Novel development tool for software pipeline optimization for VLIW-DSPs used in real-time image processing

被引:0
|
作者
Fürtler, J [1 ]
Mayer, KJ [1 ]
Krattenthaler, W [1 ]
Bajla, I [1 ]
机构
[1] ARC Seibersdorf Res GmbH, High Performance Image Proc Dept, A-2444 Seibersdorf, Austria
来源
REAL-TIME IMAGING VII | 2003年 / 5012卷
关键词
software pipelining; VLIW; real-time image processing; DSP;
D O I
10.1117/12.477491
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Although the hardware platform is often seen as the most important element of real-time imaging systems, software optimization can also provide remarkable reduction of overall computational costs. The recommended code development flow for digital signal processors based on the TMS320C6000(TM) architecture usually involves three phases: development of C code, refinement of C code; and programming linear assembly code. Each step requires a different level of knowledge of processor internals: The developer is not directly involved in the automatic scheduling process. In some cases, however, this may result in unacceptable code performance. A better solution can be achieved by scheduling the assembly code by hand. Unfortunately, scheduling of software pipelines by hand not only requires expert skills but is also time consuming, and moreover, prone to errors. To overcome these drawbacks we have designed an innovative development tool - the Software Pipeline Optimization Tool (SPOT(TM)). The SPOT is based on visualization of the scheduled assembly code by a two-dimensional interactive schedule editor, which is equipped with feedback mechanisms deduced from analysis of data dependencies and resource allocation conflicts. The paper addresses optimization techniques available by the application of the SPOT. Furthermore, the benefit of the SPOT is documented by more than 20 optimized image processing algorithms.
引用
收藏
页码:132 / 143
页数:12
相关论文
共 50 条
  • [1] SPOT -: Development tool for software pipeline optimization for VLIW-DSPs used in real-time image processing
    Fürtler, J
    Mayer, KJ
    Krattenthaler, W
    Bajla, I
    REAL-TIME IMAGING, 2003, 9 (06) : 387 - 399
  • [2] An Image Processing VLIW Architecture for Real-Time Depth Detection
    Iorga, Dan
    Nane, Razvan
    Lu, Yi
    Van Dalen, Edwin
    Bertels, Koen
    PROCEEDINGS OF 28TH IEEE INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING, (SBAC-PAD 2016), 2016, : 158 - 165
  • [3] Scalable, real-time, image processing pipeline
    Delft Univ of Technology, Delft, Netherlands
    Mach Vision Appl, 2 (110-121):
  • [4] A modularized multi-DSPs real-time image processing system
    Wang, YH
    Zhang, TX
    Yan, LX
    IMAGE MATCHING AND ANALYSIS, 2001, 4552 : 12 - 15
  • [5] Real-time image processing system of modularized multi-DSPs
    Wang, Yuehuan
    Wang, Guoyou
    Zhang, Tianxu
    Huazhong Ligong Daxue Xuebao/Journal Huazhong (Central China) University of Science and Technology, 2000, 28 (03): : 63 - 64
  • [6] Novel intelligent image processing algorithms for Real-Time software and hardware
    Yamakawa, Takeshi
    INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2006, 12 (03): : 229 - 230
  • [7] A SCALABLE, REAL-TIME, IMAGE-PROCESSING PIPELINE
    JONKER, PP
    KOMEN, ER
    KRAAIJVELD, MA
    MACHINE VISION AND APPLICATIONS, 1995, 8 (02) : 110 - 121
  • [8] A template for real-time image processing development
    Oh, PY
    IEEE ROBOTICS & AUTOMATION MAGAZINE, 2005, 12 (04) : 65 - 74
  • [9] Flexible VLIW processor based on FPGA for efficient embedded real-time image processing
    Brost, Vincent
    Yang, Fan
    Meunier, Charles
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2014, 9 (01) : 47 - 59
  • [10] Flexible VLIW processor based on FPGA for efficient embedded real-time image processing
    Vincent Brost
    Fan Yang
    Charles Meunier
    Journal of Real-Time Image Processing, 2014, 9 : 47 - 59