2. Team Members
• Resource Provider: Gompute
• Category: Aerodynamics
• Expertise Provider: Eleks
• Software Provider: ANSYS
3. Team 56
• Aim was to evaluate the HPC cloud service
without need to obtain new engineering
insights
• Basic test case was chosen
• Case with results from the end user’s own
cluster with a minimum of confidential
content
5. Significant Challenges
• High costs for hardware and licenses
• Client has a highly fluctuating load with
regard to simulations
• Current on-site cluster rarely has the correct
capacity
6. Major Benefits
• East of use
• Post- and pre-processing can be done
remotely
• Excellent opportunity to test the state of the
art in cloud based HPC
7. Main Conclusions and
Recommendations
• HPC in the cloud is technically feasible
• Most remaining issues are implementation related
and resource provider should be able to solve
• Remote visualization solution was good and
allowed user to perform some real work
• Stress test with multiple users from same company
remains unknown
• Value of the HPC in the cloud solution is limited by
absence of appropriate licensee models
8. More Information
• More information available via:
https://www.theubercloud.com/experiments
/team-56-simulating-radial-and-axial-fan-
performance/