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!

China’s Expanding Effort to Win in Microchips

July 27, 2017

The global battle for preeminence, or at least national independence, in semiconductor technology and manufacturing continues to heat up with Europe, China, Japan, and the U.S. all vying for sway. A fascinating article ( Read more…

By John Russell

Hyperion: Storage to Lead HPC Growth in 2016-2021

July 27, 2017

Global HPC external storage revenues will grow 7.8% over the 2016-2021 timeframe according to an updated forecast released by Hyperion Research this week. HPC server sales, by comparison, will grow a modest 5.8% to $14.8 Read more…

By John Russell

Exascale FY18 Budget – The Senate Provides Their Input

July 27, 2017

In the federal budgeting world, “regular order” is a meaningful term that is fondly remembered by members of both the Congress and the Executive Branch. Regular order is the established process whereby an Administrat Read more…

By Alex R. Larzelere

HPE Extreme Performance Solutions

HPE Servers Deliver High Performance Remote Visualization

Whether generating seismic simulations, locating new productive oil reservoirs, or constructing complex models of the earth’s subsurface, energy, oil, and gas (EO&G) is a highly data-driven industry. Read more…

India Plots Three-Phase Indigenous Supercomputing Strategy

July 26, 2017

Additional details on India's plans to stand up an indigenous supercomputer came to light earlier this week. As reported in the Indian press, the Rs 4,500-crore (~$675 million) supercomputing project, approved by the Ind Read more…

By Tiffany Trader

Exascale FY18 Budget – The Senate Provides Their Input

July 27, 2017

In the federal budgeting world, “regular order” is a meaningful term that is fondly remembered by members of both the Congress and the Executive Branch. Reg Read more…

By Alex R. Larzelere

India Plots Three-Phase Indigenous Supercomputing Strategy

July 26, 2017

Additional details on India's plans to stand up an indigenous supercomputer came to light earlier this week. As reported in the Indian press, the Rs 4,500-crore Read more…

By Tiffany Trader

Tuning InfiniBand Interconnects Using Congestion Control

July 26, 2017

InfiniBand is among the most common and well-known cluster interconnect technologies. However, the complexities of an InfiniBand (IB) network can frustrate the Read more…

By Adam Dorsey

NSF Project Sets Up First Machine Learning Cyberinfrastructure – CHASE-CI

July 25, 2017

Earlier this month, the National Science Foundation issued a $1 million grant to Larry Smarr, director of Calit2, and a group of his colleagues to create a comm Read more…

By John Russell

Graphcore Readies Launch of 16nm Colossus-IPU Chip

July 20, 2017

A second $30 million funding round for U.K. AI chip developer Graphcore sets up the company to go to market with its “intelligent processing unit” (IPU) in Read more…

By Tiffany Trader

Fujitsu Continues HPC, AI Push

July 19, 2017

Summer is well under way, but the so-called summertime slowdown, linked with hot temperatures and longer vacations, does not seem to have impacted Fujitsu's out Read more…

By Tiffany Trader

Researchers Use DNA to Store and Retrieve Digital Movie

July 18, 2017

From abacus to pencil and paper to semiconductor chips, the technology of computing has always been an ever-changing target. The human brain is probably the com Read more…

By John Russell

The Exascale FY18 Budget – The Next Step

July 17, 2017

On July 12, 2017, the U.S. federal budget for its Exascale Computing Initiative (ECI) took its next step forward. On that day, the full Appropriations Committee Read more…

By Alex R. Larzelere

Google Pulls Back the Covers on Its First Machine Learning Chip

April 6, 2017

This week Google released a report detailing the design and performance characteristics of the Tensor Processing Unit (TPU), its custom ASIC for the inference Read more…

By Tiffany Trader

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

Quantum Bits: D-Wave and VW; Google Quantum Lab; IBM Expands Access

March 21, 2017

For a technology that’s usually characterized as far off and in a distant galaxy, quantum computing has been steadily picking up steam. Just how close real-wo Read more…

By John Russell

HPC Compiler Company PathScale Seeks Life Raft

March 23, 2017

HPCwire has learned that HPC compiler company PathScale has fallen on difficult times and is asking the community for help or actively seeking a buyer for its a Read more…

By Tiffany Trader

Trump Budget Targets NIH, DOE, and EPA; No Mention of NSF

March 16, 2017

President Trump’s proposed U.S. fiscal 2018 budget issued today sharply cuts science spending while bolstering military spending as he promised during the cam Read more…

By John Russell

CPU-based Visualization Positions for Exascale Supercomputing

March 16, 2017

In this contributed perspective piece, Intel’s Jim Jeffers makes the case that CPU-based visualization is now widely adopted and as such is no longer a contrarian view, but is rather an exascale requirement. Read more…

By Jim Jeffers, Principal Engineer and Engineering Leader, Intel

Nvidia’s Mammoth Volta GPU Aims High for AI, HPC

May 10, 2017

At Nvidia's GPU Technology Conference (GTC17) in San Jose, Calif., this morning, CEO Jensen Huang announced the company's much-anticipated Volta architecture a Read more…

By Tiffany Trader

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

Leading Solution Providers

Facebook Open Sources Caffe2; Nvidia, Intel Rush to Optimize

April 18, 2017

From its F8 developer conference in San Jose, Calif., today, Facebook announced Caffe2, a new open-source, cross-platform framework for deep learning. Caffe2 is the successor to Caffe, the deep learning framework developed by Berkeley AI Research and community contributors. Read more…

By Tiffany Trader

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

Russian Researchers Claim First Quantum-Safe Blockchain

May 25, 2017

The Russian Quantum Center today announced it has overcome the threat of quantum cryptography by creating the first quantum-safe blockchain, securing cryptocurrencies like Bitcoin, along with classified government communications and other sensitive digital transfers. Read more…

By Doug Black

MIT Mathematician Spins Up 220,000-Core Google Compute Cluster

April 21, 2017

On Thursday, Google announced that MIT math professor and computational number theorist Andrew V. Sutherland had set a record for the largest Google Compute Engine (GCE) job. Sutherland ran the massive mathematics workload on 220,000 GCE cores using preemptible virtual machine instances. Read more…

By Tiffany Trader

Google Debuts TPU v2 and will Add to Google Cloud

May 25, 2017

Not long after stirring attention in the deep learning/AI community by revealing the details of its Tensor Processing Unit (TPU), Google last week announced the Read more…

By John Russell

Groq This: New AI Chips to Give GPUs a Run for Deep Learning Money

April 24, 2017

CPUs and GPUs, move over. Thanks to recent revelations surrounding Google’s new Tensor Processing Unit (TPU), the computing world appears to be on the cusp of Read more…

By Alex Woodie

Six Exascale PathForward Vendors Selected; DoE Providing $258M

June 15, 2017

The much-anticipated PathForward awards for hardware R&D in support of the Exascale Computing Project were announced today with six vendors selected – AMD Read more…

By John Russell

Top500 Results: Latest List Trends and What’s in Store

June 19, 2017

Greetings from Frankfurt and the 2017 International Supercomputing Conference where the latest Top500 list has just been revealed. Although there were no major Read more…

By Tiffany Trader

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