MobiSys ... : the ... International Conference on Mobile Systems, Applications and Services. International Conference on Mobile Systems, Applications, and Services最新文献

筛选

英文中文

RSTensorFlow: GPU Enabled TensorFlow for Deep Learning on Commodity Android Devices. RSTensorFlow: GPU支持的TensorFlow用于商用Android设备上的深度学习。

MobiSys ... : the ... International Conference on Mobile Systems, Applications and Services. International Conference on Mobile Systems, Applications, and Services Pub Date : 2017-06-01 DOI: 10.1145/3089801.3089805

Moustafa Alzantot, Yingnan Wang, Zhengshuang Ren, Mani B Srivastava

{"title":"RSTensorFlow: GPU Enabled TensorFlow for Deep Learning on Commodity Android Devices.","authors":"Moustafa Alzantot, Yingnan Wang, Zhengshuang Ren, Mani B Srivastava","doi":"10.1145/3089801.3089805","DOIUrl":"https://doi.org/10.1145/3089801.3089805","url":null,"abstract":"Mobile devices have become an essential part of our daily lives. By virtue of both their increasing computing power and the recent progress made in AI, mobile devices evolved to act as intelligent assistants in many tasks rather than a mere way of making phone calls. However, popular and commonly used tools and frameworks for machine intelligence are still lacking the ability to make proper use of the available heterogeneous computing resources on mobile devices. In this paper, we study the benefits of utilizing the heterogeneous (CPU and GPU) computing resources available on commodity android devices while running deep learning models. We leveraged the heterogeneous computing framework RenderScript to accelerate the execution of deep learning models on commodity Android devices. Our system is implemented as an extension to the popular open-source framework TensorFlow. By integrating our acceleration framework tightly into TensorFlow, machine learning engineers can now easily make benefit of the heterogeneous computing resources on mobile devices without the need of any extra tools. We evaluate our system on different android phones models to study the trade-offs of running different neural network operations on the GPU. We also compare the performance of running different models architectures such as convolutional and recurrent neural networks on CPU only vs using heterogeneous computing resources. Our result shows that although GPUs on the phones are capable of offering substantial performance gain in matrix multiplication on mobile devices. Therefore, models that involve multiplication of large matrices can run much faster (approx. 3 times faster in our experiments) due to GPU support.","PeriodicalId":91364,"journal":{"name":"MobiSys ... : the ... International Conference on Mobile Systems, Applications and Services. International Conference on Mobile Systems, Applications, and Services","volume":"2017 ","pages":"7-12"},"PeriodicalIF":0.0,"publicationDate":"2017-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/3089801.3089805","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35987559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 46