SoC Network Architecture for Efficient Multi-Channel On-Chip-Bus

효율적인 다중 채널 On-Chip-Bus를 위한 SoC Network Architecture

  • Lee Sanghun (Dept. of Electronic Engr., Soongsil University) ;
  • Lee Chanho (School of Electronic Engr., Soongsil University) ;
  • Lee Hyuk-Jae (School of Electrical Engr., Seoul National University)
  • 이상헌 (숭실대학교 전자공학과) ;
  • 이찬호 (숭실대학교 정보통신전자공학부) ;
  • 이혁재 (서울대학교 전기공학부)
  • Published : 2005.02.01

Abstract

We can integrate more IP blocks on a silicon die as the development of fabrication technologies and EDA tools. Consequently, we can design complicated SoC architecture including multi-processors. However, most of existing SoC buses have bottleneck in on-chip communication because of shared bus architectures, which result in the performance degradation of systems. In most cases, the performance of a multi-processor system is determined by efficient on-chip communication and the well-balanced distribution of computation rather than the performance of the processors. We propose an efficient SoC Network Architecture(SNA) using crossbar routers which provide a solution to ensure enough communication bandwidth. The SNA can significantly reduce the bottleneck of on-chip communication by providing multi-channels for multi-masters. According to the proposed architecture, we design a model system for the SNA. The proposed architecture has a better efficiency by $40\%$ than the AMBA AHB according to a simulation result.

공정기술과 EDA 툴의 발전에 따라서 하나의 실리콘 다이(Die)에 많은 IP가 집적되고 멀티프로세서가 포함되는 SoC 구조가 가능해지고 있다 그러나 대부분의 기존 SoC 버스는 공유버스 구조라는 문제점으로 인해 통신의 병목현상이 발생하고 이는 전체 시스템 성능을 저하시키는 요인이 된다. 많은 경우에 멀티프로세서 시스템의 성능은 CPU 자체의 속도보다는 효율적인 통신과 균형있는 연산의 분배가 좌우하게 된다 따라서 충분한 SoC 버스 대역폭(Bandwidth)을 확보하기 위한 하나의 해결책으로 크로스바 라우터(Crossbar Router)를 이용하여 효율적인 온 칩 버스구조인 SoC Network Architecture(SNA)를 제안한다. 제안된 SNA구조는 다중 마스터(multi-master)에 대해 다중 채널(multi-channel)을 제공하여 통신의 병목현상을 크게 줄일 수 있으며 뛰어난 확장성을 지원한다. 제안된 구조에 따라 모델 시스템을 설계하고 시뮬레이션을 진행한 결과 AMBA AHB 버스에 비해 평균 $40\%$ 이상 효율이 증가했다.

Keywords

References

  1. Inside the New Computer Industry, issue 138, Jan 2001
  2. F. MORAES, N. CALAZANS, et al., 'HERMES: an Infrastructure for Low Area Overhead Packet-switching Networks on Chip', Integration, the VLSI Journal (accepted for publication) https://doi.org/10.1016/j.vlsi.2004.03.003
  3. P. Gurrier, A. Greiner, 'A Generic Architecture for On-Chip Packet-Switched Interconnections', Proceedings of the conference on Design, Automation and Test in Europe, Paris, France, pp. 250 - 256, 2000 https://doi.org/10.1145/343647.343776
  4. ARM, 'AMBA Specification, Revision 2.0', 1999
  5. W. Peterson, 'WISHBONE SoC Architecture Specification, Revision B.2', Silicore Corporation, 2001
  6. IBM, 'CoreConnect Bus Architecture', 1999
  7. Jaesung Lee, Hyuk-Jae Lee, and Chanho Lee, 'SNP: A New Communication Protocol for SoC',in Int'l Conf. on Communications, Circuits and Systems, June 2004
  8. Hatro Products OY, 'http://www.hantro.com/pdf/overview.pdf'
  9. Marescaux, T.; Bartic, A.; Verkest, D.; Vernalde, S.; Lauwereins, R. 'Interconnection Networks Enable Fine -Grain Dynamic Multi-Tasking on FPGAs', In: Field-Programmable Logic and Applications (FPL'02), pp. 795-805, Sep. 2002
  10. Moraes, F., Mello, A., M?ller, L., Ost, L., Calazans, N., 'A Low Area Overhead Packet -switched Network on Chip: Architecture and Prototyping', IFIP Very Large Scale Integration (VLSI-SOC). pp. 318-323, Dec. 2003