English
Log in
English

Pay-As-You-Simulate powered by AI with OnScale Solve™

By Jeff Dobson 22 December 2020

No engineer wants to sit waiting and wondering when their simulation is going to complete. Time is money and that is why OnScale Solve utilizes AI estimators to provide all users a prediction of how long a simulation study is going to take and how much it will cost. These are accurately predicted prior to hitting the run button and committing to any simulation. It also predicts the memory required to solve so that appropriate cloud HPC hardware is automatically selected to compute the simulation. These predictions consider a vast range of parameters to achieve accurate predictions. This includes the model parameters such as the materials and geometry, the simulation mesh, the physics utilized and the analysis type.

AI

The provision of an accurate estimation is key to OnScale’s model which is based on the compute time it takes for a simulation to run. Using a pay-as-you-simulate business model, it provides enterprise-grade simulation capabilities available to every engineer. Combined with cloud HPC, users can scale up and down based on their requirements. Engineers can easily sign up for an OnScale Solve subscription which comes loaded with core hours ready to use to run simulations. This avoids any time wasted obtaining and configuring licenses or license keys on local hardware.

No licenses -> Just subscriptions

No license keys -> Just core-hours

A core-hour is a measurement of computational time. In OnScale, if you run one CPU for one hour, that is one core-hour. If you run 1000 CPUs for 1 hour, then that’s 1000 core-hours. The AI estimator will allow for engineers to view a simulation studies predicted simulation time and core-hour cost for different number of cores. This allows engineers to make suitable decisions on how quickly they need the results and how much they are willing to spend.

core-hour

Once your OnScale model has been set up, you can select the Simulator tab and you will be presented with the ability to Mesh & Estimate your model. This is required before submitting any job and this is where the OnScale Solve AI estimator will predict the time and cost to complete your simulations.

Meshing

After the meshing and estimations are completed, the Estimator drop-down will present the predicted Core Hours and Time for your job. There is also the ability to increase the hardware utilized for your simulation to reduce the computation time for an increase in core-hour cost. An adjustable slider allows you to adjust the hardware allocation to select a suitable cost and runtime that suits you.

          OnScale Solve

OnScale Solve AI estimators provides all users with accurate predictions of simulation runtimes and costs so that nothing is left to chance.

Getting Started with OnScale Solve

Engineers, designers, analysts, and current OnScale users can learn more about OnScale Solve and run their first cloud engineering simulation study by accessing these resources:

  • Create your Free account here.
  • Watch a quick guided video tour of the software, from log in to simulation.
  • Run your first simulation by following a 10-minute online tutorial.
  • Ask for technical support by emailing support@onscale.com.

With OnScale Solve you can work, collaborate, and share from any location and device. Ready to go? Create your free account today and start simulating with OnScale Solve! If you have any questions please contact us at info@onscale.com!

 

Jeff Dobson
Jeff Dobson

Jeff Dobson is a senior application engineer at OnScale and has recently completed an Engineering Doctorate at the University of Strathclyde in Glasgow, focused on NDT simulation. Jeff is an experienced FEA engineer with an expertise in advanced NDT simulations, such as modeling ultrasonic inspections of composite components. Jeff has over 7 years experience with OnScale and supports activity across current and future applications, whilst also managing consultancy projects and providing technical support.