AI inference is continuing to become more prevalent in workstation applications. However, in most cases, the AI portion of what the user perceives to be the feature is only a small part of the overall pipeline. Learn how to ensure that the inference on the GPU is as optimal as it can be, and also the rest of the pipeline, including memory transfers, pre- and post-processing, encode and decode, and integration with existing pipelines. Also learn about interpreting profiles using Nsight Systems and how to make design choices based on the findings. We will focus on ONNX Runtime with the DirectML backend in conjunction with DirectX12. Some experience with DirectX12 is desirable but not essential.
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.