RSTensorFlow

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 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 . By integrating our acceleration framework tightly into , 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.

AI Workload Allocation Methods for Edge-Cloud Computing: A Review

“…The Neural Processing software development kit (SDK) from Qualcomm is made to work with their Snapdragon processors [93]. There are other universal libraries designed for mobile devices that are independent of any particular hardware, such as RSTensorFlow [94], which accelerates DL matrix multiplication using the GPU. Moreover, software methods for effectively utilizing hardware have been devised.…”