Design of a Scalable Network of Communicating Soft Processors on FPGA

In this work we investigate the implementation of a general parallel architecture using platform FPGA. With the implementation of communicating multiple soft processors mapped over a hypercube topology, our objective is to determine platform FPGA and SoC design environment advantages and limits for scalable multiple processors conception. We investigate the effect of communication system in FPGA devices, experimenting with different designs decisions. We present some performance results with the illustration of a parallel sort algorithm.

[1]  Andrew A. Kennings,et al.  Symmetric multiprocessing on programmable chips made easy , 2005, Design, Automation and Test in Europe.

[2]  Stephen Bates,et al.  A memory-based architecture for FPGA implementations of low-density parity-check convolutional decoders , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[3]  Jean-Pierre Dérutin,et al.  SIMD, SMP and MIMD-DM parallel approaches for real-time 2D image stabilization , 2005, Seventh International Workshop on Computer Architecture for Machine Perception (CAMP'05).

[4]  Gerhard Fettweis,et al.  Towards a GBit/s Programmable Decoder for LDPC Convolutional Codes , 2007, 2007 IEEE International Symposium on Circuits and Systems.

[5]  Ajay Dholakia,et al.  Reduced-complexity decoding of LDPC codes , 2005, IEEE Transactions on Communications.

[6]  Ramkrishna Swamy,et al.  Architectures for ASIC implementations of low-density parity-check convolutional encoders and decoders , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[7]  Joseph R. Cavallaro,et al.  Configurable, High Throughput, Irregular LDPC Decoder Architecture: Tradeoff Analysis and Implementation , 2006, IEEE 17th International Conference on Application-specific Systems, Architectures and Processors (ASAP'06).

[8]  Wayne H. Wolf.  A Decade of Hardware/Software Codesign , 2003, Computer.

[9]  Daniel J. Costello,et al.  LDPC block and convolutional codes based on circulant matrices , 2004, IEEE Transactions on Information Theory.

[10]  Mohammad M. Mansour,et al.  A 640-Mb/s 2048-bit programmable LDPC decoder chip , 2006, IEEE Journal of Solid-State Circuits.

[11]  Jocelyn Sérot,et al.  Skeletons for parallel image processing: an overview of the SKIPPER project , 2002, Parallel Comput..

[12]  Kamil Sh. Zigangirov,et al.  Time-varying periodic convolutional codes with low-density parity-check matrix , 1999, IEEE Trans. Inf. Theory.

[13]  Ali Emre Pusane,et al.  Decoders for low-density parity-check convolutional codes with large memory , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[14]  Paul R. Schumacher,et al.  A single program multiple data parallel processing platform for FPGAs , 2004, 12th Annual IEEE Symposium on Field-Programmable Custom Computing Machines.

[15]  Robert G. Gallager,et al.  Low-density parity-check codes , 1962, IRE Trans. Inf. Theory.

[16]  Gerhard Fettweis,et al.  Synchronous Transfer Architecture (STA) , 2004, SAMOS.

[17]  K.Sh. Zigangirov,et al.  Periodic time-varying convolutional codes with low-density parity-check matrices , 1998, Proceedings. 1998 IEEE International Symposium on Information Theory (Cat. No.98CH36252).

[18]  Cameron D. Patterson,et al.  Configurable Soft Processor Arrays Using the OpenFire Processor , 2005 .