US 11,776,087 B2
Function-as-a-service (FAAS) model for specialized processing units
Robert Edgar Barton, Richmond (CA); Frank Brockners, NRW (DE); Russell Paul Gyurek, Raleigh, NC (US); and Jerome Henry, Pittsboro, NC (US)
Assigned to Cisco Technology, Inc., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Feb. 11, 2022, as Appl. No. 17/669,647.
Application 17/669,647 is a continuation of application No. 16/817,390, filed on Mar. 12, 2020, granted, now 11,282,160.
Prior Publication US 2022/0164918 A1, May 26, 2022
Int. Cl. G06T 1/20 (2006.01); G06F 9/50 (2006.01); G06F 9/38 (2018.01); G06F 9/54 (2006.01); G06F 15/80 (2006.01)
CPC G06T 1/20 (2013.01) [G06F 9/3877 (2013.01); G06F 9/5038 (2013.01); G06F 9/547 (2013.01); G06F 15/80 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, at a service and from a first edge device that is remote from the service, a first request to reserve a first number of cores of a specialized processing unit of the service for performing a first task for an application;
receiving, at the service and from the first edge device, a second request to reserve a second number of cores of the specialized processing unit of the service for performing a second task for the application that is distinguishable from the first task;
determining, based at least in part on the first number of the cores requested and based at least in part on a parameter included in the first request, that the first number of the cores of the specialized processing unit are available for use by the first edge device for the first task;
reserving the first number of the cores for the first task separately from the second number of the cores for the second task; and
sending, to the first edge device, an indication that the first number of the cores have been reserved for use by the first edge device for the first task.