Is it possible to connect the resources of two or more EC2 instances?

Question

Hello,

I want to ask if its possible to connect or unify the resources of two or more EC2 instances? Background is that we use heavy machine learning on prem right now and are running into hardware limitations. We thought about using EC2 but the possible instances specifications are not enough and we would like to combine two or more instances (like p3.16xlarge).

Is something like that possible?

Accepted Answer

Firstly there is no way to combine instance there is though a larger instance type in the p3 family p3dn.24xlarge

I'm not an ML expert but with this challenge you probably want to investigate a way to parallelise your training using the features of the framework you are using eg mentioned [here](https://docs.aws.amazon.com/sagemaker/latest/dg/model-parallel-intro.html)

Answer

Thanks for your answer! We just wanted a confirmation that there is no way to combine instances.

We look into parallelization then.

Is it possible to connect the resources of two or more EC2 instances?

相关内容