The Uber-Experiment for Manufacturers High-Performance Technical Computing as a Service
Delivering high performance technical computing (HPTC) as a service – or even in the Cloud – comes with a set of challenges, both technical and social. In this Call for Participation, Wolfgang Gentzsch and Burak Yenier discuss the various aspects of the HPTC service model, the people that need to be involved in the process, and the challenges faced when executing the manufacturer’s workloads on remote High-Performance Computing (HPC) resources. They will also describe the open HPC-as-a-Service Experiment that they have come up with to bring together manufacturing end users, resource providers, software providers, and HPC experts.
The technology components of HPTC-as-a-Service that enable multi-tenant, remote access to centralized resources, and metered use are not unfamiliar to this community. However, as service-based delivery models take off, with the promise of easy access to pay-per-use computing resources, our manufacturing users have been mostly on the fence, observing and discussing the potential hurdles to its adoption in HPTC.
Even with the challenges of data privacy, incompatible software licensing models, and a dozen other potential roadblocks, it’s time we dip our toes in the water and figure out how to achieve the benefits of service-based delivery. How far are we from an ideal HPTC-as-a-Service model? At this point, nobody knows.
What is fairly certain is that we now have the technology ingredients to make it happen. To glue it all together into a coherent end-to-end process, the authors have come up with the “Uber-Experiment for HPTC as a Service.” We believe the technology is not the challenge anymore; rather it’s the people who make service-based HPTC come together. The major stakeholders are:
The Manufacturer: small or medium size manufacturers in the process of designing and prototyping their next product. These users are candidates for HPTC-as-a-Service when in-house computation on workstations has become too lengthy a process, but acquiring additional computing power in the form of HPC is too cumbersome or is not in line with budgets.
The resource providers: owners of HPC resources, computers, and storage. An HPC center would fall into this category, a standard datacenter used to handle batch jobs, or a cluster-owning commercial entity willing to offer up cycles to run non-competitive workloads during periods of low CPU-utilization.
The application software provider: software owners of all stripes, ISVs, public domain organizations and individual developers; with rock-solid software, which has the potential to be used on a wider scale. In this experiment, on-demand license usage will be tracked to determine the feasibility of using the service model as a revenue stream.
The HPC experts: individuals or companies with HPC expertise. It also encompasses PhD-level domain specialists with in-depth application knowledge. In the experiment, experts will work with end users, computer centers, and software providers to help glue the pieces together.
For example, suppose the manufacturer is in need of additional compute resources to speed up a product design cycle, say for simulating more sophisticated geometry or physics, or for running many more simulations for a higher quality result. That suggests a specific software stack, domain expertise, and even hardware configuration. The general idea is to look at the user’s task, select the appropriate resources, software and expertise that match its requirements, run the job, and get results back to the end-user.
More information about this experiment can be found at http://www.hpcwire.com/hpcwire/2012-06-28/the_uber-cloud_experiment.html?featured=top. It is scheduled to begin later in July and run for three months. At that point, the results will be made publicly available to the HPC community, in the form of use cases, lessons learned, and recommendations on how to overcome especially the mental barriers. Anyone interested in participating can register at www.hpcexperiment.com.
