一种面向应用优化的片上总线调度策略

李德贤; 彭剑英; 严晓浪

doi:10.3724/SP.J.1146.2008.00166

一种面向应用优化的片上总线调度策略

doi: 10.3724/SP.J.1146.2008.00166

基金项目:

国家863计划项目(2005AA1Z1271)资助课题

计量
- 文章访问数: 3251
- HTML全文浏览量: 112
- PDF下载量: 649
- 被引次数: 0
出版历程
- 收稿日期: 2008-01-30
- 修回日期: 2008-07-14
- 刊出日期: 2009-05-19

An Optimized Bus Scheduling Scheme Based on Specific Application

摘要

摘要: 该文提出了一种面向应用优化的片上总线调度策略。以系统通信事件信息为基础，使用最小任务松弛时间与最小总线空闲时间相结合的调度策略，在优先保证满足任务实时要求的基础上，最大限度利用总线空闲时间，提高调度效率。并提供了可配置的权重参数用于总线时间消耗与片上缓冲区容量之间的设计折衷。在双核SoC平台上实现了本文调度方法，并以最新视频编解码标准H.264/AVC为目标应用，与FP(Fixed Priority)，SBA(Slack Based Arbitration)，RR(Round Robin)等调度方法进行了性能对比。实验结果表明，=0.5时，较以上3种策略，分别平均可减少16.6％、13.2％与9.7％的总线时间，在实时性能方面，较最接近的SBA方法，未实时完成的任务数量减少了59.4％。额外缓冲区开销随的变化关系表明，在最坏情况下(=0)仅需435字节。
- 片上系统;通信建模;总线调度
Abstract: An application-specific bus scheduling scheme was proposed in this paper. Two-fold optimization was considered in this scheme based on the communication events collected by system modeling and simulation. The first one, which had higher priority, was real time constraints of tasks while the other was making use of bus idle time to transfer data as much as possible. A configurable optimization parameter was also proposed for the tradeoff between the total bus time consumed and the extra on-chip buffer requirements. This scheme was implemented in a dual-core SoC (System on Chip) for the H.264/AVC decoder and compared with RR (Round Robin), FP (Fixed Priority) and SBA (Slack Based Arbitration) schemes. The results showed that the proposed scheme had an average 16.6%, 13.2% and 9.7% less bus time when was set to 0.5. The number of missed real time constraints tasks was 59.4% less than the SBA scheme, which was the closest to our scheme. The relationship between and the extra on-chip buffer cost showed that under worst condition (=0), it was only 435 bytes.

HTML全文

参考文献(1)

Kreutz M and Carro L, et al.. Communication architecturesfor system-on-chip[C]. 14th symposium on integratedCircuits and Systems Design Pirenopolis, Brazil, Sep. 10-15,2001: 14-19.[2]Meyerowitz T, Pinello C, and Vincentelli A. A tool fordescribing and evaluating hierarchical real-time busscheduling policies[C]. Design Automation Conference,Anaheim, California, USA, Jun. 8-13, 2003: 256-261.[3]Pasricha S, Dutt N, and Ben-Romdhane M. Extending thetransaction level modeling approach for fast communicationarchitecture exploration[C]. International Conference onHardware/Software Codesign and System Synthesis,Stockholm, Sweden, Sep. 8-10, 2004: 242-247.[4]陈科明, 刘鹏, 王维东, 姚庆栋. 用于多处理器媒体SoC设计的实时总线调度优化策略[J]. 浙江大学学报(工学版), 2007,41(9): 1546-1551.Chen Ke-ming, Liu Peng, Wang Wei-dong, and YaoQing-dong. Scheme to optimize real-time bus scheduling inmultiprocessor SoC for media processing[J]. Journal ofZhejiang University (Engineering Science), 2007, 41(9):1546-1551.[5]Jun M, Bang K, and Lee H, et al.. Slack-based bus arbitrationscheme for soft real-time constrained embedded systems[C].Asia and South Pacific Design Automation Conference,Yokohame, Japan, Jan. 23-26, 2007: 159-164.[6][6] ISO/IEC 14496-10, ITU-T Rec, H.264, joint videospecification [S]. 2002.[7]Cai L and Gajski D. Transaction level modeling: Anoverview[C]. International Conference on Hardware/Software Codesign and System Synthesis, Newport Beach,CA, USA, Oct.1-3, 2003: 19-24.[8]Salami E and Valero M. A Vector-uSIMD-VLIWArchitecture for Multimedia Applications[C]. InternationalConference on Parallel Processing, Oslo, Norway, Jun.14-17,2005: 69-77.[9]Pimentel A and Erbas C. An IDF-based trace transformationmethod for communication refinement[C]. DesignAutomation Conference, Anaheim, California, USA, Jun.8-13, 2003: 402-407.[10]Yang Ye, Yang Jian, and Qin Xing, et al.. GEM-SOC: ARISC/DSP dual-core platform for portable mediaapplications[C]. International Conference on Solid-State andIntegrated Circuit Technology, Shanghai, China. Oct.23-26,2006, 1797-1799.[11]Liu Kunjie, Qin, Xing, and Yan Xiaolang, et al.. A SIMDvideo signal processor with efficient data organization[C].IEEE Asian Solid-State Circuits Conference, Hangzhou,Nov.13-15, 2006: 115-118.[12]Sima M, Zhou Yuanhua, and Zhang Wei. An efficientarchitecture for adaptive deblocking filter of H264/AVCvideo coding[J].. IEEE Trans. on Consumer Electronics.2004,50(1):292-296

施引文献

资源附件(0)

访问统计