Methodology for refinement and optimization of dynamic memory management for embedded systems in multimedia applications

2003 IEEE Workshop on Signal Processing Systems (IEEE Cat. No.03TH8682) Pub Date : 1900-01-01 DOI:10.1109/SIPS.2003.1235698

M. Leeman, G. Deconinck, V. De Florio, David Atienza Alonso, J. Mendias, C. Ykman, F. Catthoor, R. Lauwereins

{"title":"Methodology for refinement and optimization of dynamic memory management for embedded systems in multimedia applications","authors":"M. Leeman, G. Deconinck, V. De Florio, David Atienza Alonso, J. Mendias, C. Ykman, F. Catthoor, R. Lauwereins","doi":"10.1109/SIPS.2003.1235698","DOIUrl":null,"url":null,"abstract":"In multimedia applications, run-time memory management support has to allow real-time memory de/allocation, retrieving and processing of data. Thus, its implementation must be designed to combine high speed, low power, large data storage capacity and a high memory bandwidth. We assess the performance of our new system-level exploration methodology to optimize the memory management of typical multimedia applications in an extensively used 3D image reconstruction system (Pollefeys, M. et al, 1998; Cosmas, J. et al, 2002). This methodology is based on an analysis of the number of memory accesses, normalized memory use and energy estimations for the system studied. This results in an improvement in the normalized memory footprint of up to 44.2% and in the estimated energy dissipation of up to 22.6% over conventional static memory implementations in an optimized version of the driver application. Finally, our final version is able to scale perfectly the memory consumed in the system for a wide range of input parameters, whereas the statically optimized version is unable to do this.","PeriodicalId":173186,"journal":{"name":"2003 IEEE Workshop on Signal Processing Systems (IEEE Cat. No.03TH8682)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2003 IEEE Workshop on Signal Processing Systems (IEEE Cat. No.03TH8682)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIPS.2003.1235698","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 10

Abstract

In multimedia applications, run-time memory management support has to allow real-time memory de/allocation, retrieving and processing of data. Thus, its implementation must be designed to combine high speed, low power, large data storage capacity and a high memory bandwidth. We assess the performance of our new system-level exploration methodology to optimize the memory management of typical multimedia applications in an extensively used 3D image reconstruction system (Pollefeys, M. et al, 1998; Cosmas, J. et al, 2002). This methodology is based on an analysis of the number of memory accesses, normalized memory use and energy estimations for the system studied. This results in an improvement in the normalized memory footprint of up to 44.2% and in the estimated energy dissipation of up to 22.6% over conventional static memory implementations in an optimized version of the driver application. Finally, our final version is able to scale perfectly the memory consumed in the system for a wide range of input parameters, whereas the statically optimized version is unable to do this.

查看原文本刊更多论文

多媒体应用中嵌入式系统动态存储器管理的改进和优化方法

在多媒体应用程序中，运行时内存管理支持必须允许实时内存分配、检索和处理数据。因此，它的实现必须设计成结合高速、低功耗、大数据存储容量和高内存带宽。我们评估了我们的新系统级探索方法的性能，以优化广泛使用的3D图像重建系统中典型多媒体应用程序的内存管理(Pollefeys, M. et al .， 1998;Cosmas, J. et al, 2002)。该方法基于对所研究系统的内存访问数量、规范化内存使用和能量估计的分析。这使得在驱动程序的优化版本中，与传统的静态内存实现相比，标准化内存占用提高了44.2%，估计能量耗散提高了22.6%。最后，我们的最终版本能够为大范围的输入参数完美地扩展系统中消耗的内存，而静态优化的版本无法做到这一点。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2003 IEEE Workshop on Signal Processing Systems (IEEE Cat. No.03TH8682)

自引率

0.00%

发文量