Evaluating Energy Efficiency of GPUs using Machine Learning Benchmarks

Foster, Brett

Student Work

Evaluating Energy Efficiency of GPUs using Machine Learning Benchmarks

Public

As we enter the exascale era, the energy efficiency and performance of High-Performance Computing (HPC) systems, especially running Machine Learning (ML) applications, are becoming increasingly important. Nvidia recently released its 9th-generation HPC-grade Graphics Processing Unit (GPU) microarchitecture, Ampere, claiming significant improvements over the previous generation’s Volta architecture. In this project, we perform fine-grained power collection and assess the performance of these two HPC architectures by profiling ML benchmarks on them. In addition, we analyze various hyperparameters, primarily the batch size and the number of GPUs, to determine their impact on the performance and power efficiency of these systems.

This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator