A Design of a GP-GPU based Stream Processor for an Image Processing

被引:0
作者
Lee, Kwang Yeob [1 ]
Kyung, Gyutaek [2 ]
Park, Tae Ryong [1 ]
Kwak, Jae Chang [1 ]
Koo, Yong Seo [3 ]
机构
[1] Seokyeong Univ, Dept Comp Engn, Seoul, South Korea
[2] NEXTCHIP Co Ltd, Gyeonggi Do, South Korea
[3] Dankook Univ, Dept Elect Engn, Gyeonggi Do, South Korea
来源
2015 38TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP) | 2015年
关键词
ream Processor; GP-GPU; cache; parallelism; superscalar;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Mobile devices provide a more realistic image processing and various high spec features to satisfy users. So, mobile devices have been developing in the direction of computing acceleration by using a strong parallelism of GP-GPU processing. In this paper, a GP-GPU architecture is proposed based on stream processing architecture which has the advantage of high parallelism to enhance the image processing capability. The proposed GP-GPU architecture consists of 8 stream processors and has multi-banked cache memory structure. The results of verification shows that the proposed stream processor improves the performance of the integral image generation : 24.5%, 3x3 gaussian filer mask : 4.7%, 5x5 gaussian filter mask : 1.3% in comparison with ARM Cortex-A15 quad core.
引用
收藏
页码:535 / 539
页数:5
相关论文
共 10 条
  • [1] Bay H., 2006, P EUR C COMP VIS, V1, P404, DOI DOI 10.1007/11744023
  • [2] Collange Sylvain, 2011, HAL
  • [3] Dynamic warp formation and scheduling for efficient GPU control flow
    Fung, Wilson W. L.
    Sham, Ivan
    Yuan, George
    Aamodt, Tor M.
    [J]. MICRO-40: PROCEEDINGS OF THE 40TH ANNUAL IEEE/ACM INTERNATIONAL SYMPOSIUM ON MICROARCHITECTURE, 2007, : 407 - +
  • [4] Kim J, 2013, ISCA 13
  • [5] Kim Sung Su, 2011, TABLE BASED THREAD R
  • [6] Lee S.P, 2002, DESIGN NONBLOCKING I
  • [7] Levinthal A., 1984, SIGGRAPH, P77
  • [8] NVIDIA Tesla: A unified graphics and computing architecture
    Lindholm, Erik
    Nickolls, John
    Oberman, Stuart
    Montrym, John
    [J]. IEEE MICRO, 2008, 28 (02) : 39 - 55
  • [9] Pas Ruud van der, IWOMP 2005
  • [10] Yeob Lee Kwang, 2014, [Journal of IKEEE, 전기전자학회논문지], V18, P392, DOI 10.7471/ikeee.2014.18.3.392