An Initial Scale-Factor Linear Polynomial Regression Model Approach for Hardware Performance on an HPC Compute-Node

High-Performance Computing (HPC) relies heavily on the overall performance and capabilities of the system used to implement it. The purpose of this research is to perform several benchmarks on Texas State University's LEAP Cluster and analyze the data collected from those tests to determine performance models. The tests used to collect this data will be various benchmarking programs such as High-Performance Linpack (HPL), IOZone, and CacheBench. Analysis of the performance evaluation for each benchmark was modeled with a scaled second-order linear polynomial regression and used to observe the performance when the workload was changed. Once the analysis was completed, the models were compared to the data obtained from the benchmark runs on the specific hardware devices. The models showed that scaling coefficients help to describe the performance of each hardware model. The work-in-progress is to continue to find scalable regression approaches that can improve the performance modeling fit.