首页> 外文期刊>Concurrency, practice and experience >A collaborative CPU-GPU approach for deep learning on mobile devices
【24h】

A collaborative CPU-GPU approach for deep learning on mobile devices

机译:移动设备深度学习的协同CPU-GPU方法

获取原文
获取原文并翻译 | 示例

摘要

As mobile devices become more prevalent, users tend to reassess their expectations regardingthe personalization ofmobile services. The data collected by amobile device's sensors provide anopportunity to gain insight into the user's profile. Recently, deep learning has gained momentumand has become the method of choice for solving machine learning problems. Interestingly,training a deep neural network on a mobile device is often mistakenly regarded as cumbersome.For instance, several deep learning frameworks only provide a CPU-based implementation forprediction tasks on a mobile device. In contrast to servers, a mobile computing environmentimposes many domain-specific constraints that invite us to review the general computingapproach used in a deep learning framework implementation. In this paper, we propose adeep learning framework that has been specifically designed for mobile device platforms. Ourapproach relies on the collaboration of the multicore CPU and the integrated GPU to acceleratedeep learning computation onmobile devices.Ourwork exploits the sharedmemory architectureof mobile devices to promote CPU-GPU collaboration without any data copying. We analyzeour approach with regard to three factors: performance/portability trade-off, power efficiency,and memory management.
机译:随着移动设备变得更加普遍,用户倾向于重新评估他们的期望手表服务的个性化。 Amobile设备传感器收集的数据提供了一个有机会深入了解用户的个人资料。最近,深入学习已经获得了势头并已成为解决机器学习问题的选择方法。有趣的是,在移动设备上训练一个深神经网络通常被错误地被认为是麻烦的。例如,几个深度学习框架仅提供基于CPU的实现移动设备上的预测任务。与服务器相比,移动计算环境强加了许多特定于域的约束,邀请我们审查一般计算深度学习框架实现中使用的方法。在本文中,我们提出了一个深度学习框架专为移动设备平台而设计。我们的方法依赖于多核CPU和集成GPU的协作以加速深度学习计算onmobile设备。我们的工作利用SharedMemory架构移动设备推广CPU-GPU协作,没有任何数据复制。我们分析我们对三种因素的方法:性能/可移植性权衡,功率效率,和内存管理。

著录项

  • 来源
    《Concurrency, practice and experience》 |2019年第17期|e5225.1-e5225.21|共21页
  • 作者单位

    Department of Computer Science andInformation Engineering National TaiwanUniversity Taipei Taiwan Research Center for Information TechnologyInnovation Academia Sinica Taipei Taiwan;

    Department of Computer Science andInformation Engineering National TaiwanUniversity Taipei Taiwan Graduate Institute of Networking andMultimedia National Taiwan University Taipei Taiwan;

    Department of Computer Science andInformation Engineering National TaiwanUniversity Taipei Taiwan;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    deep learning, energy efficient, GPGPU, heterogeneous system, mobile computing, OpenCL;

    机译:深度学习;节能;GPGPU;异构系统;移动计算;OpenCL;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号