GPU backed Data Mining on Android Devices
This work addresses the challenge of performing computationally intensive machine learning on low-power Android devices, which is incremental as it adapts existing OpenCL methods to a new platform.
The authors tackled the problem of enabling high-performance computing on Android devices by creating a wrapper library for OpenCL to utilize integrated GPUs, and they compared the performance of DBSCAN and Kmeans algorithms, finding that GPU usage can speed up calculations and reduce energy consumption for data mining tasks in remote or energy-constrained environments.
Choosing an appropriate programming paradigm for high-performance computing on low-power devices can be useful to speed up calculations. Many Android devices have an integrated GPU and - although not officially supported - the OpenCL framework can be used on Android devices for addressing these GPUs. OpenCL supports thread and data parallelism. Applications that use the GPU must account for the fact that they can be suspended by the user or the Android operating system at any moment. We have created a wrapper library that allows to use OpenCL on Android devices. Already written OpenCL programs can be executed with almost no modification. We have used this library to compare the performance of the DBSCAN and Kmeans algorithms on an integrated GPU of an Arm-v7 tablet with other single and multithreaded implementations on the same device. We have investigated which programming paradigm and language allows the best tradeoff between execution speed and energy consumption. Using the GPU for HPC on Android devices can help to carry out computationally intensive machine learning or data mining tasks in remote areas, under harsh environmental conditions and in areas where energy supply is an issue.