At the Nexus of Grid, Cloud and HPC

By Dennis Barker

October 17, 2008

What’s the big difference between cloud computing and grid computing? The goal of cloud computing is to put system administrators out of work.

That’s one way of looking at it, at least. Steve Armentrout, CEO of Parabon Computation, says that was the perspective tossed out by a couple of Google and IBM reps at a panel discussion in which he recently participated. Armentrout suggests a less Dickensian way of looking at it: cloud computing is about “providing a datacenter that is fully automated.” (More on cloud versus grid later.)

Armentrout sees cloud and grid as complementary in some ways — bipartisan, you might say — but he is an unapologetic grid partisan — especially when it comes to his company’s collection of solutions. “We have no intention of changing our grid stripes,” he says. “What Parabon provides is grid software as a service. We enable individuals with grid applications to scale them across a large infrastructure without having to go out and buy hardware. They can just buy capacity as it’s needed. It’s a pay-as-you-go model.”

Basically, Parabon’s Frontier Grid Services offering is a high-performance computing utility. If you need a few thousand nodes to run a financial risk model or some other long and winding analysis, Parabon will hook you up to the resources you need. “We broker computation,” Armentrout says. Like its customers, the company doesn’t own datacenters. What it has is contracts with universities and institutions with big server farms and HPC clusters to aggregate their unused capacity. “All that compute power we use to provide computation on demand,” explains Armentrout.

There’s a lot of computational capability sitting around doing nothing, Armentrout says. “You often hear the estimate that standard servers are typically running at anywhere from 5 to 20 percent capacity. Just think of 80 percent capacity going to waste. Even in a virtualized environment, seldom do you see capacity usage at over 50 percent. All that idle capacity allows us to deploy across a university datacenter, for example, and execute large-scale jobs in the background. Frontier is our technology that lets us capture that unused capacity and make it available as a grid service.”

Parabon’s technology can be used, as just described, across worldwide “public” resources like campus networks — that’s the Parabon Computation Grid — but can also be applied to a company’s own network as the Frontier Enterprise Grid.
 
Parabon built its platform around the Frontier Grid Server, which provides grid services and shared resources to users and developers, whether using the Internet-based Parabon Computation Grid or an in-house Frontier Enterprise grid. The Frontier Grid Server manages execution of jobs across hundreds or thousands of compute nodes. “It can scale up to arbitrarily large grids,” Armentrout says. “Tens of thousands of machines.” Frontier always reserves excess capacity to handle unexpected scale-out demands, he says.

The Frontier Compute Engine is the agnostic agent application that runs on each grid node to actually do the work. It executes tasks only when the resource, the virtual machine in many cases, is not handling a primary task. “Frontier runs as a low-priority process,” Armentrout says, “so if running in a virtualized datacenter — a cloud, you could say — the Compute Engine backs off if a request comes in from the cloud application. It takes precedence. But when resources are not busy, we can fully saturate the datacenter during that unused period of time.”

For example, Parabon might have an arrangement with a research facility in Australia to use its cluster when the scientists are home at night. That could be prime work time for scientists on the other side of the globe. That’s when Frontier could saturate compute nodes to calculate solutions more quickly.

Parabon just released a browser-based interface called the Dashboard that provides an intuitive front-end to the Frontier Grid Platform. “It lets you easily monitor a job, kill a job, assign resources, plus some back-office and accounting functions like looking up how much you’re paying for use,” Armentrout says.

Parabon’s pricing structure is better explained by the company, but the basic idea is that customers pay for units of computational power using a formula that involves kilo-cap hours.

The company provides an API and suite of tools to simplify adapting applications to take advantage of Frontier grid capabilities. And there’s a collection of Frontier-ready programs for applications, including data mining and biological modeling. “It’s kind of like Apple’s App Store but for distributed applications,” Armentrout analogizes. 

Parabon has been around since 2000, when it introduced “the first commercial grid,” Armentrout says. Customers include not just scientific researchers, but also financial analysts, commercial enterprises with high-end analytical demands, bioinformatics, traditional HPC users and government agencies. “Our customers are doing modeling and simulation with very large models, immense data sets,” he explains. “We enable them to run not just one complex scenario but 10,000 scenarios. With Frontier you can explore an entire space of possibilities at once instead of running one simulation, then another, then another.”

Grid vs. Cloud: Parabon-Style

“In terms of grid vs. cloud, there’s lots of confusion around those two terms,” Armentrout says. “But, honestly, the fact that cloud has so much hype surrounding it now makes it easier for us to clarify to customers the benefits of grid computing. Grid, I think, is becoming clearer in people’s minds, while cloud is still, if I might say it, a ‘cloudy’ term.”

There are certainly commonalities, he says: computational utility, virtualized use of computing resources, eliminating the need for dedicated resources and dramatically improved price/performance. “But cloud computing is more about auto-provisioning virtual machines,” explains Armentrout. “It’s about software that lets you go out into a cloud infrastructure, a virtualized datacenter, and say give me one or two VMs and get them in an automated and orderly way. It’s about a datacenter that is completely automated. Sure, customers can scale up and down — that’s one of the benefits of the model — but they typically don’t scale in large-scale numbers. That’s the nature of most Web applications, which is typically what runs in the cloud. In that environment, you still have a lot of capacity that’s available.” 

On the other hand, he believes that grid computing is all about massive parallelization and running large-scale jobs on unused capacity rather than dedicated capacity. The goal is to accelerate large jobs from days to minutes and hours to seconds, and grid computing can enable computations that “just aren’t possible,” he says.

“The folks we’re talking to understand they need grid-scale compute capacity, and that’s not something they’ll get from a pure cloud approach,” Armentrout says. “We routinely run jobs on several thousand machines. It’s that mass parallelization that you just wouldn’t run in the cloud. You want a job done in 5 minutes, not days. Our grid service reaches out to thousands and thousands of boxes and returns an answer in minutes.”

“We’ve got a high-performance solution that works for our customers. We can take advantage of a cloud infrastructure, but we don’t need to chase the cloud phenomenon.”

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!

UCSD, AIST Forge Tighter Alliance with AI-Focused MOU

January 18, 2018

The rich history of collaboration between UC San Diego and AIST in Japan is getting richer. The organizations entered into a five-year memorandum of understanding on January 10. The MOU represents the continuation of a 1 Read more…

By Tiffany Trader

New Blueprint for Converging HPC, Big Data

January 18, 2018

After five annual workshops on Big Data and Extreme-Scale Computing (BDEC), a group of international HPC heavyweights including Jack Dongarra (University of Tennessee), Satoshi Matsuoka (Tokyo Institute of Technology), Read more…

By John Russell

Researchers Measure Impact of ‘Meltdown’ and ‘Spectre’ Patches on HPC Workloads

January 17, 2018

Computer scientists from the Center for Computational Research, State University of New York (SUNY), University at Buffalo have examined the effect of Meltdown and Spectre security updates on the performance of popular H Read more…

By Tiffany Trader

HPE Extreme Performance Solutions

HPE and NREL Take Steps to Create a Sustainable, Energy-Efficient Data Center with an H2 Fuel Cell

As enterprises attempt to manage rising volumes of data, unplanned data center outages are becoming more common and more expensive. As the cost of downtime rises, enterprises lose out on productivity and valuable competitive advantage without access to their critical data. Read more…

Fostering Lustre Advancement Through Development and Contributions

January 17, 2018

Six months after organizational changes at Intel's High Performance Data (HPDD) division, most in the Lustre community have shed any initial apprehension around the potential changes that could affect or disrupt Lustre Read more…

By Carlos Aoki Thomaz

UCSD, AIST Forge Tighter Alliance with AI-Focused MOU

January 18, 2018

The rich history of collaboration between UC San Diego and AIST in Japan is getting richer. The organizations entered into a five-year memorandum of understandi Read more…

By Tiffany Trader

New Blueprint for Converging HPC, Big Data

January 18, 2018

After five annual workshops on Big Data and Extreme-Scale Computing (BDEC), a group of international HPC heavyweights including Jack Dongarra (University of Te Read more…

By John Russell

Researchers Measure Impact of ‘Meltdown’ and ‘Spectre’ Patches on HPC Workloads

January 17, 2018

Computer scientists from the Center for Computational Research, State University of New York (SUNY), University at Buffalo have examined the effect of Meltdown Read more…

By Tiffany Trader

Fostering Lustre Advancement Through Development and Contributions

January 17, 2018

Six months after organizational changes at Intel's High Performance Data (HPDD) division, most in the Lustre community have shed any initial apprehension aroun Read more…

By Carlos Aoki Thomaz

When the Chips Are Down

January 11, 2018

In the last article, "The High Stakes Semiconductor Game that Drives HPC Diversity," I alluded to the challenges facing the semiconductor industry and how that may impact the evolution of HPC systems over the next few years. I thought I’d lift the covers a little and look at some of the commercial challenges that impact the component technology we use in HPC. Read more…

By Dairsie Latimer

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

Momentum Builds for US Exascale

January 9, 2018

2018 looks to be a great year for the U.S. exascale program. The last several months of 2017 revealed a number of important developments that help put the U.S. Read more…

By Alex R. Larzelere

ANL’s Rick Stevens on CANDLE, ARM, Quantum, and More

January 8, 2018

Late last year HPCwire caught up with Rick Stevens, associate laboratory director for computing, environment and life Sciences at Argonne National Laboratory, f Read more…

By John Russell

Inventor Claims to Have Solved Floating Point Error Problem

January 17, 2018

"The decades-old floating point error problem has been solved," proclaims a press release from inventor Alan Jorgensen. The computer scientist has filed for and Read more…

By Tiffany Trader

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

Japan Unveils Quantum Neural Network

November 22, 2017

The U.S. and China are leading the race toward productive quantum computing, but it's early enough that ultimate leadership is still something of an open questi Read more…

By Tiffany Trader

AMD Showcases Growing Portfolio of EPYC and Radeon-based Systems at SC17

November 13, 2017

AMD’s charge back into HPC and the datacenter is on full display at SC17. Having launched the EPYC processor line in June along with its MI25 GPU the focus he Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

IBM Begins Power9 Rollout with Backing from DOE, Google

December 6, 2017

After over a year of buildup, IBM is unveiling its first Power9 system based on the same architecture as the Department of Energy CORAL supercomputers, Summit a Read more…

By Tiffany Trader

Fast Forward: Five HPC Predictions for 2018

December 21, 2017

What’s on your list of high (and low) lights for 2017? Volta 100’s arrival on the heels of the P100? Appearance, albeit late in the year, of IBM’s Power9? Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Leading Solution Providers

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

Perspective: What Really Happened at SC17?

November 22, 2017

SC is over. Now comes the myriad of follow-ups. Inboxes are filled with templated emails from vendors and other exhibitors hoping to win a place in the post-SC thinking of booth visitors. Attendees of tutorials, workshops and other technical sessions will be inundated with requests for feedback. Read more…

By Andrew Jones

Tensors Come of Age: Why the AI Revolution Will Help HPC

November 13, 2017

Thirty years ago, parallel computing was coming of age. A bitter battle began between stalwart vector computing supporters and advocates of various approaches to parallel computing. IBM skeptic Alan Karp, reacting to announcements of nCUBE’s 1024-microprocessor system and Thinking Machines’ 65,536-element array, made a public $100 wager that no one could get a parallel speedup of over 200 on real HPC workloads. Read more…

By John Gustafson & Lenore Mullin

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Flipping the Flops and Reading the Top500 Tea Leaves

November 13, 2017

The 50th edition of the Top500 list, the biannual publication of the world’s fastest supercomputers based on public Linpack benchmarking results, was released Read more…

By Tiffany Trader

GlobalFoundries, Ayar Labs Team Up to Commercialize Optical I/O

December 4, 2017

GlobalFoundries (GF) and Ayar Labs, a startup focused on using light, instead of electricity, to transfer data between chips, today announced they've entered in Read more…

By Tiffany Trader

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

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