Batched Compute Skinning
The following is intended for informational purposes only, and may not be incorporated into any contract. No purchasing decisions should be made based on the following materials. Unity is not committing to deliver any functionality, features or code. The development, timing and release of all products, functionality and features are at the sole discretion of Unity, and are subject to change.
If you have accepted to use functional cookies and logged in using your Unity ID at the top right of the page, then sharing feedback is as simple as clicking a card below, selecting a topic’s importance, adding your point of view, and submitting. If you prefer not to accept functional cookies or log in, you will be prompted to enter an email address and validate it, so we know how to reach out when the topic evolves. For more information read the Feedback and privacy terms.
Background:
Unity’s Skinned Mesh Renderer component utilize compute dispatches for parallelizing vertex transformations on the GPU.
Such renderers will traditionally generate a separate compute dispatch per skinned mesh. Furthermore, blend shapes are applied via separate compute shaders, which are dispatched in a serialized fashion. This approach can lead to a large number of compute dispatches and low GPU parallelization and performance.
To address this, we are now introducing the "Batched" Compute Skinning mode:
This configuration will batch skinning dispatches as much as possible, in order to increase the amount of vertices being deformed in parallel, and reduce GPU synchronization. In turn, this improves the GPU performance of Skinned Mesh Renderers across all capable platforms.