Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

QUKU

QUKU A new architecture, QUKU, is proposed for implementing stream-based algorithms on FPGAs, which combines the advantages of FPGA and Coarse Grain Reconfigurable Arrays (CGRAs). QUKU consists of a dynamically reconfigurable, coarse-grain Processing Element (PE) array with an associated softcore processor providing system support. At a coarse-grain, the PE array can be reconfigured on a cycle-by-cycle basis to change the PE functionality similarly to that in a conventional CGRA. At a fine-grain, the whole FPGA can be reconfigured statically to implement a completely different PE array that serves the target application in a better way. Advantages of the fine-grain reconfiguration include individually customized PEs, adaptable numeric format support and customizable interconnect network. A prototype CAD tool framework is also developed which facilitates programming the QUKU architecture. An example application consisting of two different image detectors is implemented to demonstrate the advantages of QUKU. QUKU provides up to 140 times speedup and 40 times improvement in area-time product compared to an implementation running on an FPGA-based softcore. The area-time product for QUKU is around 16 lower than that of a custom circuit based implementation on the same FPGA. The per-PE customization provides an area-time saving of approximately 31 compared to a homogeneous 4 4 array of PEs for the same application. The experimental results demonstrate that a dual layered reconfigurable architecture provides significant potential benefits in terms of flexibility, area and processing efficiency over existing reconfigurable computing architectures for DSP. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Embedded Computing Systems (TECS) Association for Computing Machinery

QUKU

Download PDF
26 pages

Loading next page...
 
/lp/association-for-computing-machinery/quku-z6GFQftVIh

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Association for Computing Machinery
Copyright
Copyright © 2013 ACM
ISSN
1539-9087
eISSN
1558-3465
DOI
10.1145/2435227.2435259
Publisher site
See Article on Publisher Site

Abstract

A new architecture, QUKU, is proposed for implementing stream-based algorithms on FPGAs, which combines the advantages of FPGA and Coarse Grain Reconfigurable Arrays (CGRAs). QUKU consists of a dynamically reconfigurable, coarse-grain Processing Element (PE) array with an associated softcore processor providing system support. At a coarse-grain, the PE array can be reconfigured on a cycle-by-cycle basis to change the PE functionality similarly to that in a conventional CGRA. At a fine-grain, the whole FPGA can be reconfigured statically to implement a completely different PE array that serves the target application in a better way. Advantages of the fine-grain reconfiguration include individually customized PEs, adaptable numeric format support and customizable interconnect network. A prototype CAD tool framework is also developed which facilitates programming the QUKU architecture. An example application consisting of two different image detectors is implemented to demonstrate the advantages of QUKU. QUKU provides up to 140 times speedup and 40 times improvement in area-time product compared to an implementation running on an FPGA-based softcore. The area-time product for QUKU is around 16 lower than that of a custom circuit based implementation on the same FPGA. The per-PE customization provides an area-time saving of approximately 31 compared to a homogeneous 4 4 array of PEs for the same application. The experimental results demonstrate that a dual layered reconfigurable architecture provides significant potential benefits in terms of flexibility, area and processing efficiency over existing reconfigurable computing architectures for DSP.

Journal

ACM Transactions on Embedded Computing Systems (TECS) – Association for Computing Machinery

Published: Mar 29, 2013

Keywords: CGRAs

References

  • Image Processing: Principles and Applications
    Acharya, ; T., ; Ray, ; K., A.
  • A spatial mapping algorithm for heterogeneous coarse-grained recodigurable architechures
    Ahn, ; M., ; Yoon, ; W., J.; Paek, ; Y., ; Kim, ; Y., ; Kiemb, ; M., ; Choi, ; K.,
  • AsAP: A fine-grained many-core platform for DSP Applications
    Baas, ; B., ; Yu, ; Z., ; Meeuwsen, ; Sattari, M.; Apperson, O.; Work, R.; Webb, E.; J., ; Lai, ; M., ; Mohsenin, ; T., ; Truong, ; D., ; Cheung, ; J.,
  • PACT XPP - A Self-Reconfigurable Data Processing Architecture
    Baumgarte, ; V., ; May, ; F., ; Nückel, ; A., ; Vorbach, ; M., ; Weinhardt, ; M.,
  • Compilation of C for hybrid reconfigurable architectur
    Callahan, ; J., T.
  • Difference-based partial reconfiguration
    Eto, ; E.,
  • SPR: An architecture-adaptive CGRA mapping tool
    Friedman, ; S., ; Carroll, ; A., ; Essen, Van; B., ; Ylvisaker, ; B., ; Ebeling, ; C., ; Hauck, ; S.,
  • Garp: a MIPS processor with a reconfigurable coprocessor
    Hauser, ; R., J.; Wawrzynek, ; J.,
  • Coarse-grained reconfigurable processors - flexibility meets efficiency
    Heysters, ; M., P.
  • System level tools for DSP in FPGAs
    Hwang, ; J., ; Milne, ; B., ; Shirazi, ; N., ; Stroomer, ; D., J.
  • Design aspects of multi-level reconfigurable architectur
    Lange, ; S., ; Middendorf, ; M.,
  • Design and implementation of the MorphoSys reconfigurable computing processor
    Lee, ; M., ; Singh, ; H., ; Lu, ; G., ; Bagherzadeh, ; N., ; Kurdahi, ; Fj,
  • Enhanced architectures, design methodologies and CAD tools for dynamic reconfiguration of Xilinx FPGAs
    Lysaght, ; P., ; Blodget, ; B., ; Mason, ; J., ; Young, ; J., ; Bridgford, ; B.,
  • The age of adaptive computing is here
    Master, ; P.,
  • ADRES: An Architecture with tightly coupled VLIW processor and coarse-grained reconfigurable matrix
    Mei, ; B., ; Vernalde, ; S., ; Verkest, ; D., ; Man, ; D., H.; Lauwereins, ; R.,
  • Efficient datapath merging for partially reconfigurable architectures
    Moreano, ; N., ; Borin, ; E., ; De Souza, Cid; Araujo, ; G.,
  • CRC -- Concepts and evaluation of processor-like reconfigurable architectures
    Oppold, ; T., ; Schweizer, ; T., ; Filho, ; O., J.; Eisenhardt, ; S., ; Rosenthal, ; W.,
  • Montium reconfigurable digital signal processing tile processor datasheet, www
    Systems, Recore
  • Connecting customized IP to the MicroBlaze soft processor using the fast simplex link (FSL) Channel
    Rosinge, ; H.-P.,
  • QUKU: A mixed grain dynamically reconfigurable architecture for high performance computing
    Shukla, ; K., S.
  • MorphoSys: An integrated reconfigurable system for data-parallel and computation-intensive applications
    Singh, ; H., ; Lee, ; M., ; Lu, ; G., ; Kurdahi, ; Fj,
  • Overview of the tool-flow for the Montium processor tile, In Proceedings of the International Conference on Engineering of Reconfigurable Systems and Algorithms T
    Smit, ; M., G. J.; Guo, ; Y., ; Heysters, ; M., P.
  • Reconfigurable computing for digital signal processing: A survey
    Tessier, ; R., ; Burleson, ; W.,
  • Reconfigurable computing: architectures and design methods, IEE Proc
    Todman, ; J., T.; Constantinides, ; A., G.; Wilton, ; E., S. J.; Mencer, ; O., ; Luk, ; W., ; Cheung, ; K., P. Y.
  • High-level synthesis challenges and solutions for a dynamically reconfigurable processor
    Toi, ; T., ; Nakamura, ; N., ; Kato, ; Y., ; Awashima, ; T., ; Wakabayashi, ; K., ; Jing, ; L.,
  • Energy-efficient specialization of functional units in a coarse-grained reconfigurable array
    Essen, Van; C., B.; Panda, ; R., ; Wood, ; A., ; Ebeling, ; C., ; Hauck, ; S.,
  • Optimi-Ware: Software profiling and optimization {Best of theWeb}
    Westcott, ; T., ; Docef, ; A.,
  • FPGA-Based Implementation of Signal Processing Systems
    Woods, ; R., ; Mcallister, ; J., ; Turner, ; R., ; Yi, ; Y., ; Lightbody, ; G.,
  • Microblaze Processor Reference Guide v7
    Xilinx,
  • SPKM: a novel graph drawing based algorithm for application mapping onto coarse-grained reconfigurable architectures
    Yoon, ; W., J.; Shrivastava, ; A., ; Park, ; S., ; Ahn, ; M., ; Jeyapaul, ; R., ; Paek, ; Y.,