Best Practices for Running Computational Fluid Dynamics (CFD) Workloads on AWS

By Amazon Web Services

July 8, 2020

The scalable nature and variable demand of CFD workloads makes them well-suited for a cloud computing environment. Many of the AWS instance types, such as the compute family instance types, are designed to include support for this type of workload. AWS has network options that support extreme scalability and short turn-around time as necessary.

Fluid dynamics is the study of the motion of fluids, usually in the presence of an object. Typical fluid flows of interest to engineers and scientist include: flow in pipes, through engines, and around objects, such as buildings, automobiles, and airplanes. Computational fluid dynamics (CFD) is the study of these flows through computer simulation and modeling. CFD involves the solution of conservation equations (mass, momentum, energy, and others) in a finite domain.

A typical CFD simulation involves the following four steps.

  1. Define the Geometry

In some cases, this step is simple, such as modeling flow in a duct. In other cases, this step involves complex components and moving parts, such as modeling a gas turbine engine. For many cases, the geometry creation is extremely time-consuming. The geometry step is graphics intensive and requires a capable graphics workstation, preferably with a Graphics Processing Unit (GPU). Often, the geometry is provided by a designer, but the CFD engineer must “clean” the geometry for input into the flow solver.

  1. Generate the Mesh or Grid

Mesh generation is a critical step because computational accuracy is dependent on the size, cell location, and skewness of the cells. Mesh generation can be iterative with the solution, where fixes to the mesh are driven by an understanding of flow features and gradients in the solution. Meshing is frequently an interactive process and its elliptical nature generally requires a substantial amount of memory. Like geometry definition, generating a single mesh can take hours, days, weeks, and sometimes months.

  1. Solve for the solution

For some solutions, tens of thousands of cores (processors) run over weeks to achieve a solution. Conversely, some jobs may run in just minutes when scaled out appropriately. There are choices for model equations depending on the desired solution fidelity. The Navier-Stokes equations form the basis of the solved equations for most fluid calculations. The addition of chemical reactions, liquid and gas multi-phase flows, and many other physical properties create increasing complexity. For example, increasing the fidelity of turbulence modeling is achieved with various approximate equation sets such as Reynolds Average Navier-Stokes (RANS), Large Eddy Simulation (LES), Delayed Detached Eddy Simulation (DDES), and Direct Numerical Simulation (DNS). These models typically do not change the fundamental computational characteristics or scaling of the simulation.

  1. Post process through visualization

Examples of this step include the creation of images, video, and post processing of flow fields, such as creating total forces and moments. Similar to the geometry and mesh steps, this can be graphics and memory intensive CFD workloads that typically scale well on the cloud. Most codes rely on domain decomposition to distribute portions of the calculation to the compute nodes. A case can be run highly parallel to receive results in minutes, or large numbers of cases can run simultaneously as efficiently and cheaply as possible to allow the timely completion of all cases.

Why CFD on AWS?

AWS is a great place to run CFD cases. CFD workloads are typically MPI-based, tightly coupled workloads relying on a large number of cores across many nodes. Many of the AWS instance types, such as the compute family instance types, are designed to include support for this type of workload. AWS has network options that support extreme scalability and short turn-around time as necessary. Small CFD cases can be run on a single node, with a large number of cores, and do not require the use of multiple instances.

 

CFD workloads typically scale well on the cloud. Most codes rely on domain decomposition to distribute portions of the calculation to the compute nodes. A case can be run highly parallel to receive results in minutes, or large numbers of cases can run simultaneously as efficiently and cheaply as possible to allow the timely completion of all cases.

The cloud offers a quick way to deploy and turn around CFD w

orkloads at any scale without the need to own your own infrastructure. You can run jobs that once were in the realm of national labs or large industry. In just an hour or two, you can deploy CFD software, upload input files, launch compute nodes, and complete jobs on a large number of cores. When your job completes, results can be visualized and downloaded, and then all resources can be terminated – allowing you to only pay for what you use. If preferred, your results can be securely archived in cloud storage. Due to cloud scalability, you have the option to run multiple cases simultaneously with a dedicated cluster for each case.

The cloud accommodates the variable demand of CFD. Often, there is a need to run a large number of cases as quickly as possible. Situations can require a sudden burst of tens, to hundreds, to thousands of calculations immediately, and then perhaps noruns until the next cycle. The need to run a large number of cases could be for a preliminary design review, or perhaps a sweep of cases for the creation of a solution database. On the cloud, the cost is the same to run many jobs simultaneously, in parallel, as it is to run them serially, so you can get your data more quickly and at no extra cost. The cost savings in engineering time is an often forgotten part of cost analysis. Running in parallel can be an ideal solution for design optimization. On AWS, you can launch the cases you need when your case is ready, without waiting in a queue for available cluster resources.

Cloud computing is a strong choice for other CFD steps. You can easily launch a GPU instance, a high-memory instance, or a cluster of high-memory instances, to handle the geometry, meshing, and post-processing. With remote visualization software available to handle the display, you can manage the GPU instance running your post-processing visualization from any screen (laptop, desktop, web browser) as though you were working on a large workstation.

Read the full white paper to learn about best practices for running computational fluid dynamics (CFD) workloads on AWS and quick start tools.

Get started with running your CAE/CFD workloads now – fill the form and get a $100 AWS credit!

 

 

Return to Solution Channel Homepage
Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire