US 12,346,728 B2
Job limit enforcement for improved multitenant quality of service
Ahmed M. Abdelkhalek, Ajax (CA); Rutao Zhang, Markham (CA); Bokun Zhang, Markham (CA); Min Zhang, King City (CA); Yinan Jiang, Richmond Hill (CA); and Jeffrey G. Cheng, Markham (CA)
Assigned to ATI TECHNOLOGIES ULC, Markham (CA)
Filed by ATI TECHNOLOGIES ULC, Markham (CA)
Filed on Dec. 1, 2022, as Appl. No. 18/072,818.
Prior Publication US 2024/0184623 A1, Jun. 6, 2024
Int. Cl. G06F 9/54 (2006.01); G06F 9/48 (2006.01); G06F 9/50 (2006.01)
CPC G06F 9/4881 (2013.01) [G06F 9/54 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a scheduling circuit of a graphics processing unit (GPU) and from a virtual function (VF) associated with a tenant in a multitenant computing system, a job request for execution by the GPU;
validating, by a user-mode driver (UMD) associated with the tenant, the job request in accordance with one or more defined restrictions associated with the tenant; and
responsive to successfully validating the job request in accordance with the one or more defined restrictions, forwarding the validated job request to a kernel-mode driver (KMD) associated with the tenant to provide the validated job request to one or more rendering engines of the GPU for execution.