GPU Utilization: Predictive SARIMAX Time Series Analysis

This work explores collecting performance metrics and leveraging the output for prediction on a memory-intensive parallel image classification algorithm - Inception v3 (or Inception3 ). Experimental results were collected by nvidia-smi on a computational node DGX-1, equipped with eight Tesla V100 Graphic Processing Units (GPUs). Time series analysis was performed on the GPU utilization data taken, for multiple runs, of Inception3’s image classification algorithm (see Figure 1). The time series model applied was Seasonal Autoregressive Integrated Moving Average Exogenous (SARIMAX)