Catching Up on Cloud: An Interview with IBM

By Nicole Hemsoth

May 19, 2008

If there’s one company trying to scatter cloud computing across the planet — like some kind of big, blue cloud, you might say — it’s IBM. And one of the top guys behind IBM’s cloud initiatives is Dennis Quan, chief technology officer for High-Performance On-Demand Solutions. The HiPODS team is charged with helping customers smartly grow and manage their datacenters, accelerate time to market and reduce IT complexity, among other things. In this Q&A with GRIDtoday, Quan gave us 29 minutes to recap some of the high points of IBM’s busy past six months or so in cloud computing. Then he had to catch a plane.

GRIDtoday:  When customers ask you to explain cloud computing, what do you tell them?

DENNIS QUAN: Cloud computing is about providing applications to large numbers of users via the network and their connected mobile devices, their laptop computers or whatever, and having an IT infrastructure, a cloud computing center, that’s capable of supporting large numbers of applications, and being able to massively scale to meet growing user demands. We’ve actually been able to prove out these concepts in some projects in use within IBM. And we’ve found that one of the key characteristics is not only scaling to demands, but being able to get applications on board and running as quickly as possible. This is critical for this generation of applications because of the innovation cycle being so fast today. You really need to get innovators the compute resources they need, and that’s one of our goals with our on-demand solutions.

One message that resonates well with customers is being able to increase the speed at which they can prototype their apps and get feedback. Because we’re using virtualization and provisioning automation, we’re able to allow people to go to a self-service portal and say “I need these Linux boxes with an app server,” and so on, and be able to get that done within minutes. You know, as opposed to taking potentially weeks to acquire the machines and set them up and rack them and install the software themselves. That is extremely appealing to our customers. They also like having the freedom to run any kind of workload they like and put any kind of software on the cloud that they like. It’s not limited to back-end tasks, batch-processing tasks; it could be user-facing applications, it could be Web servers, it could be database servers.


Gt:
What’s one of your most compelling examples of cloud computing?

QUAN: About two and a half years ago we launched a cloud within IBM, the Innovation Portal. When individual users at IBM had a new idea — instead of having to hunt down permission to buy a new machine and having to find a place to host it and install it, etc., which is not only time-consuming but also resource- consuming because they have to handle all the system admin stuff — what they can do instead is go to this self-service portal and request resources. It can be 20 virtual machines running Linux and WebSphere and DB2, for example, or any number of combinations. It’s a lot like booking a hotel room on a Web site. You’re able to get access to a certain number of resources for a period of time, and the system goes off and provisions that for you, and you’re given access to those machines, with all the software and middleware, etc., set up for you.

Since launching this cloud within IBM, we’ve had over 100 projects run on it, and about 20 percent have contributed to technology used in shipping products.

The applications and projects we’ve run in the cloud have ranged from collaboration tools to social networking tools to development tools — and even a game. What we’ve found is that people are able to access compute resources very quickly, which benefits not just individual innovators with a brand new idea but also design teams who want to test their new product on the greater IBM population. A software development company could use this kind of cloud to do in-house testing and quality control.

Gt: What software is at the heart of this cloud?

QUAN: We put together this cloud solution based on our Tivoli products — Tivoli Provision Manager, Tivoli Monitoring — and that’s really been the foundation architecture that we’ve been using in all our explorations of cloud computing.

Gt: What is the goal of the joint venture with Google announced last fall?

QUAN: It’s a partnership to promote research into cloud computing, especially to promote the parallel programming models we think are going to be important for future applications to take advantage of these large cloud centers. We’ve built out three clouds for this project. One at the Almaden Research Center in San Jose (California), one at the University of Washington, and one at a Google datacenter. We’ve been able to get six universities involved with this project (MIT, University of Maryland, Carnegie Mellon University, Stanford University, University of Washington, University of California, Berkeley). Overall it’s about a thousand machines across the three sites, using the Tivoli architecture mentioned earlier.

Gt: November’s Blue Cloud announcement of “ready-to-use cloud computing”: What does it mean for businesses, and what’s happened with the initiative since then?

QUAN: Blue Cloud is really a statement about everything we’ve learned about running clouds for innovation enablement inside IBM, or for supporting these new parallel programming models. It’s about how we’re going to apply these new technologies to solve some of the nagging pain points of many of our customers. They’re facing trouble trying to grow their datacenters in the face of rising energy costs and running out of space, etc.

Blue Cloud is about having a broad spectrum of products across our systems and software technologies, our services, to support a cloud computing style of datacenter management. It’s really all about having the massively scalable datacenter model that will allow you to support large numbers of applications and users, and a very diverse range of applications and workloads.

What we’ve done is put together an offering — which we project will come out this spring — that will allow our customers to be able to start up a cloud center of their own within their datacenters, within their own four walls. We’ve found that a number of our customers are very interested in this kind of highly scalable, manageable form of large-scale computing, but want to be able to maintain control of their own datacenters. So we are commercializing what we’ve learned in the clouds that we’ve built so far.

We want to be the arms dealers, as it were, of these cloud computing components that will enable our customers to build up datacenters that have these capabilities.

Gt: In February, IBM announced it will build the first cloud computing center in China, at the new Wuxi Tai Hu New Town Science and Education Industrial Park. Who will be using the Wuxi cloud, what for, and why?

QUAN: We’ve engaged with the municipal government of Wuxi, a city north of Shanghai, to build them a cloud for software development. There are cities all over China that want to create software parks, entrepreneurs who want to do enterprise software development for multinationals, or do a variety of things like animation — things that involve a large amount of compute resources. They can really benefit from access to scalable resources on demand. So, we’re building them a cloud center that includes a wide range of our Rational tools for developing enterprise applications.

An entrepreneur making use of this cloud can go to the self-service portal and say, “I am going to be doing this project for 10 months and I’m going to need resources for my 20 or 40 developers to be able to do source control and project management,” and they’ll have the appropriate products provisioned for them. The government will be able to bill them on a monthly basis, or whatever the schedule happens to be. The big benefit to these small entrepreneurs is that upfront costs of buying hardware and software licenses, as well as the ongoing maintenance, have all been centralized and borne by the government, and so the software company is able to pay as they go to make use of this.

We’ve seen that as a very popular model for governments not just in China but around the world who are interested in promoting economic development, entrepreneurialism, and innovation.

Gt: Then a month later, IBM opens a new cloud center in Dublin.

QUAN: We partnered with the local government industrial development authority. This particular cloud is run out of an IBM center. We’re able to use this center to demonstrate to clients the benefits of cloud computing, especially for enterprises.

One of the highlights of the Dublin cloud is a solution we call the Idea Factory for Cloud Computing. It’s a Web 2.0 app that allows you to exchange ideas using different collaboration tools like blogging and wikis and such. One customer’s consultants had an idea exchange session a couple weeks ago with thousands of participants. They’ve been happy with what they can do using an application being delivered from a cloud computing center. We’ve had similar experiences with a wide range of institutions, including governments and financial services.

Gt: What does cloud technology mean for tomorrow’s datacenter?

QUAN: We see cloud computing as a broadly applicable technology platform for enabling the next generation of datacenter, what we call the new enterprise datacenter. [This type of datacenter will be] able to combine the things that you see in the Web-centered cloud platforms out there — the MySpaces, the Flickrs, the YouTubes — where they’re able to do large scalable application delivery and support large numbers of users with the characteristics of traditional enterprise datacenters, where large companies are able to depend on these datacenters for mission-critical applications, being able to do secure transaction processing, being able to maintain security and isolation of data. The new enterprise datacenter model is inspired by this Web-centered cloud concept and also inherits the characteristics of enterprise datacenters that our clients find absolutely critical.

Gt: What kind of response do you get from management and IT people when talking about bringing a cloud into their business?

QUAN: I think the way we’ve talked about cloud computing tends to resonate very well. They might have concerns based on things they read in the press and hear from other folks in industry, but at the end of the day, they care most about solving the problems that hamper them. How are they going to get higher utilization out of their datacenters that are running out of space? How are they going to lower the labor costs or the maintenance costs of running large-scale systems? And that’s really where we’ve targeted our solutions. It’s by design trying to help along these axes. So using technologies like virtualization, provisioning, automation, it’s really about taking what they’ve seen in terms of the benefits from Web-centric clouds and then applying it directly to the pain points that they have.

Gt: What are some of those pain points?

QUAN: One of the biggest is machine utilization. We’ve probably all seen the statistics about x86 datacenters having about 5 to 10 percent utilization across their systems. And then you talk about needing to grow those datacenters and you’re running out of space, one of the things you want to do is make higher use of the machines you have. By using things like virtualization, we’re able to improve utilization significantly. Virtualization has been an IBM specialty for ages.

Gt: Just a couple weeks ago, IBM introduced a new line of servers. Tell us about the iDataPlex systems and how they fit into the cloud environment.

QUAN: They’re a great example of a hardware platform to support cloud systems. The iDataPlex systems allow for an extremely dense configuration of compute power in the rack. We think these Linux servers can be used to support an extremely large cloud datacenter. They double the number of systems that can fit in a rack, but use about 40 percent less power. We actually have some of these systems running within the cloud that we have in our laboratories, and they’ll be used in our other cloud installations. They’re a key part of the portfolio we’re offering to companies to build out their clouds. The systems support all the characteristics needed for cloud computing: extremely dense, vast pools of compute power, virtualization capabilities, and so on.

Gt: We will refrain from asking you if the future of cloud computing is sunny … so, how is it?

QUAN: The future is pretty bright because what we’re seeing right now is such growth in mobile technologies and need for data access anywhere. More and more users are going to be signing on from more and more locations. In developing economies they’ll be signing on mostly from mobile devices because of lack of traditional infrastructure. That’s going to put extreme demands on datacenters to be able to scale and to process the large amounts of video, audio, and text that these users are contributing and sending to each other. You’re going to need a cloud computing-style datacenter model to support these kinds of applications, and these phenomena are not restricted to consumer applications. You see these things happening within enterprises in terms of the types of collaboration or interactions people have within a business, for anything from supporting basic e-mail to sales processes, CRM, and line-of-business applications. All these things are going to undergo a transformation toward being mobile, supporting richer forms of Web 2.0 interactions, and being able to sustain lots of concurrent users.

These are all driving the need for scalable datacenter models, such as the ones we’ve been building with our cloud computing initiatives. And finally, clouds will respond to green initiatives to get the most out of the compute cycles that you have in these datacenters because of the rising cost of energy. We made an announcement about a month ago in collaboration with Ohio State and Georgia Tech about research we’re doing with them on autonomic computing as applied to clouds. There are several areas we’re looking at, like automating workload scheduling, more intelligent balancing of resources across a virtualized datacenter, and being able to do workload movement. These features would let a company shut down a portion of the datacenter if it’s not in use in order to save electricity.

We’ve been showing these technologies to customers for a couple years now and they’re now able to understand how those things apply to them. It’s basically been taking off.

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!

Intel Debuts New GPU – Ponte Vecchio – and Outlines Aspirations for oneAPI

November 17, 2019

Intel today revealed a few more details about its forthcoming Xe line of GPUs – the top SKU is named Ponte Vecchio and will be used in Aurora, the first planned U.S. exascale computer. Intel also provided a glimpse of Read more…

By John Russell

SC19: Welcome to Denver

November 17, 2019

A significant swath of the HPC community has come to Denver for SC19, which began today (Sunday) with a rich technical program. As is customary, the ribbon cutting for the Expo Hall opening is Monday at 6:45pm, with the Read more…

By Tiffany Trader

SC19’s HPC Impact Showcase Chair: AI + HPC a ‘Speed Train’

November 16, 2019

This year’s chair of the HPC Impact Showcase at the SC19 conference in Denver is Lori Diachin, who has spent her career at the spearhead of HPC. Currently deputy director for the U.S. Department of Energy’s (DOE) Read more…

By Doug Black

Microsoft Azure Adds Graphcore’s IPU

November 15, 2019

Graphcore, the U.K. AI chip developer, is expanding collaboration with Microsoft to offer its intelligent processing units on the Azure cloud, making Microsoft the first large public cloud vendor to offer the IPU designe Read more…

By George Leopold

At SC19: What Is UrgentHPC and Why Is It Needed?

November 14, 2019

The UrgentHPC workshop, taking place Sunday (Nov. 17) at SC19, is focused on using HPC and real-time data for urgent decision making in response to disasters such as wildfires, flooding, health emergencies, and accidents. We chat with organizer Nick Brown, research fellow at EPCC, University of Edinburgh, to learn more. Read more…

By Tiffany Trader

AWS Solution Channel

Making High Performance Computing Affordable and Accessible for Small and Medium Businesses with HPC on AWS

High performance computing (HPC) brings a powerful set of tools to a broad range of industries, helping to drive innovation and boost revenue in finance, genomics, oil and gas extraction, and other fields. Read more…

IBM Accelerated Insights

Data Management – The Key to a Successful AI Project

 

Five characteristics of an awesome AI data infrastructure

[Attend the IBM LSF & HPC User Group Meeting at SC19 in Denver on November 19!]

AI is powered by data

While neural networks seem to get all the glory, data is the unsung hero of AI projects – data lies at the heart of everything from model training to tuning to selection to validation. Read more…

China’s Tencent Server Design Will Use AMD Rome

November 13, 2019

Tencent, the Chinese cloud giant, said it would use AMD’s newest Epyc processor in its internally-designed server. The design win adds further momentum to AMD’s bid to erode rival Intel Corp.’s dominance of the glo Read more…

By George Leopold

Intel Debuts New GPU – Ponte Vecchio – and Outlines Aspirations for oneAPI

November 17, 2019

Intel today revealed a few more details about its forthcoming Xe line of GPUs – the top SKU is named Ponte Vecchio and will be used in Aurora, the first plann Read more…

By John Russell

SC19: Welcome to Denver

November 17, 2019

A significant swath of the HPC community has come to Denver for SC19, which began today (Sunday) with a rich technical program. As is customary, the ribbon cutt Read more…

By Tiffany Trader

SC19’s HPC Impact Showcase Chair: AI + HPC a ‘Speed Train’

November 16, 2019

This year’s chair of the HPC Impact Showcase at the SC19 conference in Denver is Lori Diachin, who has spent her career at the spearhead of HPC. Currently Read more…

By Doug Black

Cray, Fujitsu Both Bringing Fujitsu A64FX-based Supercomputers to Market in 2020

November 12, 2019

The number of top-tier HPC systems makers has shrunk due to a steady march of M&A activity, but there is increased diversity and choice of processing compon Read more…

By Tiffany Trader

Intel AI Summit: New ‘Keem Bay’ Edge VPU, AI Product Roadmap

November 12, 2019

At its AI Summit today in San Francisco, Intel touted a raft of AI training and inference hardware for deployments ranging from cloud to edge and designed to support organizations at various points of their AI journeys. The company revealed its Movidius Myriad Vision Processing Unit (VPU)... Read more…

By Doug Black

IBM Adds Support for Ion Trap Quantum Technology to Qiskit

November 11, 2019

After years of percolating in the shadow of quantum computing research based on superconducting semiconductors – think IBM, Rigetti, Google, and D-Wave (quant Read more…

By John Russell

Tackling HPC’s Memory and I/O Bottlenecks with On-Node, Non-Volatile RAM

November 8, 2019

On-node, non-volatile memory (NVRAM) is a game-changing technology that can remove many I/O and memory bottlenecks and provide a key enabler for exascale. That’s the conclusion drawn by the scientists and researchers of Europe’s NEXTGenIO project, an initiative funded by the European Commission’s Horizon 2020 program to explore this new... Read more…

By Jan Rowell

MLPerf Releases First Inference Benchmark Results; Nvidia Touts its Showing

November 6, 2019

MLPerf.org, the young AI-benchmarking consortium, today issued the first round of results for its inference test suite. Among organizations with submissions wer Read more…

By John Russell

Supercomputer-Powered AI Tackles a Key Fusion Energy Challenge

August 7, 2019

Fusion energy is the Holy Grail of the energy world: low-radioactivity, low-waste, zero-carbon, high-output nuclear power that can run on hydrogen or lithium. T Read more…

By Oliver Peckham

Using AI to Solve One of the Most Prevailing Problems in CFD

October 17, 2019

How can artificial intelligence (AI) and high-performance computing (HPC) solve mesh generation, one of the most commonly referenced problems in computational engineering? A new study has set out to answer this question and create an industry-first AI-mesh application... Read more…

By James Sharpe

Cray Wins NNSA-Livermore ‘El Capitan’ Exascale Contract

August 13, 2019

Cray has won the bid to build the first exascale supercomputer for the National Nuclear Security Administration (NNSA) and Lawrence Livermore National Laborator Read more…

By Tiffany Trader

DARPA Looks to Propel Parallelism

September 4, 2019

As Moore’s law runs out of steam, new programming approaches are being pursued with the goal of greater hardware performance with less coding. The Defense Advanced Projects Research Agency is launching a new programming effort aimed at leveraging the benefits of massive distributed parallelism with less sweat. Read more…

By George Leopold

AMD Launches Epyc Rome, First 7nm CPU

August 8, 2019

From a gala event at the Palace of Fine Arts in San Francisco yesterday (Aug. 7), AMD launched its second-generation Epyc Rome x86 chips, based on its 7nm proce Read more…

By Tiffany Trader

D-Wave’s Path to 5000 Qubits; Google’s Quantum Supremacy Claim

September 24, 2019

On the heels of IBM’s quantum news last week come two more quantum items. D-Wave Systems today announced the name of its forthcoming 5000-qubit system, Advantage (yes the name choice isn’t serendipity), at its user conference being held this week in Newport, RI. Read more…

By John Russell

Ayar Labs to Demo Photonics Chiplet in FPGA Package at Hot Chips

August 19, 2019

Silicon startup Ayar Labs continues to gain momentum with its DARPA-backed optical chiplet technology that puts advanced electronics and optics on the same chip Read more…

By Tiffany Trader

Crystal Ball Gazing: IBM’s Vision for the Future of Computing

October 14, 2019

Dario Gil, IBM’s relatively new director of research, painted a intriguing portrait of the future of computing along with a rough idea of how IBM thinks we’ Read more…

By John Russell

Leading Solution Providers

ISC 2019 Virtual Booth Video Tour

CRAY
CRAY
DDN
DDN
DELL EMC
DELL EMC
GOOGLE
GOOGLE
ONE STOP SYSTEMS
ONE STOP SYSTEMS
PANASAS
PANASAS
VERNE GLOBAL
VERNE GLOBAL

Intel Confirms Retreat on Omni-Path

August 1, 2019

Intel Corp.’s plans to make a big splash in the network fabric market for linking HPC and other workloads has apparently belly-flopped. The chipmaker confirmed to us the outlines of an earlier report by the website CRN that it has jettisoned plans for a second-generation version of its Omni-Path interconnect... Read more…

By Staff report

Kubernetes, Containers and HPC

September 19, 2019

Software containers and Kubernetes are important tools for building, deploying, running and managing modern enterprise applications at scale and delivering enterprise software faster and more reliably to the end user — while using resources more efficiently and reducing costs. Read more…

By Daniel Gruber, Burak Yenier and Wolfgang Gentzsch, UberCloud

Dell Ramps Up HPC Testing of AMD Rome Processors

October 21, 2019

Dell Technologies is wading deeper into the AMD-based systems market with a growing evaluation program for the latest Epyc (Rome) microprocessors from AMD. In a Read more…

By John Russell

Rise of NIH’s Biowulf Mirrors the Rise of Computational Biology

July 29, 2019

The story of NIH’s supercomputer Biowulf is fascinating, important, and in many ways representative of the transformation of life sciences and biomedical res Read more…

By John Russell

Xilinx vs. Intel: FPGA Market Leaders Launch Server Accelerator Cards

August 6, 2019

The two FPGA market leaders, Intel and Xilinx, both announced new accelerator cards this week designed to handle specialized, compute-intensive workloads and un Read more…

By Doug Black

Cray, Fujitsu Both Bringing Fujitsu A64FX-based Supercomputers to Market in 2020

November 12, 2019

The number of top-tier HPC systems makers has shrunk due to a steady march of M&A activity, but there is increased diversity and choice of processing compon Read more…

By Tiffany Trader

When Dense Matrix Representations Beat Sparse

September 9, 2019

In our world filled with unintended consequences, it turns out that saving memory space to help deal with GPU limitations, knowing it introduces performance pen Read more…

By James Reinders

With the Help of HPC, Astronomers Prepare to Deflect a Real Asteroid

September 26, 2019

For years, NASA has been running simulations of asteroid impacts to understand the risks (and likelihoods) of asteroids colliding with Earth. Now, NASA and the European Space Agency (ESA) are preparing for the next, crucial step in planetary defense against asteroid impacts: physically deflecting a real asteroid. Read more…

By Oliver Peckham

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This