OpenVINO™ toolkit streamlines development, integration, and deployment of performant deep learning models in domains like computer vision, large language models (LLM), and generative AI (Gen AI).

But given the ubiquity of heterogeneous compute environments, there’s a good chance your models and model-based apps must run on multiple hardware targets. Optimizing for each can take a bit of sleuthing.

This session addresses that issue, showing you how to configure and run analysis on your OpenVINO toolkit workloads to uncover bottlenecks on target hardware—CPU, GPU, and NPU—using Intel® VTune™ Profiler and Intel® Advisor.

The topics covered include:

• How the framework for OpenVINO toolkit boosts AI application performance.
• How to use Intel Advisor for performance modeling and CPU/GPU roofline generation.
• How to use Intel VTune Profiler for performance analysis across CPU (memory bottlenecks), GPU (use issues for vector engines with X^e architecture), and NPU (memory bandwidth).
• An overview of Intel VTune Profiler built-in Instrumentation and Tracing Technology API (ITT API) utilities provided with the framework for OpenVINO toolkit.

Skill level: Intermediate
 

• OpenVINO toolkit
• Get the stand-alone version of Intel VTune Profiler or as part of the Intel® oneAPI Base Toolkit.
• Get the stand-alone version of Intel Advisor or as part of the Intel oneAPI Base Toolkit.