Title
Peephole optimization of asynchronous macromodule networks
Abstract
Most high-level synthesis tools for asynchronous circuits take descriptions in concurrent hardware description languages and generate networks of macromodules or handshake components. In this paper, we propose a peephole optimizer for these networks. Our peephole optimizer first deduces an equivalent blackbox behavior for the network using Dill's trace-theoretic parallel composition operator. It then applies a new procedure called burst-mode reduction to obtain burst-mode machines from the deduced behavior. In a significant number of examples, our optimizer achieves gate-count improvements by a factor of five, and speed (cycle-time) improvements by a factor of two. Burst-mode reduction can be applied to any macromodule network that is delay insensitive as well as deterministic. A significant number of asynchronous circuits, especially those generated by asynchronous high-level synthesis tools, fall into this class, thus making our procedure widely applicable.
Year
DOI
Venue
1994
10.1109/92.748198
IEEE Trans. VLSI Syst.
Keywords
DocType
Volume
burst-mode reduction,asynchronous macromodule networks,burst-mode machine,gate-count improvements,dill's trace-theoretic parallel composition operator,high-level synthesis tool,concurrent hardware description languages,significant number,hardware description languages,asynchronous circuit,circuit optimisation,high-level synthesis tools,delays,deduced behavior,vlsi,integrated circuit design,macromodule network,asynchronous high-level synthesis tool,asynchronous circuits,asynchronous macromodule network,equivalent blackbox behavior,burst-mode machines,high level synthesis,peephole optimizer,handshake components,peephole optimization,polarization,computer science,production,hardware description language,sequential circuits,network synthesis
Conference
7
Issue
ISSN
ISBN
1
1063-8210
0-8186-6565-3
Citations 
PageRank 
References 
10
0.93
17
Authors
3
Name
Order
Citations
PageRank
Ganesh Gopalakrishnan11619130.11
Prabhakar Kudva243856.96
Erik Brunvand350966.09