A strategy for determining a Jacobi specific dataflow processor

In this paper we present a strategy for determining a dataflow processor which is intended for the execution of Jacobi algorithms which are found in the application domain of array processing and other real-lime adaptive signal processing applications. Our strategy to determine a processor for their execution is to exploit the quasi regularity property in their dependence graph representations in search for what we call the Jacobi processor. This processor emerges from an exploration iteration which takes off from a processor template and a set of Jacobi algorithms. Based on qualitative and quantitative performance analysis, both the algorithms and the processor template are restructured towards improved execution performance. To ensure the mapper is part of the emerging processor specification, the algorithm-to-processor mapping method is included in the iterative and hierarchical exploration method. Processor's hierarchy exploits properties related to regularity in the algorithm's structure, allows gentle transitions from regular to irregular levels in the algorithm hierarchy and offers different control models for the irregular structures that appear at deeper levels of the hierarchy. Transformations aiming at reducing critical paths, increasing throughput, improving mapping efficiency and minimizing control and flow overheads are essential. They include retiming, pipelining and lookahead techniques.

[1]  J. T. Buck.  Static scheduling and code generation from dynamic dataflow graphs with integer-valued control streams , 1994, Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers.

[2]  C. Rader,et al.  VLSI systolic arrays for adaptive nulling , 1996 .

[3]  Keshab K. Parhi,et al.  Pipelined Cordic based QRD-RLS adaptive filtering using matrix lookahead , 1997, 1997 IEEE Workshop on Signal Processing Systems. SiPS 97 Design and Implementation formerly VLSI Signal Processing.

[4]  E.F. Deprettere,et al.  Controlling the critical path in time adaptive QR/sup -1/ recursions , 1994, Proceedings of 1994 IEEE Workshop on VLSI Signal Processing.

[5]  A. Swindlehurst,et al.  Subspace-based signal analysis using singular value decomposition , 1993, Proc. IEEE.

[6]  C. M. Rader,et al.  VLSI systolic arrays for adaptive nulling [radar] , 1996, IEEE Signal Process. Mag..

[7]  Ed F. Deprettere,et al.  Scalable parallel processor array for Jacobi-type matrix computations , 1995, Integr..

[8]  Ed F. Deprettere,et al.  Transformational reasoning on time-adaptive jacobi type algorithms , 1995 .

[9]  Lothar Thiele,et al.  On the design of piecewise regular processor arrays , 1989, IEEE International Symposium on Circuits and Systems,.

[10]  Ed F. Deprettere,et al.  MODEL AND METHODS FOR REGULAR ARRAY DESIGN , 1993 .

[11]  Joos Vandewalle,et al.  A systolic array for recursive least squares computations , 1993, IEEE Trans. Signal Process..

[12]  J. G. McWhirter,et al.  Algorithmic engineering in adaptive signal processing , 1992 .

[13]  S. Kung,et al.  VLSI Array processors , 1985, IEEE ASSP Magazine.

[14]  Ed F. Deprettere,et al.  Jacobi-specific processor arrays , 1996, Proceedings of International Conference on Application Specific Systems, Architectures and Processors: ASAP '96.

[15]  Ed F. Deprettere,et al.  An Approach for Quantitative Analysis of Application-Specific Dataflow Architectures , 1997, ASAP.

[16]  B.D. Van Veen,et al.  Beamforming: a versatile approach to spatial filtering , 1988, IEEE ASSP Magazine.

[17]  Arjan J. C. van Gemund,et al.  Performance prediction of parallel processing systems: the PAMELA methodology , 1993, ICS '93.