Cloudnumbers Expedites Cloud-Based Supercomputing

By Tiffany Trader

February 14, 2012

Configuring a cluster on a public cloud infrastructure such as Amazon Web Services potentially requires a lot of work. The various steps involve setting up the machines, dealing with the security keys, installing the applications, negotiating the administration, and more. Most HPC users would prefer to avoid this time-consuming process if possible. That’s where German startup Cloudnumbers comes in. The company provides everything the customer needs to get their HPC applications up and running in a matter of minutes. I recently had the chance to speak with Markus Schmidberger, Senior Community Manager for Cloudnumbers.com GmbH, to find out how.

The history of the Cloudnumbers goes back to Munich circa 2010, when company founders Erik Muttersbach, Markus Fensterer and Moritz v. Petersdorff-Campen began developing their idea for an HPC cloud environment. They contacted Markus Schmidberger in October 2010 after seeing his research on the topic, and further discussed the feasibility of moving HPC workloads to the cloud.

By the end of 2010, the group had written up a business plan and begun implementing a prototype. In March 2011, Cloudnumbers was founded with investment from angel investors. At that time, the company relocated from Munich to Berlin, Germany’s capital city. After an initial testing period of about two months, the company officially launched on July 4, 2011, providing a Web interface for computer clusters in the cloud. As of now, the company has over 1,300 registered users.

If you go to their website, you may notice a beta tag on their offering, but Schmidberger assures me this is a fully-functioning stable release. The beta designation has more to do with German law than any product short-comings. Based on German law, they would have to provide a level of security that is impractical at this stage. The beta label just makes it easier for them to operate in Europe, Schmidberger explained.

In case you’re concerned about security, the core functionality is the responsibility of the IaaS provider, but Cloudnumbers has added an extra security level on top of what Amazon uses. This means that all data are encrypted with 256 bit encryption and all connections between the local hardware and between the machines use SSL encryption. Despite these high levels of security, performance has not been affected in any significant way. It bears mentioning that all aspects of user authentication, personal data, passwords, billing and credit card information are located on a secure server in Germany and not in the cloud, in full compliance with safe harbor requirements.

Cloudnumbers does all the configuration of the computer cluster for their customers. Prospective users can point their browsers to the Web interface, where a five-step process results the configuration of a computer cluster. At that point, the cloud provider starts up the cluster and performs the complete install with all required applications. After that, the customer can access the cluster through any Web interface. “Everything is pre-installed so they don’t need any administration. Basically everything works out of the box,” Schmidberger explains. Setup takes about five minutes, and the entire configuration process takes between 6-10 minutes.

To use the service, customers only need to register with Cloudnumbers. They do not need a separate account with the public cloud provider, so there is only one bill. Every registered user gets five hours free, and after that the service costs about one dollar per hour per CPU. This is slightly more than what Amazon charges, but Cloudnumbers is providing something extra, a preinstalled cluster with preinstalled applications. While Cloudnumbers uses Amazon Web Services as their main Infrastructure-as-a-Service platform, they are currently adding resources from RackSpace and Eucalyptus, and are actively seeking to partner with smaller cloud providers as well.

Cloudnumbers offers pre-installed computer clusters in the cloud with pre-installed applications. Depending on their needs, users can select from R, OpenFoam, Python, Fortan, C/C++, as well as Gromacs, BLAST, Freemat and Perl. These come with the associated libraries for parallel computing, such as all the MPI libraries and so on. “We do all the hard work for setting up the computer cluster in the cloud. It’s integrated in our interface,” notes Schmidberger.

In analyzing the behavior of their customers, Schmidberger finds that about one-third require one shared-memory machine with 8-cores and 64 GB of main memory, and the other two-thirds set up computer clusters with about 10-15 machines. If you look for competitors, you may come across Cycle Computing, which offers very large clusters. In Schmidberger’s experience, Cloudnumbers’ customers haven’t required machines this large. Their customers tend to be of the small-to-medium sized variety, and are thus well-suited to small-to-medium sized clusters. They care about getting their high-performance applications to run on these clusters, Schmidberger’s notes, but are not as interested in the learning the administration side.

With that in mind, it’s perhaps not surprising that many of their customers require consulting services to help ease the transition to the cloud. They want to know how to get their code running in the cloud and then how to get the best performance. Initially, Cloudnumbers only planned to offer the cloud product, consulting was not part of the original business plan. But after receiving numerous requests for assistance, a consulting service was added in October of last year. The bulk of the service involves simple programming support in the way of code optimization, tips and tricks. In most cases, the actual coding is performed by the customers.

“We provide the complete HPC-as-a-Service package for our customers,” Schmidberger says. “We have the support, we have the consulting, and we have the interface and the resources, which they can use.”

To illustrate the way the consulting process works, Schmidberger cites one of their most well-known customers, Gazprom Germania, a holding company for a range of international oil and gas companies. Gazprom has a lot of financial code for risk analysis, based on the statistics software R. Cloudnumbers worked with Gazprom to parallelize the code, with the actual implementation being performed by Gazprom statisticians. After that, Gazprom simply logged into the Cloudnumbers test account, confirmed everything was in order, then switched to on-demand billing and started working on the Cloudnumbers machines.

While some customers require the complete support package, most just log on and get a bill every month. For these, Cloudnumbers doesn’t even know what workloads they are running, nor do they need to know.

The initial premise for the company was to close the gap for high-performance computing in the cloud in Europe. To get into the market in Europe, and to that point, their majority of their customers are from the EU, but they have several from the US, several from China and India. The numbers break down to roughly one-third from Europe and the rest from everywhere else. The diverse customer base includes academia, industry, the finance sector, biology firms, and machine engineering outfits.

Asked whether customers have had any difficulty transferring initial data sets to the cloud, Schmidberger responded that bandwidth was not a problem since, again, the solution is designed for small-to-medium sized companies with average data sets in GB range, not on the level of TB. In fact, Schmidberger estimates they’ve never had a customer with more than 1-2 TB of data. So far, not one of their customers has complained that they’ve had a problem loading data from their local machine into the cloud.

On the somewhat sticky topic of whether HPC workloads are suitable for the cloud, Schmidberger is convinced of the merits of this approach. “While we will continue to require supercomputers for huge analysis runs,” he says “for the small-to-medium sized analysis, HPC works very well in the cloud.”

To get the customer perspective on this new cloud service, I reached out to Dr. Karsten Knothe, IT Project Manager for Gazprom Germania, mentioned earlier. Before moving to Cloudnumbers, Gazprom ran their workloads in-house on a simple desktop-PC with multicore processors. When they started thinking about transitioning to the cloud they briefly considered going directly to Amazon, but they needed more functionality. “For us it’s important to get not only a naked virtual machine but a configured cluster with the needed software installed,” Dr. Knothe comments.

Prior to the cloud transition, one calculation run would take more than 12 hours. “Now we do one calculation in about 15 minutes,” notes Dr. Knothe. Not only do they save time, but the solution allows them to do additional analysis by changing the parameters of their calculation.

Despite being satisfied with these benefits, Dr. Knothe mentioned that he would like to see a few additions to the product. Specifically, he has requested additional communication functions, so that starting and stopping sessions and finishing calculations would trigger an email notification.

Looking ahead, Schmidberger was excited to announce that Cloudnumbers is currently developing a hybrid cloud solution, which offers the promise of “perfect scalability.” Due to privacy or security concerns, many companies have chosen private clouds to run their analyses, but very often those companies have some workloads which would benefit from the cloud. A hybrid approach allows these companies to extend their private cloud with public cloud resources. Currently, the company has a prototype connection in place with Eucalyptus and Amazon, with a connection to OpenNebula in the works as well. A final release should be available soon.

“We set up a very generous framework in the background, which gives us the opportunity to connect to many different Infrastructure-as-a-Service providers,” Schmidberger stated. “So if we get a request from any customer that they have a private cloud running on whatever, we will be able to connect to this cloud within two months.”

As a new company, Cloudnumbers is proactive in seeking customer feedback, which should be good news to Gazprom.

Subscribe to HPCwire's Weekly Update!

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

Weekly Twitter Roundup (Feb. 23, 2017)

February 23, 2017

Here at HPCwire, we aim to keep the HPC community apprised of the most relevant and interesting news items that get tweeted throughout the week. Read more…

By Thomas Ayres

HPE Server Shows Low Latency on STAC-N1 Test

February 22, 2017

The performance of trade and match servers can be a critical differentiator for financial trading houses. Read more…

By John Russell

HPC Financial Update (Feb. 2017)

February 22, 2017

In this recurring feature, we’ll provide you with financial highlights from companies in the HPC industry. Check back in regularly for an updated list with the most pertinent fiscal information. Read more…

By Thomas Ayres

Rethinking HPC Platforms for ‘Second Gen’ Applications

February 22, 2017

Just what constitutes HPC and how best to support it is a keen topic currently. Read more…

By John Russell

HPE Extreme Performance Solutions

O&G Companies Create Value with High Performance Remote Visualization

Today’s oil and gas (O&G) companies are striving to process datasets that have become not only tremendously large, but extremely complex. And the larger that data becomes, the harder it is to move and analyze it – particularly with a workforce that could be distributed between drilling sites, offshore rigs, and remote offices. Read more…

HPC Technique Propels Deep Learning at Scale

February 21, 2017

Researchers from Baidu’s Silicon Valley AI Lab (SVAIL) have adapted a well-known HPC communication technique to boost the speed and scale of their neural network training and now they are sharing their implementation with the larger deep learning community. Read more…

By Tiffany Trader

IDC: Will the Real Exascale Race Please Stand Up?

February 21, 2017

So the exascale race is on. And lots of organizations are in the pack. Government announcements from the US, China, India, Japan, and the EU indicate that they are working hard to make it happen – some sooner, some later. Read more…

By Bob Sorensen, IDC

ExxonMobil, NCSA, Cray Scale Reservoir Simulation to 700,000+ Processors

February 17, 2017

In a scaling breakthrough for oil and gas discovery, ExxonMobil geoscientists report they have harnessed the power of 717,000 processors – the equivalent of 22,000 32-processor computers – to run complex oil and gas reservoir simulation models. Read more…

By Doug Black

TSUBAME3.0 Points to Future HPE Pascal-NVLink-OPA Server

February 17, 2017

Since our initial coverage of the TSUBAME3.0 supercomputer yesterday, more details have come to light on this innovative project. Of particular interest is a new board design for NVLink-equipped Pascal P100 GPUs that will create another entrant to the space currently occupied by Nvidia's DGX-1 system, IBM's "Minsky" platform and the Supermicro SuperServer (1028GQ-TXR). Read more…

By Tiffany Trader

HPC Technique Propels Deep Learning at Scale

February 21, 2017

Researchers from Baidu’s Silicon Valley AI Lab (SVAIL) have adapted a well-known HPC communication technique to boost the speed and scale of their neural network training and now they are sharing their implementation with the larger deep learning community. Read more…

By Tiffany Trader

IDC: Will the Real Exascale Race Please Stand Up?

February 21, 2017

So the exascale race is on. And lots of organizations are in the pack. Government announcements from the US, China, India, Japan, and the EU indicate that they are working hard to make it happen – some sooner, some later. Read more…

By Bob Sorensen, IDC

TSUBAME3.0 Points to Future HPE Pascal-NVLink-OPA Server

February 17, 2017

Since our initial coverage of the TSUBAME3.0 supercomputer yesterday, more details have come to light on this innovative project. Of particular interest is a new board design for NVLink-equipped Pascal P100 GPUs that will create another entrant to the space currently occupied by Nvidia's DGX-1 system, IBM's "Minsky" platform and the Supermicro SuperServer (1028GQ-TXR). Read more…

By Tiffany Trader

Tokyo Tech’s TSUBAME3.0 Will Be First HPE-SGI Super

February 16, 2017

In a press event Friday afternoon local time in Japan, Tokyo Institute of Technology (Tokyo Tech) announced its plans for the TSUBAME3.0 supercomputer, which will be Japan’s “fastest AI supercomputer,” Read more…

By Tiffany Trader

Drug Developers Use Google Cloud HPC in the Fight Against ALS

February 16, 2017

Within the haystack of a lethal disease such as ALS (amyotrophic lateral sclerosis / Lou Gehrig’s Disease) there exists, somewhere, the needle that will pierce this therapy-resistant affliction. Read more…

By Doug Black

Azure Edges AWS in Linpack Benchmark Study

February 15, 2017

The “when will clouds be ready for HPC” question has ebbed and flowed for years. Read more…

By John Russell

Is Liquid Cooling Ready to Go Mainstream?

February 13, 2017

Lost in the frenzy of SC16 was a substantial rise in the number of vendors showing server oriented liquid cooling technologies. Three decades ago liquid cooling was pretty much the exclusive realm of the Cray-2 and IBM mainframe class products. That’s changing. We are now seeing an emergence of x86 class server products with exotic plumbing technology ranging from Direct-to-Chip to servers and storage completely immersed in a dielectric fluid. Read more…

By Steve Campbell

Cray Posts Best-Ever Quarter, Visibility Still Limited

February 10, 2017

On its Wednesday earnings call, Cray announced the largest revenue quarter in the company’s history and the second-highest revenue year. Read more…

By Tiffany Trader

For IBM/OpenPOWER: Success in 2017 = (Volume) Sales

January 11, 2017

To a large degree IBM and the OpenPOWER Foundation have done what they said they would – assembling a substantial and growing ecosystem and bringing Power-based products to market, all in about three years. Read more…

By John Russell

US, China Vie for Supercomputing Supremacy

November 14, 2016

The 48th edition of the TOP500 list is fresh off the presses and while there is no new number one system, as previously teased by China, there are a number of notable entrants from the US and around the world and significant trends to report on. Read more…

By Tiffany Trader

Lighting up Aurora: Behind the Scenes at the Creation of the DOE’s Upcoming 200 Petaflops Supercomputer

December 1, 2016

In April 2015, U.S. Department of Energy Undersecretary Franklin Orr announced that Intel would be the prime contractor for Aurora: Read more…

By Jan Rowell

Enlisting Deep Learning in the War on Cancer

December 7, 2016

Sometime in Q2 2017 the first ‘results’ of the Joint Design of Advanced Computing Solutions for Cancer (JDACS4C) will become publicly available according to Rick Stevens. He leads one of three JDACS4C pilot projects pressing deep learning (DL) into service in the War on Cancer. Read more…

By John Russell

D-Wave SC16 Update: What’s Bo Ewald Saying These Days

November 18, 2016

Tucked in a back section of the SC16 exhibit hall, quantum computing pioneer D-Wave has been talking up its new 2000-qubit processor announced in September. Forget for a moment the criticism sometimes aimed at D-Wave. This small Canadian company has sold several machines including, for example, ones to Lockheed and NASA, and has worked with Google on mapping machine learning problems to quantum computing. In July Los Alamos National Laboratory took possession of a 1000-quibit D-Wave 2X system that LANL ordered a year ago around the time of SC15. Read more…

By John Russell

IBM Wants to be “Red Hat” of Deep Learning

January 26, 2017

IBM today announced the addition of TensorFlow and Chainer deep learning frameworks to its PowerAI suite of deep learning tools, which already includes popular offerings such as Caffe, Theano, and Torch. Read more…

By John Russell

HPC Startup Advances Auto-Parallelization’s Promise

January 23, 2017

The shift from single core to multicore hardware has made finding parallelism in codes more important than ever, but that hasn’t made the task of parallel programming any easier. Read more…

By Tiffany Trader

CPU Benchmarking: Haswell Versus POWER8

June 2, 2015

With OpenPOWER activity ramping up and IBM’s prominent role in the upcoming DOE machines Summit and Sierra, it’s a good time to look at how the IBM POWER CPU stacks up against the x86 Xeon Haswell CPU from Intel. Read more…

By Tiffany Trader

Leading Solution Providers

Nvidia Sees Bright Future for AI Supercomputing

November 23, 2016

Graphics chipmaker Nvidia made a strong showing at SC16 in Salt Lake City last week. Read more…

By Tiffany Trader

BioTeam’s Berman Charts 2017 HPC Trends in Life Sciences

January 4, 2017

Twenty years ago high performance computing was nearly absent from life sciences. Today it’s used throughout life sciences and biomedical research. Genomics and the data deluge from modern lab instruments are the main drivers, but so is the longer-term desire to perform predictive simulation in support of Precision Medicine (PM). There’s even a specialized life sciences supercomputer, ‘Anton’ from D.E. Shaw Research, and the Pittsburgh Supercomputing Center is standing up its second Anton 2 and actively soliciting project proposals. There’s a lot going on. Read more…

By John Russell

Tokyo Tech’s TSUBAME3.0 Will Be First HPE-SGI Super

February 16, 2017

In a press event Friday afternoon local time in Japan, Tokyo Institute of Technology (Tokyo Tech) announced its plans for the TSUBAME3.0 supercomputer, which will be Japan’s “fastest AI supercomputer,” Read more…

By Tiffany Trader

IDG to Be Bought by Chinese Investors; IDC to Spin Out HPC Group

January 19, 2017

US-based publishing and investment firm International Data Group, Inc. (IDG) will be acquired by a pair of Chinese investors, China Oceanwide Holdings Group Co., Ltd. Read more…

By Tiffany Trader

Dell Knights Landing Machine Sets New STAC Records

November 2, 2016

The Securities Technology Analysis Center, commonly known as STAC, has released a new report characterizing the performance of the Knight Landing-based Dell PowerEdge C6320p server on the STAC-A2 benchmarking suite, widely used by the financial services industry to test and evaluate computing platforms. The Dell machine has set new records for both the baseline Greeks benchmark and the large Greeks benchmark. Read more…

By Tiffany Trader

What Knights Landing Is Not

June 18, 2016

As we get ready to launch the newest member of the Intel Xeon Phi family, code named Knights Landing, it is natural that there be some questions and potentially some confusion. Read more…

By James Reinders, Intel

Is Liquid Cooling Ready to Go Mainstream?

February 13, 2017

Lost in the frenzy of SC16 was a substantial rise in the number of vendors showing server oriented liquid cooling technologies. Three decades ago liquid cooling was pretty much the exclusive realm of the Cray-2 and IBM mainframe class products. That’s changing. We are now seeing an emergence of x86 class server products with exotic plumbing technology ranging from Direct-to-Chip to servers and storage completely immersed in a dielectric fluid. Read more…

By Steve Campbell

KNUPATH Hermosa-based Commercial Boards Expected in Q1 2017

December 15, 2016

Last June tech start-up KnuEdge emerged from stealth mode to begin spreading the word about its new processor and fabric technology that’s been roughly a decade in the making. Read more…

By John Russell

  • arrow
  • Click Here for More Headlines
  • arrow
Share This