Page 343 - 《软件学报》2020年第10期

高珑 等:并行帧缓存设备:基于多核 CPU 的 Xorg 并行显示优化 3319

可以在同一个桌面上支持多个相对独立的鼠标键盘,但是目前,测试 XInput 的多个鼠标键盘只能按照主从模式
交替使用,还无法做到指针移动和点击等全部功能完全对等地同时使用.另外,XInput 子系统对于应用程序不透
明,导致有些应用程序暂时还无法使用 XInput 子系统.
如果能够实现单桌面多用户,即同一个桌面允许多个用户(每个用户使用一对鼠标键盘)同时操作,与通过
网络连接起来的多桌面多用户相比,就可以共享更多资源,并降低用户间的通信开销,提高多用户之间互操作和
协作的效率,例如共用显存中已经渲染好的 3D 图像、使用共享内存作为高带宽通信等.结合多屏显示技术还可
以通过一台终端并行完成多台显控终端的功能,减小显控终端的体积和重量.这对于车载或者机载条件下的协
同指挥而言,可能具有潜在的应用价值.
将主事件循环完全线程化,是实现单桌面多用户的技术途径之一,还可以避免因为某个用户的某个耗时操
作导致主事件循环的后续操作无法进行,以至整个桌面陷入无响应死锁状态的情况.本文中所研究的多任务队
列,将为这些研究工作提供技术支持.

References:
[1] http://www.x.org
[2] Simson G, Weise D, Strassmann S. UNIX-Hater Handbook. IDG Books Worldwide, Inc., 1994.
[3] http://wayland.freedesktop.org
[4] https://en.wikipedia.org/wiki/Direct_Rendering_Infrastructure
[5] https://www.kernel.org/doc/html/latest/gpu/drm-internals.html
[6] http://dri.freedesktop.org/wiki/
[7] https://www.kernel.org/doc/Documentation/fb/framebuffer.txt
[8] Crow FC, Howard MW. A frame buffer system with enhanced functionality. ACM SIGGRAPH Computer Graphics, 1981,15(3):
63−69.
[9] Han K, Min AW, Jeganathan NS, et al. A hybrid display frame buffer architecture for energy efficient display subsystems. In: Proc.
of the IEEE Int’l Symp. on Low Power Electronics & Design. IEEE, 2013. 347−352.
[10] Fournier A, Fussell D. On the power of the frame buffer. ACM Trans. on Graphics (TOG), 1988,7(2):103−128.
[11] Bando Y, Saito T, Fujita M. Hexagonal storage scheme for interleaved frame buffers and textures. In: Proc. of the ACM
SIGGRAPH/Eurographics Symp. on Graphics Hardware. DBLP, 2005. 33−40.
[12] Shim H, Chang N, Pedram M. A compressed frame buffer to reduce display power consumption in mobile systems. In: Proc. of the
2004 Asia and South Pacific Design Automation Conf. 2004. 818−823.
[13] Fowler J, McGowen A. Design and implementation of a supercomputer frame buffer system. In: Proc. of the ’88 ACM/IEEE Conf.
on Supercomputing. 1988. 140−147.
[14] Boettcher M, Alhashimi BM, Eyole M. Advanced SIMD: Extending the reach of contemporary SIMD architectures. In: Proc. of the
Conf. on Design. European Design and Automation Association, 2014. 1−4.
[15] Weiss M. Strip mining on SIMD architectures. In: Proc. of the 5th Int’l Conf. on Supercomputing. 1991. 234−243.
[16] Olson KM. Efficient tree codes on SIMD computer architectures. Computer Physics Communications, 1996,98(3):267−287.
[17] Fatoohi R, Field M. Performance analysis of four SIMD machines. In: Proc. of the 7th Int’l Conf. on Supercomputing. 1993.
117−126.
[18] Narayanan PJ. Processor autonomy on SIMD architectures. In: Proc. of the 7th Int’l Conf. on Supercomputing. 1993. 127−136.
[19] Chen Z, Nicolau A. Veidenbaum AV. SIMD-based soft error detection. In: Proc. of the ACM Int’l Conf. on Computing Frontiers.
2016. 45−54.
[20] Peleg A, Wilkie S, Weiser U. Intel MMX for multimedia PCs. Communications of the ACM, 1997,40(1):24−38.
[21] Krishnaprasad S. SIMD programming illustrated using Intel’s MMX instruction set. Journal of Computing Sciences in Colleges,
2004,19(3):268−277.
[22] Ma WC, Yang CL. Using Intel streaming SIMD extensions for 3D geometry processing. In: Proc. of the Advances in Multimedia
Information Processing. 2002. 1080−1087.