Thesis
Performance evaluation of fault tolerant methodologies for network on chip architecture
Washington State University
Master of Science (MS), Washington State University
2007
Handle:
https://hdl.handle.net/2376/100785
Abstract
Current SoC designs are appearing with very large numbers of embedded processors. From consumer multimedia to image processing to defense applications, new designs are coming out with very high numbers of embedded processors. The communication requirements of these large MP-SoCs are convened by the emerging network-on-a-chip (NoC) paradigm. In the deep sub-micron (DSM) VLSI processes, it is difficult to guarantee correct fabrication with an acceptable system performance and chip yield without employing design techniques that take into account the intrinsic existence of manufacturing faults. To become a viable alternative IC design methodology the NoC paradigm must address the system-level reliability issues, which is going to be the dominant concern in the DSM and beyond silicon era. By incorporating fault tolerant methodologies in the data communication mechanism it is possible to tolerate permanent manufacturing faults in the NoC interconnect architectures. Performance of two different NoC architectures, namely Mesh and Butterfly Fat Tree (BFT) are explored by incorporating the partially adaptive routing algorithms and spare hardware block respectively. The performance tradeoffs associated with fault tolerant schemes in NoC fabrics, like network throughput, latency, silicon area overhead and power consumption are explored. With the help of fault tolerant mechanisms, the chip yield can be improved because of higher sustained throughput in presence of faults.
Metrics
2 File views/ downloads
8 Record Views
Details
- Title
- Performance evaluation of fault tolerant methodologies for network on chip architecture
- Creators
- Haibo Zhu
- Contributors
- Partha Pratim Pande (Degree Supervisor)
- Awarding Institution
- Washington State University
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University; Pullman, Wash. :
- Identifiers
- 99900525181801842
- Language
- English
- Resource Type
- Thesis