Automated Dynamic Memory Data Type Implementation Exploration and Optimization

Authors:
Marc Leeman;Chantal Ykman;David Atienza;Vincenzo De Florio;Geert Deconinck
Affiliations:
-;-;-;-;-
Venue:
ISVLSI '03 Proceedings of the IEEE Computer Society Annual Symposium on VLSI (ISVLSI'03)
Year:
2003

Citing 0
Cited 5

Systematic methodology for exploration of performance - Energy trade-offs in network applications using Dynamic Data Type refinement

Journal of Systems Architecture: the EUROMICRO Journal
Optimization of dynamic data structures in multimedia embedded systems using evolutionary computation

SCOPES '07 Proceedingsof the 10th international workshop on Software & compilers for embedded systems
The formalism underlying EASYMAP: A precompiler for refinement-based exploration of hierarchical data organizations

Science of Computer Programming
Exploration methodology of dynamic data structures in multimedia and network applications for embedded platforms

Journal of Systems Architecture: the EUROMICRO Journal
Performance and energy trade-offs analysis of L2 on-chip cache architectures for embedded MPSoCs

Proceedings of the 20th symposium on Great lakes symposium on VLSI

Quantified Score

Hi-index	0.00

Visualization

Abstract

The behavior of many algorithms is heavily determinedby the input data. Furthermore, this often means that multipleand completely different execution paths can be followed,also internal data usage and handling is frequentlyquite different. Therefore, static compile time memory allocationis not efficient, especially on embedded systemswhere memory is a scarce resource, and dynamic memorymanagement is the only feasible alternative. Includingapplications with dynamic memory in embedded systemsintroduces new challenges as compared to traditional signalprocessing applications. In this session, an automatedframework is presented to optimize embedded applicationswith extensive use of dynamic memory management. Theproposed methodology automates the exploration and identificationof optimal data type implementations based onpower estimates, memory accesses and normalized memoryusage.