Generic Systolic Array for Run-Time Scalable Cores

This paper presents a scalable core architecture based on a generic systolic array. The size of this kind of cores can be adapted in real-time to cover changing application requirements or to the available area in a reconfigurable device. In this paper, the process of scaling the core is performed by the replication of a single processing element using run-time partial reconfiguration. Furthermore, rather than restricting the proposed solution to a given application, it is based on a generic systolic architecture which is adapted using a design flow which is also proposed. The paper includes a related work discussion, the proposal and definition of a systolic array communication approach, which does not require the use of specific macro structures and permits to achieve higher flexibility, and a design flow used to adapt the generic architecture. Further, the paper also includes an image filter application as a simple use case, along with implementation results for Virtex 5 FPGA.

[1]  Jooheung Lee,et al.  An array-based scalable architecture for DCT computations in video coding , 2008, 2008 International Conference on Neural Networks and Signal Processing.

[2]  M.P. Bekakos,et al.  VHDL Code Automatic Generator for Systolic Arrays , 2006, 2006 2nd International Conference on Information & Communication Technologies.

[3]  Jooheung Lee,et al.  Scalable FPGA Architecture for DCT Computation Using Dynamic Partial Reconfiguration , 2008, ERSA.

[4]  Xun Zhang,et al.  Auto-adaptive reconfigurable architecture for scalable multimedia applications , 2007, Second NASA/ESA Conference on Adaptive Hardware and Systems (AHS 2007).

[5]  Klaus Danne.  Distributed arithmetic FPGA design with online scalable size and performance , 2004, Proceedings. SBCCI 2004. 17th Symposium on Integrated Circuits and Systems Design (IEEE Cat. No.04TH8784).

[6]  G. Venkatesh,et al.  Area-delay tradeoff in distributed arithmetic based implementation of FIR filters , 1997, Proceedings Tenth International Conference on VLSI Design.

[7]  Sergei Sawitzki,et al.  Scalable Reconfigurable Channel Decoder Architecture for Future Wireless Handsets , 2007, 2007 Design, Automation & Test in Europe Conference & Exhibition.

[8]  O. Wing,et al.  Mapping strategy for automatic design of systolic arrays , 1988, [1988] Proceedings. International Conference on Systolic Arrays.

[9]  Wei Shaojun,et al.  Parameterized IP core design , 2001, ASICON 2001. 2001 4th International Conference on ASIC Proceedings (Cat. No.01TH8549).

[10]  Jooheung Lee,et al.  Scalable FPGA-based architecture for DCT computation using dynamic partial reconfiguration , 2009, TECS.

[11]  Wayne Luk,et al.  Reconfigurable shape-adaptive template matching architectures , 2002, Proceedings. 10th Annual IEEE Symposium on Field-Programmable Custom Computing Machines.

[12]  Chong Ho Lee,et al.  A reconfigurable FIR filter design using dynamic partial reconfiguration , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[13]  Yin-Tsung Hwang,et al.  Scalable FFT kernel designs for MIMO OFDM based communication systems , 2007, TENCON 2007 - 2007 IEEE Region 10 Conference.

[14]  M. A. Bayoumi,et al.  A scalable architecture for discrete wavelet transform , 1995, Proceedings of Conference on Computer Architectures for Machine Perception.

[15]  Griselda Saldaña-González,et al.  FPGA-based customizable systolic architecture for image processing applications , 2005, 2005 International Conference on Reconfigurable Computing and FPGAs (ReConFig'05).

[16]  Abbes Amira,et al.  FPGA Realization of FIR Filters by Efficient and Flexible Systolization Using Distributed Arithmetic , 2008, IEEE Transactions on Signal Processing.

[17]  Jooheung Lee,et al.  A Self-Reconfigurable Platform for Scalable DCT Computation Using Compressed Partial Bitstreams and BlockRAM Prefetching , 2009, 2009 IEEE Computer Society Annual Symposium on VLSI.