Title: Shared scratch pad memory space management across applications

Authors: Ozcan Ozturk, Mahmut Kandemir, Seung Woo Son, Ibrahim Kolcu

Addresses: Department of Computer Engineering, Engineering Building, EA407B, Bilkent University, Bilkent, Ankara 06800, Turkey. ' Computer Science and Engineering Department, The Pennsylvania State University, University Park, PA 16802, USA. ' Argonne National Laboratory, 9700 South Cass Avenue, Argonne, IL 60439, USA. ' Computation Department, University of Manchester, Oxford Road, Manchester M13 9PL, UK

Abstract: Scratch Pad Memories (SPMs) have received considerable attention lately as on-chip memory building blocks. The main characteristic that distinguishes an SPM from a conventional cache memory is that the data flow is controlled by software. The main focus of this paper is the management of an SPM space shared by multiple applications that can potentially share data. The proposed approach has three major components; a compiler analysis phase, a runtime space partitioner, and a local partitioning phase. Our experimental results show that the proposed approach leads to minimum completion time among all alternate memory partitioning schemes tested.

Keywords: memory space management; scratch pad memory; chip multiprocessors; parallel execution; data sharing; compiler analysis; runtime space partition; local partitioning; memory partitioning.

DOI: 10.1504/IJES.2009.027240

International Journal of Embedded Systems, 2009 Vol.4 No.1, pp.54 - 65

Published online: 18 Jul 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article