acceptable run times,’ said Slagter. ‘This is not what they want. They clearly want to solve their engineering problem and not unnecessarily to spend time adapting the model to suit the computing resources available.’

Selecting the right technology Once the performance benchmark has been run on a user’s model, Ansys engineers will produce a report that highlights performance on a small HPC cluster compared to their existing infrastructure and simulation timings over a number of CPU cores. ‘We want to demonstrate that, if they

were to run their model on a more powerful machine, you can get time savings in a certain order of magnitude. On average we have shown a six-times shorter runtime using a small cluster, when compared to a customer’s current configuration. This is across the board, across different models that we have received so far,’ said Slagter. With this jump in performance, an

organisation ‘can increase their simulation throughput, tack on more complex models, larger models with more complex physics, or create more design variants to demonstrate the performance or make product trade-off studies. The benefits of using HPC for simulation

are well understood, yet the technology has not been adopted by some engineering organisations. This can be for a number of reasons but generally it comes down to two primary factors; lack of expertise or a reluctance to invest in a new technology. In Slagter’s experience, it is often that

companies lack the expertise or the staff to set up and manage an HPC cluster. ‘Proper sizing of an HPC cluster involves more than just choosing the processor, core count or memory. People need to consider storage, remote visualisation, job scheduling and possibly workload management software, and that is not what these engineers want to do,’ said Slagter. ‘We do not want to put a burden on their IT department either. We propose two options: one is an on-premise deployment option and the other is off-premise deployment in the cloud,’ said Slagter.

HPC in the cloud Ansys has developed cloud-based solutions with a number of cloud-hosting partners who provide HPC infrastructure and IT services to cater for either burst capacity, or as an extension of an organisation’s in-house computing capacity. Slagter noted that flexibility can be a key factor when talking to customers.

16 Scientific Computing World August/September 2018

“This allows the customers to stay more focussed on their core engineering competence rather than spending time on IT”

This relates not only to flexibility on compute capacity, but also the ability to scale the number of software licenses an organisation is using. Cloud hosting offers a platform to

expand computing capacity or a way of trying HPC on-demand before bringing a cluster in-house. It can also be used to provide burst capacity for users with an existing HPC system. ‘We have developed an ecosystem of

cloud-hosting partners such as Rescale, Gompute (Gridcore) and Ubercloud, which provide HPC infrastructure and IT services for customers,’ said Slagter. ‘This allows the customers to stay more focussed on their core engineering competence, rather than spending time on IT. Many of those engineer organisations lack good IT staff or even an IT department. Sometimes they have to manage the computer themselves.’ These products – developed by Ansys

partners – offer a solution to a challenge that faces many HPC users. While large automotive and aerospace companies have been using HPC simulation for some time, many smaller enterprises are much less experienced. Without the infrastructure and expertise to configure

and manage an HPC cluster, the barrier to entry can be too large, which discourages organisations from taking the first step.

HPC out of the box For enterprises that prefer an on premise solution, Ansys has partnered with Hewlett Packard Enterprise (HPE), to offer an out- of-the box solution for users that want a fully managed cluster, optimised for Ansys software and pre-configured with Ansys engineering and job management software. This system has been designed to shift simulation jobs off local workstations to a central cluster resource, enabling users to increase resource utilisation. The appliance reduces the time and cost of acquisition and aims to make it easier to adopt and maintain HPC, even if you don’t have IT support and resources. Ansys offers several different appliances for different application workloads, with each optimised for a specific set of workflows. ‘Not everybody is ready for cloud

computing yet, but we want to give people the choice. Either they choose to adopt cloud or continue to invest in on premise hardware. ‘We need to make it much simpler to

acquire a system and to reduce the risk of acquiring a new cluster that may not be balanced or optimised for engineering workloads,’ added Slagter. ‘Simulation is a different application,

a more computationally demanding application than any other enterprise application. Even different Ansys products have different requirements for hardware,’ Slagter concluded.

@scwmagazine |

DRN Studio/

Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36