Multi-user multi-GPU render server apparatus and methods

摘要

The invention provides, in some aspects, a system for rendering images, the system having one or more client digital data processors and a server digital data processor in communications coupling with the one or more client digital data processors, the server digital data processor having one or more graphics processing units. The system additionally comprises a render server module executing on the server digital data processor and in communications coupling with the graphics processing units, where the render server module issues a command in response to a request from a first client digital data processor. The graphics processing units on the server digital data processor simultaneously process image data in response to interleaved commands from (i) the render server module on behalf of the first client digital data processor, and (ii) one or more requests from (a) the render server module on behalf of any of the other client digital data processors, and (b) other functionality on the server digital data processor.

主权项

1. A method to render image requests comprising the steps of:
a) executing a render server program; b) receiving two or more render requests to generate two or more rendered images from one or more clients, where each of the two or more render requests include a time of receipt of the render request; c) selecting from the two or more render requests the render request requiring the most processing time as a large render request, where one or more render requests are not selected as the large render request; d) ‘breaking down’ the large render request into a plurality of partial render requests including at least a first partial render request a second partial render request and remaining partial render requests, where each of the plurality of partial render requests require one or both less compute time and less graphics resources than one or both the requirements for compute time and graphics resources of the large render request; e) assigning a time of receipt of the first partial render request based on the time of receipt of the large render request; f) assigning a time of receipt of the second partial render request such that at least one of the one or more render requests is assigned a time of receipt after the time of receipt of the first partial render request and before the time of receipt of the second partial render request; g) assigning a time of receipt of the remaining partial render request such that at least one of the one or more render requests is assigned a time of receipt after the time of receipt of the second partial render request and before the time of receipt of the remaining partial render requests; h) determining a sequence of interleaved commands for rendering the one or more render requests and the plurality of partial render requests based on the time of receipt of the one or more render requests and the assigned time of receipt of the first partial render request and the assigned time of receipt of the second partial render request and the assigned time of receipt of the remaining partial render requests; i) issuing the sequence of interleaved commands to one or more graphics processing units to generate the two or more rendered images; and j) sending to the one or more clients the two or more rendered images.