the 38th annual Design Automation Conference
Orion: a power-performance simulator for interconnection networks
Proceedings of the 35th annual ACM/IEEE international symposium on Microarchitecture
A modular simulation framework for architectural exploration of on-chip interconnection networks
Proceedings of the 1st IEEE/ACM/IFIP international conference on Hardware/software codesign and system synthesis
Proceedings of the 1st IEEE/ACM/IFIP international conference on Hardware/software codesign and system synthesis
Cost-Performance Trade-Offs in Networks on Chip: A Simulation-Based Approach
Proceedings of the conference on Design, automation and test in Europe - Volume 2
Fast and Accurate Multiprocessor Architecture Exploration with Symbolic Programs
DATE '03 Proceedings of the conference on Design, Automation and Test in Europe - Volume 1
A Complete Network-On-Chip Emulation Framework
Proceedings of the conference on Design, Automation and Test in Europe - Volume 1
Proceedings of the conference on Design, automation and test in Europe: Designers' forum
Electronics beyond nano-scale CMOS
Proceedings of the 43rd annual Design Automation Conference
Application driven traffic modeling for NoCs
SBCCI '06 Proceedings of the 19th annual symposium on Integrated circuits and systems design
Automatic phase detection for stochastic on-chip traffic generation
CODES+ISSS '06 Proceedings of the 4th international conference on Hardware/software codesign and system synthesis
Hi-index | 0.00 |
Multi-core System-on-Chips (SoCs) with on-chip networks are becoming a reality after almost a decade of research. One challenge in developing such SoCs is the need of efficient and accurate simulators for design space exploration. This paper addresses this need by presenting SoCExplore, a framework for last communication-centric design space exploration of complex SoCs with network-based interconnects. Efficiency is achieved through abstraction of computation as a high-level trace, while accuracy is maintained through cycle-accurate interconnect simulation. The flexibility offered allows for fast partition/mapping and interconnect design space exploration. In a case study, a speed-up of 94% over architectural simulation is obtained for the MPEG application. A critical evaluation of the capabilities of our (or any trace based) framework is also provided.