Winograd Algorithmic Tuning

Using the Winograd algorithm for convolution execution can provide increased performance compared to common implementation. However, it may be difficult to understand which algorithm would be faster due to dependency on convolution layer parameters and hardware configuration. The Winograd Algorithmic Tuner solves this problem automatically.

For more detailed information about the algorithm, refer to this whitepaper.

Winograd Algorithmic Tuner Workflow

NOTE: OpenVINO™ toolkit supports the Winograd algorithm only for a limited set of convolution parameters. Some convolution layers with prioritization of the Winograd algorithm cannot be executed with this approach.

Winograd Algorithmic Tuner Prerequisites and Limitations

Configure Winograd Optimization Settings

Once a job is finished, configure model optimization to Winograd.

calibration-winograd-b.png

NOTE: Using Winograd optimization, you can tune an original (top-level) model, or a model that has already been tuned.

Select the Optimize section, and check Winograd.

View Winograd Calibration

Click Optimize and a new row of your model appears.

configs-b.png

Once the job is complete, click on it to view inference results.