Adaptive Source-Level Data Assignment to Dual Memory Banks

Alastair Murray, Björn Franke

Research output: Contribution to journalArticlepeer-review

Abstract

Dual memory banks provide extra memory bandwidth to DSP applications and enable simultaneous access to two operands if the data is partitioned appropriately. Fully automated and compiler integrated approaches to data partitioning and memory bank assignment have, however, found little acceptance by DSP software developers. In this article we present a novel source-level approach that is more programmer friendly. Our scheme is based on soft graph coloring and highly adaptive heuristics generated by genetic programming. We have evaluated our scheme on an Analog Devices TigerSHARC TS-101 DSP and achieved speedups of up to 57% on 13 UTDSP benchmarks.
Original languageEnglish
Pages (from-to)20:1-20:22
Number of pages22
JournalACM Transactions on Embedded Computing Systems
Volume11S
Issue number1
DOIs
Publication statusPublished - 1 Jun 2012

Keywords

  • Compilers, Digital Signal Processors, Dual Memory Banks, Genetic Programming, Graph Coloring, Integer Linear Programming, Source-Level Transformations

Fingerprint

Dive into the research topics of 'Adaptive Source-Level Data Assignment to Dual Memory Banks'. Together they form a unique fingerprint.

Cite this