Dual-pronged deep learning preprocessing on heterogeneous platforms with CPU, GPU and CSD

Most existing data preprocessing is done at the CPU. Although some studies use techniques such as multi-processing and double buffering to accelerate CPU preprocessing, CPU computational speed and storage bandwidth still limit the processing speed. Other studies try to use intelligent data storage devices, such as computational storage devices, to complete data preprocessing instead of CPUs. The current studies use only one device to complete data preprocessing operations, which cannot fully overlap data preprocessing and accelerator computation time. To fully exploit the independence and high bandwidth of the novel CSD, this paper proposes an advanced, highly parallel dual-pronged data preprocessing algorithm (DDLP) that significantly improves the execution efficiency and computational overlap between heterogeneous devices. DDLP enables the CPU and CSD to start data preprocessing operations from both ends of the dataset separately. Meanwhile, we propose two adaptive dynamic selection strategies to make DDLP control the GPU to automatically read data from different sources. We achieve sufficient computational overlap between CSD data preprocessing and CPU preprocessing, GPU computation, and GPU data reading. In addition, DDLP leverages GPU Direct Storage technology to enable efficient SSD-to-GPU data transfer. DDLP reduces the usage of expensive CPU and DRAM resources, reduces the number of SSD-to-GPU data transfers, and improves the energy efficiency of preprocessing while reducing the overall preprocessing and training time. Extensive experimental results show that DDLP can improve learning speed by up to 23.5% on ImageNet Dataset while reducing energy consumption by 19.7% and CPU and DRAM usage by 37.6%. DDLP also improve learning speed by up to 27.6% on Cifar-10 Dataset.