| CPC G06F 9/5038 (2013.01) [G06F 9/5044 (2013.01); G06F 9/505 (2013.01); G06F 11/3409 (2013.01); G06F 11/3433 (2013.01); G06N 20/00 (2019.01); G06F 11/3003 (2013.01); G06F 2209/501 (2013.01); G06F 2209/509 (2013.01)] | 14 Claims |
|
1. An apparatus, comprising:
a processor; and
a memory that stores code executable by the processor to:
receive a request at a client device to execute a machine learning workload for the client device, the machine learning workload comprising a machine learning algorithm, wherein the client device uses results of execution of the machine learning workload;
dynamically determine a wait time for executing the machine learning workload on the client device;
dynamically determine a wait time for executing the machine learning workload on a server device, the server device communicatively coupled to the client device and providing computing services to the client device;
select the client device in response to determining that the client device is able to provide a result of executing the machine learning workload in real-time;
in response to determining that the client device is not able to provide the result of executing the machine learning workload in real-time, select one of the client device and the server device with a quickest execution time for execution of the machine learning workload based on the wait time of the client and server devices; and
execute the machine learning workload using the selected client or server device.
|