Optimized software synthesis for digital signal processing algorithms: an evolutionary approach
Authors:
- E. ZitzlerEZE. Zitzler
- S.S. BhattacharyyaSBS.S. Bhattacharyya
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 589-598
Abstract
Based on the model of synchronous data flow (SDF), so-called single appearance schedules are known to provide memory-optimal schedules. Among these, the problem of buffer memory optimization is treated: (1) an evolutionary algorithm (EA) is applied to efficiently explore the (in general) exponential search space of actor firing orders; (2) for each order, the buffer costs are evaluated by applying a dynamic programming post-optimization step (GDPPO).Keywords
This publication has 7 references indexed in Scilit:
- High level software synthesis for signal processing systems2003
- Scheduling for optimum data memory compaction in block diagram oriented software synthesis2002
- Lower bounds on memory requirements for statically scheduled DSP programsJournal of Signal Processing Systems, 1996
- Optimal register assignment to loops for embedded code generationACM Transactions on Design Automation of Electronic Systems, 1996
- Software Synthesis from Dataflow Graphs1996
- GRAPE: a CASE tool for digital signal parallel processingIEEE ASSP Magazine, 1990
- Synchronous data flowProceedings of the IEEE, 1987