Best Configuration for Machine-Learning Training VM
Question
A cloud administrator is building a new VM for machine-learning training.
The developer requesting the VM has stated that the machine will need a full GPU dedicated to it.
Which of the following configuration options would BEST meet this requirement?
Answers
Explanations
Click on the arrows to vote for the correct answer
A. B. C. D.C.
https://blogs.vmware.com/apps/2018/09/using-gpus-with-virtual-machines-on-vsphere-part-2-vmdirectpath-i-o.htmlThe BEST configuration option to meet the requirement of a full GPU dedicated to a virtual machine for machine-learning training is C. Passthrough GPU.
Explanation: A Virtual GPU (A) is a software-based GPU that allows multiple virtual machines to share a single physical GPU. While it can provide some level of hardware acceleration, it may not be sufficient for machine learning workloads that require high GPU performance.
An External GPU (B) is a separate physical device that can be connected to a computer or server to provide additional GPU resources. However, it may not be the best option for virtual machines, as it requires additional hardware and may not be easy to manage in a virtual environment.
A Passthrough GPU (C) allows a virtual machine to have exclusive access to a physical GPU. This configuration option provides the highest level of GPU performance and is ideal for machine learning workloads that require intensive GPU processing.
A Shared GPU (D) is a configuration option that allows multiple virtual machines to share a single physical GPU. This option may not be suitable for machine learning workloads that require high GPU performance.
In summary, a Passthrough GPU configuration is the BEST option for meeting the requirement of a full GPU dedicated to a virtual machine for machine-learning training.
