A Low-Power Handheld GPU using Logarithmic Arithmetic and Triple DVFS Power Domains

被引:0
|
作者
Nam, Byeong-Gyu [1 ]
Lee, Jeabin [1 ]
Kim, Kwanho [1 ]
Lee, Seung Jin [1 ]
Yoo, Hoi-Jun [1 ]
机构
[1] Korea Adv Inst Sci & Technol, Dept EECS, Taejon 305701, South Korea
关键词
GPU; Hardware Architecture; 3D Computer Graphics; Handheld Systems; Low-Power;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, a low-power GPU architecture is described for the handheld systems with limited power and area budgets. The GPU is designed using logarithmic arithmetic for power- and area-efficient design. For this GPU, a multifunction unit is proposed based on the hybrid number system of floating-point and logarithmic numbers and the matrix, vector, and elementary functions are unified into a single arithmetic unit. It achieves the single-cycle throughput for all these functions, except for the matrix-vector multiplication with 2-cycle throughput. The vertex shader using this function unit as its main datapath shows 49.3% cycle count reduction compared with the latest work for OpenGL transformation and lighting (TnL) kernel. The rendering engine uses also the logarithmic arithmetic for implementing the divisions in pipeline stages. The GPU is divided into triple dynamic voltage and frequency scaling power domains to minimize the power consumption at a given performance level. It shows a performance of 5.26Mvertices/s at 200MHz for the OpenGL TnL and 52.4mW power consumption at 60fps. It achieves 2.47 times performance improvement while reducing 50.5% power and 38.4% area consumption compared with the latest work.
引用
收藏
页码:73 / 80
页数:8
相关论文
共 50 条
  • [31] Low-Power Testing for Low-Power Devices
    Wen, Xiaoqing
    2010 IEEE 25TH INTERNATIONAL SYMPOSIUM ON DEFECT AND FAULT TOLERANCE IN VLSI SYSTEMS (DFT 2010), 2010, : 261 - 261
  • [32] Low- and ultra low-power arithmetic units: Design and comparison
    Vratonjic, M
    Zeydel, BR
    Oklobdzija, VG
    2005 IEEE INTERNATIONAL CONFERENCE ON COMPUTER DESIGN: VLSI IN COMPUTERS & PROCESSORS, PROCEEDINGS, 2005, : 249 - 252
  • [33] Low-Power Ultrasound Imaging on Mixed FPGA/GPU Systems
    Cacko, Damian
    Walczak, Mateusz
    Lewandowski, Marcin
    2018 JOINT CONFERENCE - ACOUSTICS, 2018, : 42 - 47
  • [34] Parallelizing Multimodal Background Modeling on a Low-Power Integrated GPU
    Shoaib Azmat
    Linda Wills
    Scott Wills
    Journal of Signal Processing Systems, 2017, 88 : 43 - 53
  • [35] Parallelizing Multimodal Background Modeling on a Low-Power Integrated GPU
    Azmat, Shoaib
    Wills, Linda
    Wills, Scott
    JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2017, 88 (01): : 43 - 53
  • [36] Low-power macro-cells for pulse code arithmetic
    Univ of Oslo, Oslo, Norway
    Proc IEEE Int Conf Electron Circuits Syst, (289-292):
  • [37] Glitch-conscious low-power design of arithmetic circuits
    Eriksson, H
    Larsson-Edefors, P
    2004 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOL 2, PROCEEDINGS, 2004, : 281 - 284
  • [38] Low-power high-performance arithmetic circuits and architectures
    Fahim, AM
    Elmasry, MI
    IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2002, 37 (01) : 90 - 94
  • [39] Design of A Low-Power RNS-Enhanced Arithmetic Unit
    Patronik, Piotr
    Piestrak, Stanislaw J.
    2016 IEEE 7TH LATIN AMERICAN SYMPOSIUM ON CIRCUITS & SYSTEMS (LASCAS), 2016, : 151 - 154
  • [40] Low-power distributed arithmetic architectures using non-uniform memory partitioning
    Ramprasad, S
    Shanbhag, NR
    Hajj, IN
    ISCAS '99: PROCEEDINGS OF THE 1999 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOL 3: ANALOG AND DIGITAL SIGNAL PROCESSING, 1999, : 470 - 473