ABSTRACT
In the SoC, the system bus makes a bottleneck for data communication in high speed on a chip. In addition, the system allows multiple bus layers for efficient management of the bus resources on a SoC. In this paper, we present a latency model of the shared bus connecting multiple IPs. Using the latency model, we analyzed the latencies of the system bus on a SoC to get a throughput needed for the system. This result is used as a criterion for setting optimal bus architecture for a specific SoC design. We get latencies for examples MPEG and USB 2.0 using the proposed latency model and compare with the simulation result from MaxSim tools. As a result, the accuracy of the latency model for a single layer and multiple layers is over 96% and 85%, respectively.
- W.O. Cesario, D. Lyonnard G., G. Nicolescu, Y. Paviot, Sungjoo Yoo, A.A. Jerraya, L. Gauthier and M. Diaz-Nava, "Multiprocessor SoC platform: a component-based design approach", Design & Test of Computers, IEEE, vol. 19, no. 6, pp. 52--63, Dec. 2002. Google ScholarDigital Library
- K. Keutzer, A.R. Newton, J.M. Rabaey and A. Saniovanni-Vincentelli, "System-level design: orthgonalization of concerns and platform-based design", Computer-Aided Design of Integrated Circuits and Systems, IEEE, vol. 19, no. 20, pp. 1523--1543, Dec. 2002. Google ScholarDigital Library
- Li Li, Minglun Gao, Zuoren Cheng, Duoli Zhang and Shuzhuan He, "A new platform-based orthogonal SoC design methodology", ASIC, 2003 Proceedings. on 5th International Conference, vol. 1, no. 3, pp. 428--432, Oct. 2003.Google ScholarCross Ref
- Kyeong Keol Ryu, Eung Shin, V.J. Mooney, "A comparison of five different multiprocessor SoC bus architectures," in Proc. of Euromicro Symposium on Digital Systems, Design, pp. 202--209, Sept. 2001. Google ScholarDigital Library
- Wen-Tsuen Chen, Jang-Ping Sheu, "Performance analysis of multiple bus interconnection networks with hierarchical requesting model," IEEE Trans. on Computers, vol. 40, no. 7, pp. 834--842, Jul. 1991. Google ScholarDigital Library
- Qing Yang, Laxmi N.Bhuyan, "Analysis of packet-switched multiple-bus multiprocessor system," IEEE Trans. On Computers, vol. 45, no.5, pp. 580--588, May. 1996. Google ScholarDigital Library
- John L.K.,Yu-cheng Liu, "Performance model for a prioritized multiple-bus multiprocessor system," IEEE Trans. On Computers, vol. 45, no.5, pp.580--588, May. 1996. Google ScholarDigital Library
- C.A.Jeferino, M.E.Kreutz, L.Carro and A.A.Susin, "A study on communication issue forsystems-on-chip" in Proc. Of 15th Symposium on Integrated Circuits and Systems Design, pp.121--126, Sept.2002. Google ScholarDigital Library
- AMBA specification Rev2.0, ARM co., May 1999.Google Scholar
- S. Okada, N. Takada, H. Miura and T. Asaeda, " System-on-a-chip for digital still camera with VGA-size clip shooting", Consumer Electronics, IEEE, vol. 46, no. 3, pp. 622--627, Aug. 2000. Google ScholarDigital Library
- MaxSim developer suite user's guide Ver 5.0, AXYS Design Automation Inc., Mar. 2004.Google Scholar
- C.A. Jeferino, M.E. Kreutz, L. Carro and A. A. Susin, "A study on communication issues for systems-on-chip" in Proc. Of 15th Symposium on Integrated Circuits and Systems Design, pp.121--126, Sept. 2002. Google ScholarDigital Library
- Furber. S, "Future Trends in SoC Interconnect". 2005 IEEE International Symposium on VLSI Design, Automation and Test, 2005. (VLSI-TSA-DAT). pp. 295--298, April 2005.Google Scholar
- Sang Hun Lee, Chan Ho Lee, Hyuk Jae Lee, "A New multi-channel on-chip-bus architecture for system-on-chips" Proc. of IEEE International SOC Conference, pp.305--308, Sept. 2004.Google Scholar
Index Terms
- Modeling and analysis of the system bus latency on the SoC platform
Recommendations
Automated bus generation for multiprocessor SoC design
The performance of a multiprocessor system heavily depends upon the efficiency of its bus architecture. This paper presents a methodology to generate a custom bus system for a multiprocessor system-on-a-chip (SoC). Our bus-synthesis tool, which we call ...
Self-timed communication platform for implementing high-performance systems-on-chip
Special issue: Networks on chip and reconfigurable fabricsThis paper discusses design of a modular self-timed communication platform aimed for high-performance globally asynchronous locally synchronous system-on-chip applications. The platform is based on a concurrent multitopology bus architecture with ...
Design and implementation of Performance Analysis Unit (PAU) for AXI-based multi-core System on Chip (SOC)
With the rapid development of semiconductor technology, more complicated systems have been integrated into single chips. However, system performance is not increased in proportion to the gate-count of the system. This is mainly because the optimized ...
Comments