Use Cases

    Can’t find your model in the below list?
    Please tell us more to find a solution.

    1

    Weather Research and Forecast (WRF):

    HPCMinds identifies the best resource allocation for numerical weather prediction system. The platform understands the parameters of the WRF in order to suggest the best level of parallelization required to complete the execution successfully within the provided deadline and cost limit. HPCMinds then provisions the resources and runs the containerized tasks.

    2

    Computational Fluid Dynamics (CFD):

    HPCMinds allows users to run their OpenFOAM simulations faster and more cost effectively on OCI. OpenFOAM supports a wide range of CFD applications like automotive, energy and aerospace. HPCMinds can help scale the simulation without the hassle of finding the right resources, allowing the engineers to focus exclusively on the modelling while the platform parallelizes and executes the models on the cloud.

    3

    Artificial Intelligence (AI):

    HPCMinds aids the user to exploit the scalability of OCI to solve complex problems using AI. This is very important when we are dealing with deep learning models that are highly parallelizable and require huge training times. HPCMinds enables the use of elastic cloud resources, as a supercomputer with unlimited resources able to train the desired model as fast as possible. HPCMinds also automates the AI lifecycle by choosing the right resources for different processes like data analysis, feature engineering, prediction and data visualization.

    4

    Emergency Staff Training:

    Emergency services need to be trained for a fire incident in a big and crowded building. HPCMinds allows the trainees to execute parts of the simulations (fire and crowd) with the initial setup for a few seconds, perform actions, and continue the execution for a few more seconds. If results are not as expected, the trainees may revert to previous timeline of the simulation, change the actions, and resume the simulation. This ability to try different actions at any point of the incident timeline, helps trainees evaluate different actions and quickly learn their expected reactions in case of an incident.