[1]凌明,武建平,柳琦,等.面向国产Unicore架构的Android图形系统优化[J].东南大学学报(自然科学版),2012,42(6):1069-1073.[doi:10.3969/j.issn.1001-0505.2012.06.009]
 Ling Ming,Wu Jianping,Liu Qi,et al.Optimization for Android graphics system based on domestic Unicore architecture[J].Journal of Southeast University (Natural Science Edition),2012,42(6):1069-1073.[doi:10.3969/j.issn.1001-0505.2012.06.009]
点击复制

面向国产Unicore架构的Android图形系统优化()
分享到:

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

卷:
42
期数:
2012年第6期
页码:
1069-1073
栏目:
电子科学与工程
出版日期:
2012-11-20

文章信息/Info

Title:
Optimization for Android graphics system based on domestic Unicore architecture
作者:
凌明1 武建平1 柳琦2 杨晓东1 张阳1
1 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; 2 中国飞行试验研究院测试所,西安710089
Author(s):
Ling Ming1 Wu Jianping1 Liu Qi2 Yang Xiaodong1 Zhang Yang1
1 National ASIC System Engineering Research Center, Southeast University, Nanjing 210096, China
2 Measurement Depontment, Chinese Flight Test Establishment, Xi’an 710089,China
关键词:
Android图形系统 Unicore 硬件加速 GPU
Keywords:
Android graphics system Unicore hardware acceleration graphic processing unit(GPU)
分类号:
TN302
DOI:
10.3969/j.issn.1001-0505.2012.06.009
摘要:
采用基于国产Unicore内核的嵌入式处理器平台,进行了Android系统移植.首先,移植实现了本地框架层的物理内存模块(PMEM)、图形显示内存分配模块(Gralloc)、块拷贝模块(Copybit)和图形处理单元驱动(GPU驱动)模块.然后,通过分析传统GPU(graphic processing unit)驱动调用过程中Linux内核态与用户态的数据交互方式,提出了一种新的访存机制,增加了Skia库到GPU驱动的访问路径,使内核态可以直接访问用户态数据,克服了传统模式中必须将用户态数据拷贝到内核态才能被内核态访问的弊端,降低了访存开销.最后,对Skia图形库的热点函数进行了优化.实验结果表明:与GPU驱动优化前相比,优化后的图形绘制性能平均加速3.08倍; Skia图形库中矩形搬运函数的运行时长缩短至原来的1/9; 相比于无GPU的情况,GPU驱动优化后的图形绘制性能平均提升7.46倍.
Abstract:
Based on the embedded processor platform of the domestic Unicore, the Android system is transplanted. Firstly, four critical function modules, PMEM(physical memory), Gralloc, Copybit and GPU(graphic processing unit)driver, in the local frame of Android graphics system, are designed and implemented. Then, the data interaction process between the Linux kernel and the user mode in the GPU driver is analyzed and a novel memory access mechanism is put forward. A memory access path from Skia lib to GPU driver is introduced, and the kernel mode can directly access user data, avoiding the drawbacks of copying data from the user mode to the kernel mode in the traditional mode and reducing the memory access overhead. Finally, the hotspot functions in Skia lib are optimized. The experimental results show that after optimization the graphics rendering performance can obtain 3.08 times speedup on average, and the execution time of rectangle transporting function is compressed to 1/9 of that before optimization for Skia lib. The graphics rendering performance of the systems with optimized GPU driver is accelerated by 7.46 times on average than that of the systems without GPU.

参考文献/References:

[1] Wikipedia. Mobile operating system [EB/OL].(2010-12-02)[2011-12-12].http://en.wikipedia.org/wiki/Mobile_operating _system.
[2] Wikipedia. Android(operating system)[EB/OL].(2010-12-05)[2012-01-10].http://en.wikipedia.org/wiki/Android(operating_system).
[3] Kosmach J,Neff R,Sherwood G,et al.Introduction to the OpenCORE audio components used in the android platform[C] //Proceedings of 34th International Conference of New Trends in Audio for Mobile and Handheld Devices. Jeju,Korea,2008:23-25.
[4] Cheung T L,Okamoto K,Maker I F,et al.Markov decision process(MDP)framework for optimizing software on mobile phones[C] //Proceedings of the 7th ACM International Conference on Embedded Software. Grenoble,France,2009:11-20.
[5] Ughetti M,Turin T T,Gotta D.Development of agent-based,peer-to-peer mobile applications on ANDROID with JADE[C] //Proceedings of the Second International Conference on Mobile Ubiquitous Computing,Systems,Services and Technologies.Valencia,Spain,2008:287-294.
[6] 常乐. PKUnity-3(SK)系统芯片二维图形加速器的功能验证与性能评测[D].北京:北京大学信息科学技术学院,2009.
[7] 蒋永刚, 戚正伟,彭娟春,等.PXA300平台2D图形加速器性能测试与分析[J].计算机应用与软件,2010,27(5):86-88.
  Jiang Yonggang,Qi Zhengwei,Peng Juanchun,et al.Performance test and analysis for 2D graphic accelerator on PXA300 platform[J].Journal of Computer Applications and Software, 2010,27(5):86-88.(in Chinese)
[8] Mark Murphy.Beginning Android [M].New York:Apress,2009:93-97.
[9] 北大众志微系统科技有限责任公司.Unicore系统结构手册[EB/OL].(2001-05-10)[2011-11-25].http://www.pkunity.com/863-2.asp.
[10] 搏芯电子技术有限公司.SEP6200设计文档 [EB/OL].(2010-12-11)[2012-01-14].http://www.prochip.com.cn/product_show.asp?detailid=27.
[11] Pulli K,Aarnio T,Roimela K,et al.Designing graphics programming interfaces for mobile devices [J].Journal of IEEE Computer Graphics and Applications, 2005,25(6):66-75.
[12] Sergio M,Alexandru T.Visualizing dynamic memory allocations [C] //Proceedings of the 4th IEEE International Workshop on Visualizing Software for Understanding and Analysis. Banff,Canada,2007:31-38.
[13] DirectFB Constitution.DirectFB Roadmap[EB/OL].(2011-09-26)[2012-01-20].http://www.directfb.org/.
[14] Bin Z.Xbench:a benchmark evaluating the performance of graphic display system in virtual machines[C] //Proceeding of the 5th International Conference on Computer Science and Education. Hefei,China,2010:1730-1734.

相似文献/References:

[1]武建平,时龙兴,凌明,等.Unicore架构下的Dalvik虚拟机优化[J].东南大学学报(自然科学版),2013,43(1):17.[doi:10.3969/j.issn.1001-0505.2013.01.004]
 Wu Jianping,Shi Longxing,Ling Ming,et al.Optimization of Dalvik virtual machine based on Unicore architecture[J].Journal of Southeast University (Natural Science Edition),2013,43(6):17.[doi:10.3969/j.issn.1001-0505.2013.01.004]

备注/Memo

备注/Memo:
作者简介: 凌明(1972—),博士,副教授,trio@seu.edu.cn.
基金项目: 国家科技重大专项资助项目(2009ZX01031)、江苏省“青蓝工程”资助项目.
引文格式: 凌明,武建平,柳琦,等.面向国产Unicore架构的Android图形系统优化[J].东南大学学报:自然科学版,2012,42(6):1069-1073. [doi:10.3969/j.issn.1001-0505.2012.06.009]
更新日期/Last Update: 2012-11-20