[1]卢俊,颜哲,田泽. 一种高效GPU存储系统体系架构设计[J].计算机技术与发展,2015,25(04):6-9.
 LU Jun,YAN Zhe,TIAN Ze. An Efficient Memory System Structure Design of GPU[J].,2015,25(04):6-9.
点击复制

 一种高效GPU存储系统体系架构设计()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
25
期数:
2015年04期
页码:
6-9
栏目:
智能、算法、系统工程
出版日期:
2015-04-10

文章信息/Info

Title:
 An Efficient Memory System Structure Design of GPU
文章编号:
1673-629X(2015)04-0006-04
作者:
 卢俊颜哲田泽
 中国航空计算技术研究所
Author(s):
 LU JunYAN ZheTIAN Ze
关键词:
 图形处理系统层次化存储带宽存储管理模块
Keywords:
 graphic processing systemmemory hierarchybandwidthMMU
分类号:
TP31
文献标志码:
A
摘要:
 图形处理技术被广泛应用于电影、视频、游戏以及动画的制作,而图形处理系统( GPU)的出现极大地减轻了CPU日益繁重的图形处理任务,使得其能更专注于通用控制。文中阐述了制约GPU性能提升的重要因素,指出提高带宽利用率是应对这一问题的关键措施。通过局部性原理的分析,提出了一种基于层次化架构的高效GPU存储系统的设计。文中介绍了4层结构的存储系统,并逐层说明了各自的功能和架构,评估了基于层次化存储架构的GPU在典型应用中的带宽。文中还描述了Cache以及显存管理等子模块的功能。通过仿真可知,该GPU存储系统能充分利用共享和复用等手段尽量减少外部存储器的访问次数,从而提高了带宽利用率。
Abstract:
 Graphic processing technique has been widely used in movie,video,game and cartoon making. GPU has greatly reduced the pressure of graphic processing,which was CPU’ s job in the past. It introduces the key factor which limits improvement of GPU perform-ance,and also indicates that the bandwidth utilization is one of the critical resources to deal with that limits. According to analysis of prin-ciple of locality,attempt to explore an efficient GPU memory system based on layered architecture. This global memory hierarchy struc-ture has four layers of memory,and the function of each layer has been described. In this paper,present the bandwidth utilization ratio of typical GPU running scenarios,also introduce the architecture of the modules such as Cache and MMU. This GPU memory system can re-duce the frequency of accessing SDRAM by sharing cache on chip,so that the utilization ratio of bandwidth has been greatly improved.

相似文献/References:

[1]张志宏,吴庆波,邵立松,等.基于飞腾平台TOE协议栈的设计与实现[J].计算机技术与发展,2014,24(07):1.
 ZHANG Zhi-hong,WU Qing-bo,SHAO Li-song,et al. Design and Implementation of TCP/IP Offload Engine Protocol Stack Based on FT Platform[J].,2014,24(04):1.
[2]梁文快,李毅. 改进的基因表达算法对航班优化排序问题研究[J].计算机技术与发展,2014,24(07):5.
 LIANG Wen-kuai,LI Yi. Research on Optimization of Flight Scheduling Problem Based on Improved Gene Expression Algorithm[J].,2014,24(04):5.
[3]黄静,王枫,谢志新,等. EAST文档管理系统的设计与实现[J].计算机技术与发展,2014,24(07):13.
 HUANG Jing,WANG Feng,XIE Zhi-xin,et al. Design and Implementation of EAST Document Management System[J].,2014,24(04):13.
[4]侯善江[],张代远[][][]. 基于样条权函数神经网络P2P流量识别方法[J].计算机技术与发展,2014,24(07):21.
 HOU Shan-jiang[],ZHANG Dai-yuan[][][]. P2P Traffic Identification Based on Spline Weight Function Neural Network[J].,2014,24(04):21.
[5]李璨,耿国华,李康,等. 一种基于三维模型的文物碎片线图生成方法[J].计算机技术与发展,2014,24(07):25.
 LI Can,GENG Guo-hua,LI Kang,et al. A Method of Obtaining Cultural Debris’ s Line Chart Based on Three-dimensional Model[J].,2014,24(04):25.
[6]翁鹤,皮德常. 混沌RBF神经网络异常检测算法[J].计算机技术与发展,2014,24(07):29.
 WENG He,PI De-chang. Chaotic RBF Neural Network Anomaly Detection Algorithm[J].,2014,24(04):29.
[7]刘茜[],荆晓远[],李文倩[],等. 基于流形学习的正交稀疏保留投影[J].计算机技术与发展,2014,24(07):34.
 LIU Qian[],JING Xiao-yuan[,LI Wen-qian[],et al. Orthogonal Sparsity Preserving Projections Based on Manifold Learning[J].,2014,24(04):34.
[8]尚福华,李想,巩淼. 基于模糊框架-产生式知识表示及推理研究[J].计算机技术与发展,2014,24(07):38.
 SHANG Fu-hua,LI Xiang,GONG Miao. Research on Knowledge Representation and Inference Based on Fuzzy Framework-production[J].,2014,24(04):38.
[9]叶偲,李良福,肖樟树. 一种去除运动目标重影的图像镶嵌方法研究[J].计算机技术与发展,2014,24(07):43.
 YE Si,LI Liang-fu,XIAO Zhang-shu. Research of an Image Mosaic Method for Removing Ghost of Moving Targets[J].,2014,24(04):43.
[10]余松平[][],蔡志平[],吴建进[],等. GSM-R信令监测选择录音系统设计与实现[J].计算机技术与发展,2014,24(07):47.
 YU Song-ping[][],CAI Zhi-ping[] WU Jian-jin[],GU Feng-zhi[]. Design and Implementation of an Optional Voice Recording System Based on GSM-R Signaling Monitoring[J].,2014,24(04):47.
[11]马超[][],王婷[][],田泽[][],等. 图形处理系统中主机接口设计及应用[J].计算机技术与发展,2016,26(05):125.
 MA Chao[][],WANG Ting[][],TIAN Ze[][],et al. Design and Application of Host Interface in Graphic Processing System[J].,2016,26(04):125.

更新日期/Last Update: 2015-06-02