Static Rate-Optimal Scheduling of Iterative Data-Flow Programs Via Optimum Unfolding
IEEE Transactions on Computers
Module selection and data format conversion for cost-optimal DSP synthesis
ICCAD '94 Proceedings of the 1994 IEEE/ACM international conference on Computer-aided design
Scheduling and behavioral transformation for parallel systems
Scheduling and behavioral transformation for parallel systems
Static scheduling for synthesis of DSP algorithms on various models
Journal of VLSI Signal Processing Systems
Minimizing resources in a repeating schedule for a split-node data-flow graph
Proceedings of the 12th ACM Great Lakes symposium on VLSI
Synthesis and Optimization of Digital Circuits
Synthesis and Optimization of Digital Circuits
VLSI and Modern Signal Processing
VLSI and Modern Signal Processing
Introduction to Algorithms
Scheduling Data-Flow Graphs via Retiming and Unfolding
IEEE Transactions on Parallel and Distributed Systems
Techniques for optimizing loop scheduling
Techniques for optimizing loop scheduling
Extended retiming: optimal scheduling via a graph-theoretical approach
ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 04
Hi-index | 0.00 |
Many applications commonly found in digital signal processing and image processing applications can be represented by data-flow graphs (DFGs). In our previous work, we proposed a new technique, extended retiming, which can be combined with minimal unfolding to transform a DFG into one which is rate-optimal. The result, however, is a DFG with split nodes, a concise representation for pipelined schedules. This model and the extraction of the pipelined schedule it represents have heretofore not been explored. In this paper, we develop new results regarding the construction of such graphs. We develop scheduling algorithms for such graphs, and then discuss a way to reduce the hardware requirements of such schedules. In the process, we state and prove a tight upper bound on the minimum number of processors required to execute the static schedule produced by our algorithms. We also construct an unfolding algorithm for split-node graphs and combine it with our scheduling methods to achieve rate-optimality in all cases. Finally, we demonstrate our methods on a specific example.