Master NVIDIA's profiling tools for CUDA and AI workloads. After learning how to use Nsight Systems to identify and solve inefficiencies and scalability issues on the application level, you'll deep-dive into the challenges of tuning your CUDA kernels for maximum efficiency with Nsight Compute. Take a tour across the most common optimization patterns and how the profilers allow developers to recognize and resolve them to achieve great performance. The tool engineers themselves will cover a broad range of techniques and examples, including data collection, analysis, result comparison, and integration into customized workflows. This lab is applicable to interested beginners as well as experienced performance analysts wanting to uncover the latest available features and tips.
Prerequisite(s):
Please disregard any reference to "Event Code" for access to training materials. "Event Codes" are only valid during the original live session. Explore more training options offered by the NVIDIA Deep Learning Institute (DLI). Choose from an extensive catalog of self-paced, online courses or instructor-led virtual workshops to help you develop key skills in AI, HPC, graphics & simulation, and more.