Efficient retiming and unfolding

Authors:
Liang-Fang Chao;Edwin Hsing-Mean Sha
Affiliations:
Dept. of Computer Science, Princeton University;Dept. of Computer Sci. & Eng., University of Notre Dame
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: plenary, special, audio, underwater acoustics, VLSI, neural networks - Volume I
Year:
1993

Citing 3
Cited 0

Static Rate-Optimal Scheduling of Iterative Data-Flow Programs Via Optimum Unfolding

IEEE Transactions on Computers
Data Flow Program Graphs

Computer
Data Flow Supercomputers

Computer

Quantified Score

Hi-index	0.00

Visualization

Abstract

Data-flow graphs (DFG) can be used to represent a signal-flow graph, a synchronous system or a digital circuitry. Retiming and unfolding are two useful techniques which have been effectively applied to optimize the realization of DFGs. Retiming technique reorganizes an iteration; unfolding technique schedules several iterations together. These two techniques can be combined to schedule DFGs optimally. We show a very efficient algorithm to combine these two techniques. We also present simple methods for examining an unfolded graph by simulating it on the original DFG.