Heterogeneous Behavioral Hierarchy for System Level Designs

Enhancing productivity for designing complex embedded systems requires system level design methodology and language support for capturing complex design in high level models. For an effective methodology, efficiency of simulation and a sound refinement based implementation path are also necessary. A...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the Design Automation & Test in Europe Conference Vol. 1; pp. 1 - 6
Main Authors: Patel, H.D., Shukla, S.K., Bergamaschi, R.A.
Format: Conference Proceeding
Language:English
Published: IEEE 2006
Subjects:
Computational modeling
Control systems
Embedded software
Embedded system
Hardware
Kernel
Productivity
Software design
Software systems
System-level design
ISBN:3981080114, 9783981080117
ISSN:1530-1591
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Enhancing productivity for designing complex embedded systems requires system level design methodology and language support for capturing complex design in high level models. For an effective methodology, efficiency of simulation and a sound refinement based implementation path are also necessary. Although some of the recent system level design languages for system level abstractions, several essential ingredients are missing from these. We consider (i) explicit support for multiple models of computation (MoCs) or heterogeneity; (ii) the ability to build complex behaviors by hierarchically composing simpler behaviors; and (iii) hierarchical composition of behaviors that belong to distinct models of computation, as essential for successful SLDLs. These render an SLDL with modeling fidelity that exploits both heterogeneity and hierarchy and allows for simpler modeling and efficient simulation. One important requirement for such an SLDL should be that the simulation semantics be also compositional, and hence no flattening of hierarchically composed behaviors be needed for simulation. In this paper we show how we designed SystemC extensions to provide facilities for heterogeneous behavioral hierarchy, compositional simulation semantics, and implemented a simulation kernel which we show experimentally as up to 50% more efficient than standard SystemC simulation
ISBN:3981080114
9783981080117
ISSN:1530-1591
DOI:10.1109/DATE.2006.243955