Home » Uncategorized

UberCloud Voice October 2016

UberCloud celebrates 3rd year of its HPC Cloud Marketplace Service

Shopping MallAfter one year and 80+ engineering and scientific HPC cloud experiments, during the Supercomputing Conference Nov 2013, UberCloud opened the first (beta) version of its engineering cloud marketplace with then 5 stores providing cloud services from cloud hardware and engineering software vendors. Since then the number of stores grew to 40, and the trend from providers and users of the marketplace is now clearly accelerating. “When we started the marketplace 3 years ago the service we offered was all manual,” explained Wolfgang Gentzsch who founded UberCloud together with Burak Yenier in 2012. “But already then we were developing our HPC software container technology based on Docker which today provides a fully automated software packaging and porting environment and allows users to access their engineering workflow within seconds, at their fingertips, in any cloud. They don’t have to learn how to handle a new cloud user platform, because handling a software container provides the same look and feel identical to the engineer’s desktop.” Based on this technology UberCloud has also cracked the software licensing problem in the cloud because every container contains its own license server. In the meantime the UberCloud Marketplace has 40 software and cloud hardware stores, and growing.

Cloud Team 192: Thermal Modelling of a Fragrance Extraction Reactor in the Cloud with COMSOL Multiphysics

Team 192In this cloud project for High Performance Computing (HPC) in the Cloud, Stephan Savarese, Multiphysics Consultant and Founder at ForCES, wanted to find out how cloud computing resources can help in speeding up and enabling high performance FEM simulations with COMSOL Multiphysics® and COMSOL ServerTM. He used two COMSOL applications on the CPU 24/7 cloud: one 2D model and one 3D model of an industrial fragrance extraction boiler.  Both models use specific modeling for mass and heat transfer of fluid flows and immobile solids, built from the COMSOL Multiphysics Heat Transfer Module. These two models were chosen since they represent two frequent options for thermal and fluid flows models. The 2D model enables exploring a wide range of operating condition, while the 3D model is suitable for detailed analysis and optimization. Please read the detailed case study HERE.

Sorting Fact from Fiction: HPC-Enabled Engineering Simulations, On-Premises or in the Cloud

Ansys11HPC was once the sole province of corporations with money and resources to afford and use supercomputers for engineering simulations. Over time, HPC hardware and cloud resources became more powerful and affordable. This opened the door for small and mid-size companies  to use HPC too. Still, myths and misconceptions surround HPC, on-premises and in the cloud, which prevent adoption of HPC (both in-house and in the cloud) for product development, ultimately yielding less competitive companies! This paper (available for download from HPCwire and based on blogs from Wim Slagter, ANSYS Marketing Director for HPC and Cloud) aids engineers and directors in sorting fact from fiction. With these facts in hand, making decisions on how, when and where to use HPC becomes easier and more sensible.

SC16 Showcases Use of HPC and Cloud In Cancer Research

shutterstock_cancerThe effort to attack cancer with HPC resources has been growing for years. Indeed, it’s accurate to say the sequencing of the human genome was as much a tour de force of HPC as of the new DNA sequencers. Back in June, Department of Energy Secretary Ernst Moniz blogged on the effort (Supercomputers are key to the Cancer Moonshot) and in a few weeks the opening panel at SC16 is on Precision Medicine. Among the panelists are Warren Kibbe, director of the Center for Biomedical Informatics and Information Technology (CBIIT) at the NCI, which he helped establish. Steve Conway of IDC will moderate the panel Monday evening (November 14, 2016),HPC and Precision Medicine: Researchers Are on the Brink of Finding Cures to Cancer and Other Deadly Diseases within This Generation but Only with the Power of HPC. Read more details in HPCwire HERE.

Slidecast: Running HPC Simulation Workflows in Microsoft Azure

Tejas azure-300x216In this slidecast from the Microsoft Ignite Conference Tejas Karmarkar,Senior Program Manager, Microsoft Azure, describes how to run your HPC Simulations on Microsoft Azure – with UberCloud container technology. “High performance computing applications are some of the most challenging to run in the cloud due to requirements that can include fast processors, low-latency networking, parallel file systems, GPUs, and Linux. We show you how to run these engineering, research and scientific workloads in Microsoft Azure with performance equivalent to on-premises. We use customer case studies to illustrate the basic architecture and alternatives to help you get started with HPC in Azure.” See the slidecast on insideHPC HERE.

Cloud Case Study: CADFEM on Amazon AWS

CADFEMCADFEM was finding it hard to compete with larger organizations when bidding on major contracts, where computational needs are extremely high. “Anyone involved in simulation will tell you the industry has a constant need for faster and faster computers,” says Sweeney, managing director at CADFEM Ireland Ltd. “We have some very powerful workstations in our office, but when we were up against a firm with a 500-core, high-performance cluster, we were at a disadvantage.” Small firms often don’t have the budget to build such large clusters, but when cloud-computing services started becoming more widespread and affordable, new opportunities arose for CADFEM. “The cloud offered a cost-effective way to get access to high-performance computing,” Sweeney says. “We saw the opportunity to switch clusters on and off as required and pay only for what we use.” Read the case study HERE.

Is it cost-effective to outsource CFD (or any other CAE project) ?

OutsourceOutsourcing is being redefined.  It is becoming increasingly synonymous with forming ad hoc teams of specialist working together to solve complex challenges.  In today’s rush to market, product development requires a team equipped with diverse skills and outsourcing allows our clients to form the right team for the project.  Outsourcing can free up your in-house design department to focus on what they do best:  design great products.  This very informative article compares in-house cost for CFD engineers and overhead with the cost of outsourcing CFD projects. The article’s general conclusion that a 3rd party consultant can be the more cost-effective approach to meeting internal CFD demands should not be ignored by those considering CFD purchasing decisions.

A Comparison of CFD Software Packages

CFD PackagesThe website CFD-Online lists over 200 CFD related software packages, with new packages coming online monthly claiming capability and performance improvements over established packages. Such a variety can be a little overwhelming for those who are trying to identify which is the right tool for the job. While there have been a number of academic papers attempting quantitative comparisons of results obtained from competing software packages, more pragmatic comparisons between major packages in terms of ownership costs, usability and performance are needed. This review, based on the authors 15 years of experience working with most of the vendors discussed herein, will help fill this void.

© Copyright 2018 UberCloud™ - UberCloud is a trademark of TheUberCloud, INC. | Privacy Policy
Logo Header Menu

Credit Card Help

UberCloud Marketplace accepts international payments for products. All prices are in United States Dollars (USD $) unless specifically stated otherwise. We accept the following major card brands.
The CVC is usually the three digit number located on the back of the credit card. On some cards, the CVC is displayed on the front of the card and can be 4 digits long.
We take your privacy and security seriously. See our privacy policy, which defines the measures we take to secure your private information.
We use a well known payment processor based in San Francisco, California called Stripe. Your credit card information is processed by Stripe securely and we do not retain your credit card information on UberCloud's servers.