Speculative render ahead and caching in multiple passes

摘要

Various embodiments are directed to intelligently rendering or pre-rendering content that may likely be brought into an associated viewport during a user's interaction with the content. In at least some embodiments, the process of caching pre-rendered content is separated from a determination of which regions outside of the viewport are to be kept up to date over use and time. Further, at least some embodiments perform rendering activities in multiple passes in an effort to reduce potential delays in the user visible content reaching completion, without interfering with other work that an associated application or system performs during rendering.

主权项

1. A method comprising:
rendering content within a current viewport; receiving a directional manipulation of the viewport; responsive to receiving the directional manipulation of the viewport, starting a time-constrained rendering loop; pre-rendering and caching content for the manipulation that lies in a virtual surface outside of the viewport, in the direction of the manipulation, wherein the content that lies in the virtual surface outside of the viewport is pre-rendered as long as time remains in the rendering loop and responsive to ascertaining that no invalidated content remains in the viewport; maintaining cached:
at least some previously-rendered pre-rendered content, the at least some previously-rendered pre-rendered content having been identified based on one or more rendering policies that control which of the previously-rendered pre-rendered content is to remain cached; andthe content that is pre-rendered for the manipulation; and rendering content, that includes at least some of the cached content, within a new current viewport.