ISCA '95 Proceedings of the 22nd annual international symposium on Computer architecture
Analysis and Implementation of Hybrid Switching
IEEE Transactions on Computers
Noncontiguous Processor Allocation Algorithms for Mesh-Connected Multicomputers
IEEE Transactions on Parallel and Distributed Systems
Processor Allocation in the Mesh Multiprocessors Using the Leapfrog Method
IEEE Transactions on Parallel and Distributed Systems
Evaluation of the Traffic-Performance Characteristics of System-on-Chip Communication Architectures
VLSID '01 Proceedings of the The 14th International Conference on VLSI Design (VLSID '01)
Networks on Silicon: Combining Best-Effort and Guaranteed Services
Proceedings of the conference on Design, automation and test in Europe
Principles and Practices of Interconnection Networks
Principles and Practices of Interconnection Networks
DATE '03 Proceedings of the conference on Design, Automation and Test in Europe - Volume 1
Architecture of a Dynamically Reconfigurable NoC for Adaptive Reconfigurable MPSoC
AHS '06 Proceedings of the first NASA/ESA conference on Adaptive Hardware and Systems
A fast MPI-based parallel framework for cycle-accurate HDL multi-parametric simulations
International Journal of High Performance Systems Architecture
Concurrent hybrid switching for massively parallel systems-on-chip: the CYBER architecture
Proceedings of the 9th conference on Computing Frontiers
A hybrid packet-circuit switched router for optical network on chip
Computers and Electrical Engineering
Hi-index | 0.00 |
Multi-Processor Systems-on-Chip (MPSoCs) are the most recent challenge of the VLSI technologies and Networks on Chip represent a high performance alternative to the traditional bus architectures. In this paper, a novel approach to the design of a dual-mode router, based on the idea of supporting both circuit and packet switching in a non-exclusive way, is presented and evaluated. This feature makes the proposed architecture suitable for MPSoCs which have to deal with heterogeneous traffic characteristics especially in terms of data size, such as the Massively Parallel Processors. Non-exclusivity enables packets latency reduction, which in turn implies lower task completion times, and also it increases throughput.