论文信息 - Comments on 'A systolic array for computing BA-1'

Comments on 'A systolic array for computing BA-1'

An algorithm and a systolic array for computing BA/sup -1/ was presented by P. Comon and Y. Robert (see ibid., vol.ASSP-35, p.717-23, June 1987). A and B are n by n and p by n matrices, respectively. Such an array computes BA/sup -1/ in (4n+p-2) time units using n(n+1) processing elements (PE's). The commenters apply a graph-based method for the design of systolic arrays to such an algorithm. They systematically derive the original array and another array that performs the computation in the same time but using (n(n+1)/2+pn) units. For p >

Tomás Lang | Jaime H. Moreno

[1] Thomas Kailath,et al. Regular iterative algorithms and their implementation on processor arrays , 1988, Proc. IEEE.

[2] Jaime H. Moreno,et al. Design Of Special-Purpose Arrays For Matrix Computations: Preliminary Results. , 1987, Optics & Photonics.

[3] J. H. Moreno. Comparing design methods based on index-dependencies and on data-dependencies , 1990 .

[4] Tomás Lang,et al. Arrays For Partitioned Matrix Algorithms: Tradeoffs Between Cell Storage And Cell Bandwidth , 1989, Optics & Photonics.

[5] Yves Robert,et al. A systolic array for computing B A-1 , 1987, IEEE Trans. Acoust. Speech Signal Process..

[6] Jean-Marc Delosme,et al. Highly concurrent computing structures for matrix arithmetic and signal processing , 1982, Computer.

[7] Harper J. Whitehouse,et al. Parallel Processing Algorithms And Architectures For Real-Time Signal Processing , 1982, Optics & Photonics.

[8] H. T. Kung. Why systolic architectures? , 1982, Computer.