[1]刘波,肖建,曹鹏,等.面向媒体处理可重构系统中数据缓存结构和缓存管理策略优化[J].东南大学学报(自然科学版),2014,44(6):1149-1154.[doi:10.3969/j.issn.1001-0505.2014.06.010]
 Liu Bo,Xiao Jian,Cao Peng,et al.Data cache structure and management strategy optimization of reconfigurable system for multimedia applications[J].Journal of Southeast University (Natural Science Edition),2014,44(6):1149-1154.[doi:10.3969/j.issn.1001-0505.2014.06.010]
点击复制

面向媒体处理可重构系统中数据缓存结构和缓存管理策略优化()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
44
期数:
2014年第6期
页码:
1149-1154
栏目:
电子科学与工程
出版日期:
2014-11-20

文章信息/Info

Title:
Data cache structure and management strategy optimization of reconfigurable system for multimedia applications
作者:
刘波肖建曹鹏杨苗苗
东南大学国家专用集成电路系统工程技术研究中心, 南京 210096
Author(s):
Liu Bo Xiao Jian Cao Peng Yang Miaomiao
National ASIC System Engineering Research Center, Southeast University, Nanjing 210096, China
关键词:
可重构系统 数据缓存结构 缓存管理策略
Keywords:
reconfigurable system data cache structure cache management strategy
分类号:
TN302
DOI:
10.3969/j.issn.1001-0505.2014.06.010
摘要:
研究并提出了一种基于二维访问机制的数据缓存结构(2D Cache)及其更新管理策略.该缓存结构可以在控制硬件存储开销的同时,有效提升可重构系统的数据访存效率.实验结果表明,仅需4KB的数据缓存开销,可重构系统的访存性能提升了29.16%~35.65%,并且对于不同标准的媒体处理算法都能获得较好的优化效果,具有很好的适应性.芯片实测结果表明,采用所述数据缓存设计方案的可重构系统可以在200MHz下满足1080p@30fps的实时解码需求,与国际同类架构相比,性能提高了1.8倍以上.
Abstract:
In order to improve the data flow of the reconfigurable system with a lower embedded data memory cost, a data cache optimization method is proposed, including the two-dimensional Cache structure and the related cache management strategy. The experimental results show that the approach is efficient for various multimedia applications, and the memory access performance of the reconfigurable system can be improved by 29.16% to 35.65% with a 4 KB data cache. The proposed data cache structure was adopted in a reconfigurable system and realized with real chip. Based on the the proposed data cache structures, the reconfigurable system can support the 1080p@30fps stream decoding at the clock frequency of 200MHz. Moreover, the performance of the reconfigurable system is 1.8 times higher than that of other reconfigurable architectures.

参考文献/References:

[1] Cervero T, Lopez S,Callico G M, et al. Survey of reconfigurable architectures for multimedia applications[C]//VLSI Circuits and Systems IV. Dresden, Germany, 2009,736303-01-736303-12.
[2] Chuang T D, Chang L M, Chiu T W, et al. Bandwidth-efficient cache-based motion compensation architecture with dram-friendly data access control[C]//IEEE International Conference on Acoustics, Speech, and Signal Processing. Taipei, China, 2009: 2009-2012.
[3] Chuang T D, Tsung P K, Lin P C, et al. A 59.5mW scalable/multi-view video decoder chip for quad/3D full HDTV and video streaming applications[C]//2010 IEEE International Solid-State Circuits Conference. San Francisco, CA, USA, 2010: 330-331.
[4] Chang Y N, Tong T C. An efficient design of H.264 interpolator with bandwidth optimization[J]. Signal Processing Systems, 2008, 53(3): 435-448.
[5] Tsai C Y, Chen T C, Chen T W, et al. Bandwidth optimized motion compensation hardware design for H. 264/AVC HDTV decoder[C]//48th Midwest Symposium on Circuits and Systems. Covington, KY, USA, 2005: 1199-1202.
[6] Chien Chih-Da, Lin Chien-Chang, Shih Yi-Hung,et al. A 252kgate/71mW multi-standard multi-channel video decoder for high definition video applicatioins[C]//ISSCC Dig Tech Papers. San Francisco, CA, USA, 2007: 282-283.
[7] Cucchiara Rita, Piccardi Massimo, Prati Andrea. Exploiting cache in multimedia[C]//IEEE Conference on Multimedia Computing and Systems. Florence, Italy, 1999, 1: 345-350.
[8] Zatt B,de L Silva L M,Azevedo A,et al.A reduced memory bandwidth and high throughput HDTV motion compensation decoder for H.264/AVC high 4∶2∶2 profile[J].Journal of Real-Time Image Processing,2013, 8(1): 127-140.
[9] Whitty S, Ernst R. A bandwidth optimized SDRAM controller for the MORPHEUS reconfigurable architecture[C]//IEEE International Symposium on Parallel and Distributed Processing. Miami, FL, USA, 2008: 1-8.
[10] Probell J. Architecture considerations for multi-format programmable video processors[J]. Journal of Signal Processing Systems, 2008, 50(1):33-39.
[11] Wiegand T. Draft ITU-T recommendation and final draft international standard of joint video specification[J].ITU-T rec. H.264 |ISO/IEC 14496-10 AVC, 2003, 26(2):167-184.
[12] ITU-T. ISO/IEC-13818 Generic coding of moving pictures and associated audio(MPEG-2)[J]. Journal of the Audio Engineering Society(AES), 1994, 42(10):780-792.
[13] Ganesan M K A, Singh S, May F, et al. H. 264 decoder at HD resolution on a coarse grain dynamically reconfigurable architecture[C]//International Conference on Field Programmable Logic and Applications. Amsterdam, Netherlands, 2007: 467-471.
[14] Mei B, de Sutter B, Vander Aa T, et al. Implementation of a coarse-grained reconfigurable media processor for AVC decoder[J].Journal of Signal Processing Systems, 2008, 51(3): 225-243.

备注/Memo

备注/Memo:
收稿日期: 2014-07-16.
作者简介: 刘波(1984—),男,博士,讲师,liubo_cnasic@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(61404028, 61204023)、国家高技术研究发展计划(863计划)资助项目(2012AA012703).
引用本文: 刘波,肖建,曹鹏,等.面向媒体处理可重构系统中数据缓存结构和缓存管理策略优化[J].东南大学学报:自然科学版,2014,44(6):1149-1154. [doi:10.3969/j.issn.1001-0505.2014.06.010]
更新日期/Last Update: 2014-11-20