Much focus is directed towards hardware when it comes to parallel performance scalability of solving massive engineering problems. When distributing a large partitioned CFD or FEA model over many nodes, the lower latency network becomes exponentially more important as the number of nodes increases. However, for today’s post, I would like to shift attention away from the hardware and take a short look at what some independent software vendors (ISV) do on the software side to make sure that computational cores sit idle as little as possible.

CONVERGE CFD
Convergent Science’s CONVERGE CFD code takes a less traditional approach, implementing Adaptive Mesh Refinement (AMR) into their solver. AMR is not unique to CONVERGE–it has been implemented in many software including open source codes like Gerris–however, one of CONVERGE’s main applications is the internal combustion engine where moving boundaries and high gradients are the perfect application for using AMR.

In the internal combustion engine, locations of high gradient may move from the valves to the injector tip to the spray region. To obtain the transient solution and maintain high fidelity in these high gradient locations the orthogonal mesh elements may be sub-divided into 8 smaller elements multiple times.

Because individual compute cores, in general, solve continuous regions of the domain–to minimize communication with other cores–any new elements added to the domain will invariably be added to one core. When they’re subtracted, only one core may see the computation benefit of having less elements to solve. The AMR would cause major load imbalance were it not for the built in load-balancing algorithm. Of course load-balancing itself takes computational time, so the CONVERGE user can specify a time interval for when to re-balance the cells over all the cores.

Untitled

CONVERGE load balance can be monitored using Rescale’s Live Tailing feature

In summary:

  • AMR reduces the overall computational cost and increases the solution accuracy compared to statically meshed domains
  • AMR ensures that computationally expensive regions are not expensive throughout the entire simulation
  • AMR settings can be customized to match the user’s desired solution accuracy
  • Built-in load balancing ensures that cores don’t sit idle waiting for other cores to solve computationally expensive regions

CONVERGE is available on demand on Rescale and is now easier than ever to run in just 4 easy steps:
(1) Select CONVERGE from the analysis list
(2) Select the number of cores
(3) Upload zip file of inputs
(4) Click “Submit” to run the job

LS-DYNA
When it comes to solving mechanical problems, non-linear jobs are some of the most computationally expensive to solve. The premier non-linear solver is LS-DYNA, developed by Livermore Software Technology Corporation (LSTC) and integrated in many third-party packages for its excellent reputation. Like Convergent Science, LSTC focuses its main effort on the development of its solvers.

The mechanical problems which deal with plasticity and high deformations require a non-linear solver. One of the main applications for this type of simulation is the crash-test simulation. The point of impact sees the most deformation and requires the most computation to solve. The traditional Recursive Coordinate Bisection method (RCB) approach splits the domain along its widest axis, leaving the front of the car to be solved by a single core, while the rest of the car, which sees no deformation, is solved by all the other nodes. This kind of partitioning causes bad load imbalance.

As a solution, LS-DYNA allows the user to specify several decomposition settings. For example, this allows the user to partition the domain of a car model into small slivers length-wise. This kind of decomposition spreads the computationally expensive regions among all cores when modeling a head-on crash. Side impact crash simulations would not benefit from this decomposition. A more in-depth description is excellently explained here.

On Rescale, the user may add decomposition parameters by specifying a “pfile”. The pfile may contain a definition to specify the parts with sliding contacts (part 6) and the scaling factor in certain directions (scale y by 24x):

To use a pfile on Rescale, specify it from the Analysis command line. To run a single-precision mpp-hybrid (version 7.1.1) crash simulation over 64 cores (8 dmp ranks each utilizing 8 smp threads) the Rescale user would run:

In short:

  • LS-DYNA’s RCB decomposition algorithm allows custom specification of important model parts and scaling along 1 or more axes
  • LS-DYNA provides a hybrid mpp solver which uses MPI as well as openMP technology to most efficiently scale very large problems
  • The custom decomposition settings can be easily set in a pfile, so when experimenting with decomposition, the user will only have to re-upload a small file to Rescale as opposed to having to change and re-upload the large model file

Both LS-DYNA and CONVERGE are available on Rescale with short-term or hourly on-demand licensing. Please contact support@rescale.com if you are interested in running these software on Rescale.

This article was written by Mulyanto Poort.

blog-post3

Graz, Austria – Rescale, Inc. and AVL List GmbH are pleased to announce a technology partnership that allows users of AVL FIRE®, a powerful, multi-purpose, thermo-fluid dynamics CFD software product to run on the Rescale simulation platform. AVL FIRE® users now have the ability to run their simulations in the cloud, on demand across thousands of cores, to address their most complex simulation workflows, using Rescale’s highly scalable web-based platform.

“We are very excited to offer a comprehensive suite of features to AVL customers through our alliance with AVL,” said Joris Poort, CEO, Rescale, Inc.  “Most notably, AVL FIRE® users now have access to virtually unlimited high-performance computing resources, native platform integration with AVL FIRE®, and an intuitive user interface – securely accessible through any web browser.” Rescale’s platform allows AVL customers to significantly reduce simulation runtimes and expand internal simulation workflow capabilities with seamless access to on-demand software and hardware resources and no downloads or upfront costs. Rescale’s workflow tools enable engineers to easily set up design of experiments and formulate optimizations to develop innovative designs. Customers can run AVL FIRE®  with confidence, as Rescale adheres to the highest industry level security standards, trusted by Fortune 500 enterprises.

“Our alliance with Rescale will now empower our global AVL FIRE® customers with a scalable on-demand capability to run AVL’s powerful 3D CFD software,” said Maik Suffa, Group Product Manager CFD, at AVL.  “We share Rescale’s dedication to solving customer problems related to research and development in automotive and process engineering. AVL is extremely excited that our particular emphasis on ease of use, short turnaround times and high end modeling capabilities for sprays, combustion, heat transfer, and multi-phase flows will now be enabled on Rescale.”

For more information about Rescale and AVL List GmbH:

Rescale: http://www.rescale.com/
AVL List GmbH: http://www.avl.com/

About Rescale

Rescale provides a secure, pay-per-use, web-based platform that helps engineers and scientists build, compute, and analyze large simulations on demand. Headquartered in San Francisco, CA, Rescale’s customers include global Fortune 500 companies in the aerospace, automotive, life sciences, and energy sectors.

About AVL List GmbH

AVL is the world’s largest independent company for development, simulation and testing technology of powertrains (hybrid, combustion engines, transmission, electric drive, batteries and software) for passenger cars, trucks and large engines. AVL with its headquarters in Graz, Austria has 45 affiliates and more than 6600 employees worldwide

One of AVL’s business areas is Advanced Simulation Technologies, which develops simulation software focusing on design and optimization of powertrain systems covering all phases of the development process.

This article was written by Ilea Graedel.

blog-post

Rescale provides a platform where its users (mostly engineers and scientists) can run their computer simulations on demand in the cloud. At a high level, running these computer simulations require two steps. First, an engineer or a scientist has to design a scientific model to test his/her hypothesis. And secondly, he/she has to set up a computer simulation so that the result is obtained in a desired time period. These simulations, however, are usually complex workflows that require high performance computers that are not always available to the user. Rescale helps engineers and scientists set up and run a complex simulation with a few clicks of a mouse button, producing results faster than most in-house clusters.

Improving the user interface (UI) of our platform, therefore, is critical to the problem that we set out to solve. An intuitive UI will not only save hours for existing users, but it will also lower the bar for other engineers and scientists who previously could not easily scale their simulations in cloud. Previously, we have written about the change in our development stack, and today we’d like to share three features that will help our users set up a simulation on the Rescale platform.

1. Job Visualizations

job-setup

Based on our previous usage analytics, we figured out which simulation workflows are most frequently run by our users. For these simulation types, the new platform will provide a visual aide-which will also update based on users’ input. Users can also jump to different parts of their setup by simply clicking on one of the icons.

2. Core-to-Instance Mapping

hardware

Knowing the number of cores available for every node is important in parallelizing a simulation. The visualization of core-to-instance mapping will inform users of this information without any conversion charts or tables.

3. License Options

license

One of the main requirements of running computer simulations is acquiring a license, which could cost up to thousands of dollars up front. On Rescale’s platform, however, users can utilize our “on-demand” licensing option for select software to pay only for the hours they use. This process is made easier in the new UI, as users can simply choose the best licensing option for them.

These are the highlights of the new UI that will soon be available. If you’re interested in following our progress, please subscribe to our community newsletter on the top right corner.

This article was written by Rescale.