Telephone: 0114 257 2200

Cloud bursting is on the horizon for universities series: part 3

In the final part of our ‘cloud bursting in universities’ series, I will look at the advantages of bursting HPC platforms. Typically, HPC services or systems are bought from research council funding and the best HPC system is bought at the time. But, eighteen months later, its utilisation is close to 100% and the compute capabilities are ageing with no more money available for a new system for a few years.

But all is not lost, as it is becoming cost effective for research computing departments at universities to access cutting edge technologies or burst beyond their current capacity by leveraging the public cloud.

In our experience, a university can extend the life of its cluster and be given the ability to offer newer technologies and services through its cluster by bursting out to the public cloud.

At the time of purchase of its new HPC system, a university might have bought the latest GPUs at the time of release, but eighteen months later, NVIDIA has released a better performing GPU which can’t be purchased due to a lack of additional funding.

Hardware manufacturers are recognising this advantage and bolstering it by releasing new hardware to public cloud providers before the rest of the industry – for example, NVIDIA released their latest Volta GPUs and they were available to use in the public cloud before they could be bought!

By bursting into the public cloud, the university can offer the latest and greatest technologies as part of its Research Computing Service for all its researchers.

Time and time again, at OCF, we can help the research computing team make this a process which is transparent to their users, with the design of a research computing platform with a single point of entry for users.

This involves researchers being able to use the on-premises cluster and that cluster can burst out to the public cloud for additional resources or when priority jobs are required.

Also, through that single point of entry, researchers can take up the non-HPC aspects of the cloud, like Hadoop clusters or running AI workloads without needing the research computing team to install a whole new set of software or hardware!

Another key consideration I’d like to make you aware of is how to manage the billing aspect of bursting into the cloud, which could become very expensive if not monitored closely.  There are specific toolsets that have been designed to help with billing control and they are continuing to be developed to meet the needs of universities.

People power

Systems’ administrators who would have run the university’s HPC service previously now have the ability to provide a complete Research Computing Platform and can have greater visibility of all their researchers’ needs, so they can continuously enhance the design of the research computing service, helping the researchers carry out even better work.

This kind of service is very attractive for universities and removes the need for researchers to become ‘pseudo IT systems administrators’ who need to learn how to run a server under their desk and can focus instead entirely on their research.

There is a noticeable increase in awareness of the benefits of public cloud bursting by universities, particularly in research computing. Whilst no-one is replacing their on-premises HPC system with the public cloud yet, it is recognised that bursting into the public cloud is incredibly useful for the provision of the latest technologies or extra capacity and expertise for researchers.

As part of their 10-20 year roadmaps, we are now seeing some universities considering whether they will be buying an on-premises cluster in 10 years’ time and may consider alternatively purchasing a public cloud version of an HPC cluster.

I think there will need to be a culture shift in universities and funding for HPC in the cloud to be fully accepted and most importantly the costs in using the public cloud will need to be driven down further for wider adoption, but the trends are pointing to it not being too far off.

If you have any comments on this blog series, please leave a comment or if you would like to explore this further, please get in touch with me here.