An extended analysis of memory hierarchies for efficient implementations of image processing applications

An extended analysis of memory hierarchies for efficient implementations of image processing applications
复制标题

对内存层次结构的扩展分析,以有效实现图像处理应用程序

DOI:
10.1007/s11554-017-0723-2
复制
发表时间:
2017
影响因子:
3
通讯作者:
D. Fey
D. Fey
中科院分区:
计算机科学4区
文献类型:
--
作者:
C. Hartmann;D. Fey

文献摘要

参考文献

被引文献

相似文献

随着电子设备的不断小型化,嵌入式智能摄像头正变得越来越重要。相机尺寸的减小增加了应用范围。在工业应用中,智能相机的范围从质量监控和位置跟踪到生产机器的校准。在非专业应用中,可以观察到结合融合传感器信息的运动相机的明显繁荣。然而,所有这些应用程序都有一个共同的瓶颈:内存架构。大多数图像处理应用程序都是内存受限的任务。因此,用图像处理应用程序传输数据的时间对应用程序的整个处理时间有决定性的影响。不同的内存访问模式需要不同的内存配置和层次结构。由于图像处理应用与内存体系结构匹配不足,导致图像处理系统性能不佳。这可能导致更长的处理时间和更大的能耗率。本文介绍了一种新的图像处理应用分类方法,该方法利用图像处理应用的存储器访问模式在存储器架构上进行映射。我们的工作结合了一个模拟框架(异构内存模拟器)和一个分析框架(内存分析器),以发现图像处理应用程序中的瓶颈,并帮助在处理时间和能耗方面找到合适的、特定于应用程序的内存配置。
Through continued miniaturization of electronic devices embedded smart cameras are steadily becoming more and more important. The reduction of the camera size increases the spectrum of applications. In industrial applications the range of smart cameras spans from quality monitoring and position tracking to the calibration of production machines. In non-professional applications a distinct boom in action cameras combined with fused sensor information can be observed. However, all of these applications have a common bottleneck: the memory architecture. Most image processing applications are memory-bound tasks. Thus, the amount of time for transferring data with image processing applications decisively affects the application’s entire processing time. Different memory access patterns require different memory configurations and hierarchies. An insufficient match between the image processing application and the memory architecture leads to a poor performance in the image processing system. This can lead to longer processing times, and larger energy consumption rates. This work introduces new methods of classifying image processing applications by using their memory access pattern for mapping on memory architectures. Our work combines a simulation framework the heterogenous memory simulator with a analytical framework the memory analyzer to find bottlenecks inside the image processing application and aids in finding a suitable, application-specific memory configuration in terms of processing time and energy consumption.
用于 FPGA 上 2D 模板代码应用的通用 VHDL 模板
DOI: 10.1109/isorcw.2012.39
发表时间: 2012
期刊: 2012 IEEE 15th International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing Workshops
影响因子: --
作者:
Michael Schmidt;M. Reichenbach;D. Fey
通讯作者: D. Fey
DOI: 10.1007/978-1-4471-6684-9
发表时间: 2016-03
期刊: --
影响因子: --
作者:
W. Burger;M. Burge
通讯作者: W. Burger;M. Burge
高级 DRAM 时序、功率和区域探索工具
DOI: --
发表时间: 2015
期刊: International Conference / Workshop on Embedded Computer Systems: Architectures, Modeling and Simulation
影响因子: --
作者:
Omar Naji;C. Weis;Matthias Jung;N. Wehn;Andreas Hansson
通讯作者: Andreas Hansson
嵌入式硬件非功能属性估计及其在图像处理中的应用
DOI: 10.1109/ipdpsw.2015.58
发表时间: 2015
期刊: 2015 IEEE International Parallel and Distributed Processing Symposium Workshop
影响因子: --
作者:
C. Herglotz;A. Hendricks;M. Reichenbach;J. Seiler;D. Fey;A. Kaup
通讯作者: A. Kaup
IPOL - 用于图像处理应用程序的领域特定语言
DOI: --
发表时间: 2015
期刊:
影响因子: --
作者:
C. Hartmann;M. Reichenbach;D. Fey
通讯作者: D. Fey