Exercises
Steve Lantz
Cornell Center for Advanced Computing
Revisions: 5/2023, 12/2021, 5/2021 (original)
These exercises show you how to interrogate NVIDIA devices so that you can determine certain properties of the hardware. You do this by compiling and running programs on the host that execute predefined CUDA methods on the attached device(s). The necessary programs are supplied for you: the exercises are just meant to acquaint you with the important features of GPU architecture. The instructions and batch scripts are geared toward Frontera, but the exercises are applicable to any system that includes a compute-capable NVIDIA device and that has the CUDA Toolkit installed.
Objectives
After you complete this topic, you should be able to:
- Describe the names, sizes, and speeds of the computational components of specific models of NVIDIA GPU devices
Prerequisites
- Familiarity with High Performance Computing (HPC) concepts could be helpful, but most terms are explained in context.
- Parallel Programming Concepts and High-Performance Computing could be considered as a possible companion to this topic, for those who seek to expand their knowledge of parallel computing in general, as well as on GPUs.