insideHPC » Business of HPC

India to Invest $1 Billion in Supercomputing Race

Rich Brueckner — Thu, 26 Jan 2012 11:40:01 +0000

Dinesh C. Sharma writes that India is rebooting their efforts in the supercomputing race with a billion-dollar initiative to create next-generation supercomputers.

The government has committed `5,000 crore (nearly $1billion) for the plan, making it the largest ever grant for a single research programme since Independence. The money is likely to start flowing during the 12th five-year plan period. The only jarring aspect of the project is that its reins are being handed over to the Indian Institute of Science (IISc), Bangalore, which has only been a user and not a designer or developer of supercomputers.

Read the Full Story.

Three Issues that Stymie HPC Growth

Rich Brueckner — Wed, 25 Jan 2012 18:11:57 +0000

Douglas Eadline over at HPC Admin writes that while the HPC market has come along way in the last decade, the same three issues continue to impede the full potential of the market: the last mile problem, the lack of a missing middle infrastructure, and a lack of focus on parallel software.

The absence of a missing middle infrastructure has stymied the growth of this sector. Addressing this audience (see The Council On Competitiveness) can have a huge effect on both the HPC market and the entire economy. Again, the solution lives across the industry but has less to do with peak FLOPS and more to do with effective FLOPS. Reducing the “barriers to effective FLOPS” benefit all HPC vendors, but no vendor has taken on this role in the industry, nor should they. Just like the last mile problem, the problem of the missing middle spans the entire market.

Read the Full Story.

Podcast: Eurotech Leverages Mfg Excellence for HPC Market

Rich Brueckner — Tue, 24 Jan 2012 20:41:03 +0000

In this this podcast Giovanbattista (Giovanni) Mattiussi from Eurotech discusses the company’s push into the HPC market and their growing presence at the annual SC and ISC conferences. Widely known for their embedded manufacturing capabilities, Eurotech is receiving accolades for their high-density Aurora Intel-based clusters.

Download the MP3 * Subscribe on iTunes * Subscribe on other podcast players. If your IT Crowd blocks Dropbox, you can download the audio from this Google page.

insideHPC: Eurotech does not seem to be widely known in the U.S. supercomputing market. When did the company start doing HPC?

Giovanni: I would start saying the Eurotech is a publicly listed global company who does not only HPC. I think this is important to point out for financial and competence reasons: Eurotech relies on a wide beyond HPC offering that guarantees cash flows and technical synergies/exchanges between divisions.

Eurotech started doing HPC in 1998. For 10 years, between 1998 and 2008, the company took part to large (10M€+) HPC projects as engineering and design partner, producing special and general purpose supercomputers and collaborating with some of the most prestigious European research centres. The competencies inherited from the core embedded electronic business allowed Eurotech to include innovative design solutions in its HPC systems. Supercomputer were evolving in HPC clusters, using commercial components, absorbing increasingly more power, generating increasingly more heat and using an increasingly smaller space: all of these aspects are areas where an embedded electronic company like Eurotech thrived.

These 10 years saw the birth of supercomputers like the APE series, a family of systems that almost set a paradigm in the history of the 3D Torus architecture for LQCD. Also worth to be mentioned, Janus was one of the first FPGA based supercomputers and Avogadro, the first Eurotech top500 entry. A common characteristic of these systems is that they never became commercial products, leaving Eurotech to play in the field of custom supercomputers. Things changed in 2008 with Aurora, which Eurotech designed in collaboration with the research consortium Aurora Science, backed by the prestigious INFN, the national institute of nuclear physics, where scientists like Fermi worked. Aurora was designed to be highly “scientific” and special in its design, but also suitable to be marketed because it relied on main stream components. Aurora soon became a product line, which leveraged more than 10 years of research. Around the Aurora product family, Eurotech built its HPC division shaping it as independent business unit. Nowadays, whilst maintaining its hardware manufacturer DNA, Eurotech can offer HPC solutions, integrating its own and 3rd party hardware and software plus services that cover design, installation and support.

insideHPC: What prompted Eurotech to develop the Aurora series of supercomputer clusters based on commodity components?

Giovanni: The idea that the company had built through research projects enough technical competencies to design, build and launch its own product line. Also, the willingness to follow the HPC industry trends which were pushing toward standardization if not commoditization. Eurotech keeps doing research projects (DEEP, Dynamic Exascale Entry Platform, and others I can’t mention yet are some examples), but strategically aims to become a player in the HPC market like the Crays or SGIs of this world.

insideHPC: Eurotech has a core competency in hardware manufacturing. What additional strengths does the company bring to the table in the HPC marketplace?

Giovanni: You said it right. Eurotech comes from hardware design and manufacturing. However, few years ago, the company started its journey as software developer: the “device cloud” offering Eurotech proposes is an example. At the group level, we have been building software competencies to match the HW ones. In the HPC division, at the moment, we retain a 50% split between HW and SW engineers. So, despite not producing HPC software, I believe Eurotech has the competencies to integrate and maintain HPC software packages. The other aspect are good services that, despite not being sold standalone, are built on a a real intimacy between us and our customers and follow the customers throughout each HPC project. So, I would say, technical leadership, solution design and customer intimacy are the strong points in our HPC proposition.

insideHPC: In terms of your HPC products, would you say that you are mostly a player at the very high end, or do you also have departmental offerings?

Giovanni: With the introduction of Aurora, we have been in the condition to sell at the same price level of companies like Cray and IBM for instance. Also, we normally configure small clusters and mid end systems that, despite maintaining a high engineering content, are stripped down of “fancy” features to become more standardized. Due the size of our company we prioritize producing rock solid, high quality, energy efficient HPC systems, rather than selling on volume. We totally focus on customers, trying to design the best solution for them. This is the reason why we think that more than competing with many large HPC hardware vendors, we complement their offering.
Also, note that we are the only HPC player offering a rugged high performance computer, able to withstand vibrations, heat, cold, rain etc. a product that oil&gas, security and meteorological sectors are seeing with an increased interest.

insideHPC: Is the ISC conference an important part of your HPC marketing strategy?

Giovanni: Yes, it is. To be honest, if I had to do a crude analysis of the cost per lead, I would need to disqualify both ISC and SC! However, there has been no other marketing activity that has given me the same quality in the leads so far. Also, both ISC and SC are unique opportunities to showcase Eurotech technologies in front of all industry reunited. This is not trivial for a company like Eurotech whose marketing reach is limited by budget. ISC is particularly relevant because it is an European show and Europe is at the moment our main field of play.

insideHPC: On the road to Exascale computing, It seems like Europe has chosen to focus on developing software. Does Eurotech participate in these planning discussions?
Eurotech is involved in PRACE and other European initiatives. Recently, we announced our participation to the European Technology Platform for HPC. This collaboration happens at a very wide European level and wants to tackle exascale challenges from the software and hardware points of view. Eurotech already participates to large EU funded research projects like DEEP, whose focus is equally hardware and software. All in all, what I can see is that, eventually, Europe realized that only communitarian European wide initiatives will bring enough weight to play at the same level than US, Japan and now China in the supercomputing arena. Maybe, this will serve an example to inspire that European political unity, whose absence is now the cause of the sever economic a crisis. At the moment, I would be happy with an HPC united Europe!

insideHPC: Besides Europe, you have subsidiaries in Japan, the U.K., and the U.S.. Do you believe Eurotech will be a worldwide force in HPC in the long term?

Giovanni: Yes we do, but it will take some time. We believe Europe is where at the moment we stand most chances to increase our installed based. At the same time, we are equipping our worldwide sales force to be able to sell HPC and discussing business in Japan and the middle East. While in Japan we can sell through the locally recognized Advanet brand, markets like the U.S. one will require Eurotech to collaborate with a U.S. system integrator or a larger US vendor.

Intel Upsets Apple Cart, Snaps Up QLogic’s InfiniBand Biz

Ralph — Tue, 24 Jan 2012 08:01:43 +0000

By Timothy Prickett Morgan • Get more from this author

The high-performance networking market just got a whole lot more interesting, with Intel shelling out $125m to acquire the InfiniBand switch and adapter product lines from upstart QLogic.

Intel has made no secret that it wants to bolster its Data Center and Connected Systems business by getting network equipment providers to use Xeon processors inside of their networking gear – that Intel division posted $10.1bn in revenues in 2011, and the company wants to break $20bn in the next five years.

The plan is to kill off mainframes and RISC machines, and to get Xeons inside of storage and network gear – but it also includes Intel being a major supplier of chips used in high speed switches.

Last July, Intel paid an undisclosed amount to get its hands on Fulcrum Microsystems, a maker of the FocalPoint family of ASICs for Ethernet switches and routers that run at 10GbE and 40GbE speeds. Fulcrum’s most famous customer was Arista Networks, the low-latency networking switch-maker founded by Sun Microsystems cofounder Andy Bechtolsheim. Intel never said what it paid for Fulcrum, but the company had raised $102m in venture capital since it was founded, and the price was very likely a multiple of that figure.

Despite the improvements in 10GbE and 40GbE switch chips over the past several years, InfiniBand still has important niches where even lower latency and still higher bandwidth are crucial – the supercomputing racket, for instance, or in database clustering. Just ask Oracle, which uses InfiniBand silicon from Mellanox Technologies in its Exadata database clusters and Exalogic web application server clusters, and which took a 10.2 per cent stake in the chip and switch-maker back in October 2010.

At the time, Mellanox assured Wall Street that Oracle had no intention of taking over the chipmaker, but with QLogic’s upstart InfiniBand biz snapped up by Intel, some systems or networking companies might now be tempted to take a run at Mellanox. But if Oracle or IBM or Cisco Systems are tempted to eat Mellanox, all that will do is eventually drive everyone into the loving arms of Intel, with its own Ethernet or InfiniBand ASICs. So, in a funny way, Intel is probably praying that someone does eat Mellanox.

And the funniest thing of all would be if AMD actually woke up and smelled the systems biz, and did it. By doing so, AMD would have the SwitchX two-timing Ethernet and InfiniBand ASICs and the ConnectX-3 switch-hitting server adapters, and could start integrating these deeper into its chipsets and eventually onto its chips.

Intel and InfiniBand go way back

InfiniBand has its roots in the Next Generation I/O project supported by Intel, Sun Microsystems, and Microsoft, along with the Future I/O alternative supported by IBM, Compaq, and HP. These specs were merged back in 1999, with Intel and IBM largely steering the process.

The idea was to provide a single switched fabric that would link computers and storage to each other from the desktop to the data center, and be an alternative to Ethernet networks for server-to-server and PC-to-server links, and to PCI-Express and Fibre Channel for linking peripherals.

Academically, InfiniBand was probably the right answer for a unified switch fabric – but markets don’t study in schools, they live on the mean streets and give and take hard knocks. And thus, InfiniBand has been relegated to a niche and, more importantly, the key technologies that made InfiniBand better, stronger, and faster than Ethernet have been borged onto Ethernet, closing the gap.

For now, Intel is saying that its acquisition of the InfiniBand chip, adapter, and switch business from QLogic is all about HPC, but it may be looking further down the road, when PCI-Express runs out of gas.

“At the International Supercomputing Conference 2011, Intel unveiled a bold vision to redefine HPC performance and break the exascale barrier by 2018,” said Kirk Skaugen, the outgoing general manager of Intel’s Data Center and Connected System Group, said in a statement. “The technology and expertise from QLogic provide important assets to provide the scalable system fabric needed to execute on this vision. Adding QLogic’s InfiniBand product line to our networking portfolio will bring increased options and exceptional value to our datacenter customers.”

Last week, Skaugen – who has been pushing Intel’s expansion into switching and storage chippery for the past several years – was tapped to run Chipzilla’s PC Client Group. Diane Bryant, who has worked for Skaugen in the past and who was most recently Intel’s CIO, has replaced Skaugen and will be driving Intel’s server, storage, and networking strategies.

By selling its InfiniBand biz to Intel, QLogic will be able to double down on its Fibre Channel and Ethernet switches and adapters. QLogic has had some success with its InfiniBand gear, landing the 2,000-node “Sierra” cluster with Dell at Lawrence Livermore National Labs and also being the switch supplier for the 20,000-node procurement awarded to Appro International last June by the US Department of Energy’s Tri-Labs: Lawrence Livermore, Los Alamos, and Sandia National Laboratories.

“The sale of these InfiniBand assets will benefit our shareholders by enabling us to provide better focus and greater investment in growth opportunities for the data center with our converged networking, enterprise Ethernet, and storage area networking products,” said QLogic’s president and CEO, Simon Biddiscombe, in his statement. “After the sale, our cash position will be further strengthened and we expect the impact on earnings per share to be neutral. In addition, the sale of these assets to a leading technology innovator and recognized HPC leader will provide a greater investment stream in high performance fabrics for InfiniBand partners and customers.”

Speaking to El Reg two weeks ago apropos of nothing about the InfiniBand racket, QLogic’s head of global alliances and solutions marketing for HPC Joe Yaworksi said that the reason why QLogic was winning more InfiniBand deals is that its TruScale chips offer better performance running at Quad Data Rate (QDR) 40Gb/sec speeds than do Mellanox’ SwitchX products running at Fourteen Data Rate (FDR) 56Gb/sec speeds.

The big reason for this, said Yaworksi, was that QLogic bought compiler-maker PathScale in early 2006, and it has a networking stack that was designed to handle millions of messages per second. (PathScale was sold to SciCortex in 2007, and when it went bust, Cray picked up the PathScale pieces in 2009 and an open source PathScale has emerged from the ashes with a license from Cray.) The combination of the TruScale InfiniBand ASICs and PathScale messaging stack and compilers is what gave QLogic the idea it could take on Mellanox and win.

Yaworksi told El Reg that QLogic was “taking a hard look at whether or not we will ship FDR InfiniBand,” although with Intel picking up the company, there will be more funds to do whatever might seem appropriate. The company was thinking that in the second half of 2013 or the first half of 2014 it might jump straight to Eight Data Rate (EDR) speeds, which runs the InfiniBand lanes at 25Gb/sec.

That would be a long time to wait between products and to live on QDR, and a gap that Intel is probably not likely to tolerate. But it all depends on what Intel’s plans are, and the company isn’t saying anything right now. If QLogic weren’t a public company, both would have probably said less.

Intel expects the QLogic InfiniBand deal to close by the end of March, and added that a “significant number” of the employees associated with the business were expected to accept job offers from Chipzilla. ®

This article originally appeared in The Register. It appears here in its entirety as part of a cross-publishing agreement.

Intel Acquires InfiniBand Business from QLogic

Rich Brueckner — Mon, 23 Jan 2012 16:18:45 +0000

Today Intel announced that the company has acquired the InfiniBand business from QLogic for $125 million in cash. According to the release, a number of QLogic employees have received offers from Intel to join the company.

At the International Supercomputing Conference 2011, Intel unveiled a bold vision to redefine HPC performance and break the Exascale barrier by 2018,” said Kirk Skaugen, vice president and general manager of Intel’s Data Center and Connected System Group. “The technology and expertise from QLogic provide important assets to provide the scalable system fabric needed to execute on this vision. Adding QLogic’s InfiniBand product line to our networking portfolio will bring increased options and exceptional value to our datacenter customers.”

www.youtube.com/watch?v=-L7lFAq6UYw

You can watch the SC11 event that Skaugen refers to in this exclusive insideHPC video.

QLogic was one of the last remaining providers of InfiniBand silicon, and their TrueScale technology looked to be skipping the FDR speed iteration currently offered by their sole competitor, Mellanox. As for Intel, I’m betting we’re going to see Xeons with on-chip InfiniBand/100 GbE within three years.

Read the Full Story.

Programming all those GPUs – Exascale Report Community Weighs in on Blue Waters, Titan

Rich Brueckner — Fri, 20 Jan 2012 17:14:55 +0000

The Exascale Report has shared with us their Community Responds column in which readers discuss challenges of extreme scale in today’s systems. The participants are a who’s who of HPC thought leaders, so the article is well-worth a look.

Question from NAG’s Andrew Jones: What should be done about the applications that won’t be able to exploit thousands of GPUs together in a single simulation, for example because of algorithm limitations or legacy coding issues? Will the community be supported to develop and implement new algorithms for those codes? Or will it be acceptable for those codes to use large numbers of nodes but leave the GPUs idle? Blue Waters had a significant planning and preparation effort with the applications development community — what are the plans in this respect for Titan?

Download the PDF. If your IT Crowd blocks Dropbox, you can download from this Google page.

HP Makes Headway in Korean Supercomputer Market

Ralph — Mon, 16 Jan 2012 16:57:53 +0000

Korea IT News is reporting that HP has won several major HPC deals recently in South Korea, threatening IBM’s local dominance in the supercomputing market.

According to the industry, on January 15, Hyundai Motor, pushing forward a project of purchasing new super-computers, finally chose HP Korea’s products, breaking the custom of using IBM Korea’s products for years. Hyundai Motor’s super-computers will be used for high-performance computing such as design, crash simulation, etc.

Additional HP wins listed in the story include the National Fusion Research Institute and the Agency for Defense Development, which was previously a Cray customer. Read the Full Story.

Video: Appro Takes HPC Momentum into 2012

Rich Brueckner — Sun, 15 Jan 2012 13:00:53 +0000

www.youtube.com/watch?v=kdvI0__0_Mo

Our Video Sunday feature continues with Appro’s Mike Vildibill and Anthony Kenisky discussing the company’s recent HPC wins and what they see coming up for supercomputing in 2012.

Cray Expects Loss in 2011, Record Year in 2012

Rich Brueckner — Thu, 05 Jan 2012 16:11:35 +0000

This week Cray Inc. announced 2011 preliminary financial results projecting a loss for the year. Unspecified component shortages stymied the acceptance of Titan at ORNL, but the year ahead is actually looking good for the company.

With incredible efforts from our employees and our customers we were able to complete the vast majority of our system acceptances, but due to delays related to a key component of our systems we weren’t able to complete our planned acceptance at Oak Ridge,” said Peter Ungaro, president and CEO of Cray. “This acceptance is currently in process and we expect to complete it in the first quarter of 2012. We previously expected to have record revenue in 2012, and with this change in timing we have increased our outlook accordingly.

Lumpy revenue has always been a challenge for Cray, but I see this as just a bump in the road. The company expects revenue to go up something like 60 percent year over year with $400-$420 Million expected in 2012.

Wordcloud – What insideHPC Looked Like in 2011

Rich Brueckner — Sat, 31 Dec 2011 13:00:05 +0000

We had a phenomenal year at insideHPC. Not only did we launch three sister publications (inside-BigData, inside-Cloud, and inside-Startups) we also grew our readership 6 percent after a record year in 2010! I believe this growth reflects what’s in store for the entire industry in the coming months, so I thought it might be fun to take a look at all of our recent posts in a word cloud.

Vendors: Are you looking to reach more key influencers in HPC? Be sure to check out our new Media Kit for 2012.

At insideHPC, we are the industry’s only source with daily news on high performance computing–365 days a year. There’s always something new to see here, and I think that’s just one of the reasons why our readers look to us for HPC News without the Noise.

insideHPC Readers - Their Role in Purchasing Decisions

Here’s to all of our readers and sponsors with best wishes in 2012.

Cheers!

-Rich Brueckner
President, insideHPC

Report: HPC Market Fell Short of 2011 Growth Forecast

Rich Brueckner — Thu, 29 Dec 2011 20:55:20 +0000

According to a new report by Intersect360 Research, the HPC industry will fall short of the 9.2% year-over-year revenue growth originally forecast for 2011. The primary causes for the revised expectations are the Eurozone crisis, which is causing a slowdown in government and academic spending in that region, and the Thailand flooding, which has caused a disruption in the supply chain for disk drives.

We don’t predict floods or major international macroeconomic shifts as part of our forecast methodology, but these do wind up having a real impact on the market,” said Addison Snell, CEO of Intersect360 Research. “In 2011 we saw enough market dampers that we are compelled to lower our year-end expectations.”

The reduction in growth is supported by Intersect360 Research survey data on end-user budget expectations, which are at the lowest levels in five years. Respondents in academia and government are projecting lower budget growth than in previous years.

Commercial markets worldwide so far appear to be stable, but the restricted spending in government and academia seems to have spread from the U.S. to Europe,” said Chris Willard, Chief Research Officer. “Asia will be an increasing percentage of the market in 2011 and 2012.”

In the report, Intersect360 Research emphasizes that its analysis is preliminary, pending further survey analysis and the release of vendors’ revenue numbers from the final calendar quarter. In early 2012 the company will release a complete year-end 2011 HPC total market model and updated five-year forecast through 2016.

Read the Executive Summary of this report.

www.youtube.com/watch?v=Nzr5zvyJ-wM

The Future of Benchmarks – Slidecast and Whitepaper

Rich Brueckner — Mon, 14 Nov 2011 16:18:30 +0000

www.youtube.com/watch?v=1fsYJuwChBw

In the enterprise world, few things are as competitive as TPC (Transaction Processing) benchmarks. When the fastest machine wins the deal, the rules, procedures, and setup of individual benchmarks translates into truly high stakes.

In this video, Meikel Poess, co-chair of the TPCTC 2011 Council, presents: The Future of Benchmarking - Three Novel Concepts Presented at the Transaction Processing Performance Council’s Technical Conference (TPCTC 2011).

Abstract:

The ever-evolving technological landscape is challenging industry experts and researchers alike to develop innovative and increasingly powerful compute systems. Rapid improvements in transistor density, disk capacity and performance enable new innovations in system designs, system architectures and algorithms that can manage and query large amounts of data very efficiently.

As new fields of research emerge, adapting existing benchmarks (or creating entirely new benchmarks) becomes necessary. This paper examines three novel concepts for expanding the Transaction Processing Performance Council’s existing set of benchmarks (TPC-C, TPC-E and TPC-H), as presented at the TPC’s 2011 Technical Conference.

The ideas proposed within this paper are actively influencing the TPC’s direction, in terms of future benchmark development, and include:

Extending TPC-E to Measure Availability in Database Systems

Introducing Skew into the TPC-H Benchmark

Metrics for Measuring the Performance of the Mixed Workload CH-benCHmark

Researchers and industry experts who would like to offer feedback, or propose new ideas for TPC benchmark development, are encouraged to contact the author, Meikel Poess, at (meikel [dot] poess [at] oracle.com).

Download the Slides (PDF) and the Whitepaper (PDF).

Steve Conway: GPU Momentum Growing

Rich Brueckner — Fri, 04 Nov 2011 16:09:27 +0000

While AMD’s financial troubles indicate that the adoption of Firestream has not been as strong as hoped, Over at Scientific Computing, IDC’s Steve Conway writes that GPUs are gaining momentum in HPC and have tripled their worldwide footprint in the past two years.

GPUs today are still far from being able to tell x86 processors they have 24 hours to get out of town, but GPUs are clearly proliferating in the HPC market at a decent clip. An important sign is the spread of GPU-related academic offerings. At the September 2010 HPC User Forum meeting in Seattle, Rob Farber of the U.S. Department of Energy’s Pacific Northwest National Laboratory reported that GPU computing is part of the curriculum at more than 200 universities around the world, including marquee names, such as MIT, Harvard, Cambridge, Oxford, the Indian Institutes of Technology, National Taiwan University, and the Chinese Academy of Sciences.

Read the Full Story.

AMD to Cut 1400 Employees to Save Costs

Rich Brueckner — Fri, 04 Nov 2011 15:56:23 +0000

www.youtube.com/watch?v=oOYAAN5mFRc

I wish I had better news this morning. Randall Hand at Vizworld reports that AMD will lay off 10 percent of it’s workforce.

It’s not terribly surprising, as AMD has been having a bit of a rough patch compared to NVidia and Intel. Their CPU’s are falling short of Intel’s performance figures, and their GPU’s are falling in market-share compared to NVidia and the new Intel Sandy-Bridge. With Intel rapidly entering the GPU space and NVidia moving powerfully into the mobile space, AMD will soon have to find a new way to compete.

Approximately 1400 people were affected including about 60 percent of AMD’s marketing department and some key members of the Fusion engineering team. AMD will reportedly announce its new course, codenamed “Project WIN”on November 9th, 2011. Read the Full Story.

Streaming Sessions Available from Rensselaer Workshop on HPC for Industry

Rich Brueckner — Mon, 31 Oct 2011 11:41:46 +0000

Clipped from: www.rpi.edu (share this clip)

The Workshop on High-Performance Computing for Industry wrapped up this week at Rensselaer Polytechnic Institute. The workshop featured an Executive Session that focused on the roles of business, government, universities and laboratories in creating the environment needed for industry to take full advantage of HPC for gaining competitive advantage.

The Program Agenda page features all the sessions on streaming media, so check it out.

Fujitsu Poised to Take K Computer to International HPC Market

Rich Brueckner — Wed, 26 Oct 2011 11:04:49 +0000

Bloomberg BusinessWeek is reporting that Fujitsu hopes to nab $2.6 billion worth of supercomputer orders from the Japanese government in the next five years, but it’s not stopping there. The company is close to releasing its K supercomputer to an international market hungry for it’s extreme bandwidth and computational efficiency.

Fujitsu is preparing the K supercomputer for export by developing a system to help evaluate performance of individual machines, Yamamoto said. The offering can be delivered unit by unit, allowing it to scale its processing power to customer needs, he said. The company is also counting on rising sales from so-called cloud services, which allow clients to outsource data centers and other computing resources and access them online. Fujitsu predicts such revenue will triple from the current fiscal year to 300 billion yen in the 12 months ending March 31, 2013.

Read the Full Story.

Slidecast: Innovation for Business: The IBM SmartCloud Service Delivery Model

Rich Brueckner — Mon, 24 Oct 2011 12:00:14 +0000

In this video, Ric Telford from IBM presents: Innovation for Business: The SmartCloud Service Delivery Model.

Several years in the making, IBM’s recent announcement of SmartCloud is a major push for the company to bring the benefits of cloud computing to a whole new set of SMBs. In other words, the grid has come home to roost at your local mom and pop shop.

To realize the benefits of cloud computing while overcoming the inherent challenges, organizations must take a holistic approach. Implementing a cloud computing model means encouraging innovation by simplifying and standardizing underlying infrastructure. It entails the creation of efficient yet flexible IT foundations that can support the development of new services and the consistent delivery of quality user experiences. And it demands a focus on ensuring interoperability, resiliency and security in an integrated fashion.

Learn more at: http://ibm.com/smartcloud.

Download the MP3 * Subscribe on iTunes * Subscribe on other podcast players

Songnian Zhou: Why Combine Platform and IBM?

Rich Brueckner — Thu, 20 Oct 2011 21:08:22 +0000

Last week’s announcement about IBM’s acquisition of Platform Computing may have had some pundits scratching their heads, but this week Platform’s CEO Songnian Zhou has posted some insightful reflections on why the merger makes sense at this point in the evolution of the coluds, clusters, and grids:

Just as client/server took 20 years to mature into the mainstream, clusters and grids have taken 20 years, and cloud for general business apps is still just emerging. Two areas have been leading the way: HPC/technical computing followed by Internet services. It’s no accident that Platform Computing was founded in 1992 by Jingwen Wang and I, two renegade Computer Science professors with no business experience or even interest. We wanted to translate ‘80s distributed operating systems research into cluster and grid management products. That’s when the lowly x86 servers were becoming powerful enough to do the big proprietary servers’ job, especially if a bunch of them banded together to form a cluster, and later on an enterprise grid with multiple clusters. One system for all apps, shared with order. Initially, we talked to all the major systems vendors to transfer university research results to them, but there was no taker. So, we decided to practice what we preached. We have been growing and profitable all these 19 years with no external funding. Using clusters and grids, we replaced a supercomputer at Pratt & Whitney to run 10 times more Boeing 777 jet engine simulations, and we supported CERN to process insane amounts of data looking for God’s Particle. While the propeller heads were having fun, enterprises in financial services, manufacturing, pharmaceuticals, oil & gas, electronics, and the entertainment industries turned to these low cost, massively parallel systems to design better products and devise more clever services. To make money, they compute. To out-compete, they out-compute.

Read the Full Story.

IBM to Acquire Platform Computing

Rich Brueckner — Tue, 11 Oct 2011 14:56:22 +0000

Today IBM announced it has entered into a definitive agreement to acquire Platform Computing, a Canadian vendor of cluster and grid management software for distributed computing environments. While financial terms were not disclosed, the acquisition is anticipated to close in the fourth quarter of 2011.

IBM considers the acquisition of Platform Computing to be a strategic element for the transformation of HPC into the high growth segment of technical computing and an important part of our smarter computing strategy,” said Helene Armitage, general manager, IBM Systems Software. “This acquisition can be leveraged across IBM as we enhance our IBM offerings and solutions, providing clients with technology that helps draw insights to fuel critical business decisions or breakthrough science.”

Read the Full Story.

Video: Advancing HPC == Advancing the Business of Software

Rich Brueckner — Mon, 10 Oct 2011 11:28:31 +0000

www.youtube.com/watch?v=dU9yhwPk6BI

In this video, Intel’s Rich Altmaier presents: Advancing HPC == Advancing the Business of Software. This presentation was recorded at the HPC User Forum on Sept 8, 2011 in San Diego.

Altmaier makes a good point; HPC software development has to be commercially viable for companies to make the required investments in development and support. That requires an ecosystem, and where exactly would that come from for an exotic Exascale machine? Download the PDF.