Feeds

HPC > More stories

Green supercomputer benchmarks make boffins see red, check blueprints

SC13 The biannual Green500 list of the most energy-efficient supercomputers has broken new ground in two important ways: for the first time an HPC system broke the 4 gigaflops per watt barrier, and also for the first time all the top 10 systems benefitted from GPU acceleration. Then there's a third bit of note: the benchmarks are …
Rik Myslewski, 21 Nov 2013

Nvidia to Intel: 'Which HPC chip brain will win? Let the people decide'

SC13 Nvidia is of the opinion that in the tussle with Intel as to whether Nvidia's Tesla GPU accelerators or Chipzilla's Xeon Phi many-core CPU coprocessors will dominate the supercomputing market, the HPC community has already voted with its checkbooks. "This community continues to invest in GPU computing – GPU-based accelerated …
Rik Myslewski, 20 Nov 2013

Micron takes on Intel with 'breakthrough' processor for streaming data

Memory specialist Micron has announced a new accelerator processor that it claims outperforms Intel's chips when it comes to dealing with streaming data. The "Automata Processor" was announced by the company on Monday and billed as a device that uses the inherent parallelism of memory architectures to speed the ingestion and …
Jack Clark, 19 Nov 2013

Decades ago, computing was saved by CMOS. Today, no hero is in sight

SC13 The general chair of the SC13 supercomputing conference thinks the semiconducting industry has reached a tipping point more radical – and uncertain – than it has gone through in decades. "We've reached the end of a technological era where we had a very stable technology," Bill Gropp, Thomas M. Siebel Chair in Computer Science at …
Rik Myslewski, 19 Nov 2013
The Cave 2 visualisation facility in Melbourne, Australia

Why not build a cluster out of WORKSTATIONS?

Australia's Monash University has just opened an amazing visualisation facility called Cave 2. The facility offers an eight-metre long, 320-degree wall comprised of 80 3D monitors with a combined resolution of 27320 x 3072 pixels. “We spend millions of dollars building supercomputers and then look at the results they produce on …
Simon Sharwood, 19 Nov 2013

Nvidia, AMD tout 12GB GPUs for supers ... But ONE question remains

SC13 The battle of the big-memory GPU cards targeted at HPC and the data center is now well underway, with AMD having unveiled its FirePro S10000 12GB Edition card, and Nvidia announcing its 12GB Tesla K40 GPU accelerator card today. Nvidia Tesla K40 GPU card Nvidia Tesla K40 ... Double your pleasure, double your GDDR5 memory ( …
Rik Myslewski, 18 Nov 2013

Top500: 'Sky River 2' still rules as graphics tech leaves HPC applecart largely untouched

SC13 The Top500 ranking of the world's fastest supercomputers has been released, and the list of the top five systems could very well be simply a Xerox copy of the previous list, which came out back in summer. In the June rankings, the number one spot was taken by the massively parallel Tianhe-2 (Milky Way-2) at China's National …
Rik Myslewski, 18 Nov 2013

IBM and Nvidia: We'll build your data center like a SUPERCOMPUTER

SC13 IBM and Nvidia have announced a partnership to "bring supercomputer performance to the corporate data center," in the words of Nvidia's accelerated computing honcho Ian Buck, with systems based on Nvidia Tesla GPUs and IBM Power8 CPUs, and to accelerate IBM enterprise software using Nvidia GPUs. "This is the biggest technology …
Rik Myslewski, 18 Nov 2013

Nvidia reveals CUDA 6, joins CPU-GPU shared memory party

Nvidia has announced the latest version of its GPU programming language, CUDA 6, which adds a "Unified Memory" capability that, as its name implies, relieves programmers from the trials and tribulations of having to manually copy data back and forth between separate CPU and GPU memory spaces. CUDA 6 Unified Memory schematic …
Rik Myslewski, 16 Nov 2013
IBM Watson QA Power7 cluster

IBM. HUMAN-crushing SUPERCOMPUTER Watson. The Cloud. You know where THIS is going

IBM is exposing the super computer brain that crushed puny humans in a TV quiz show to the entire internet. Big Blue announced its IBM Watson Developers Cloud on Thursday, inviting all comers to build big data apps that tap the cognitive powers of its Watson super computer. The idea is to tempt application authors keen on …
Gavin Clarke, 14 Nov 2013
2001: A Space Odyssey

Boffins look down back of Amazon Web Services, find a SUPERCOMPUTER

What runs faster than the majority of the world's supercomputers, costs less, and was used to research organic solar-power cells? The answer is Megarun, a 1.21-petaflop super that was spun up by Cycle Computing in the AMAZON CLOUD. Cycle Computing revealed its Megarun beast on Tuesday before the kickoff of Amazon Web Services's …
Jack Clark, 12 Nov 2013
Bird's eye view of the proposed new Nvidia HQ

GPU secrets unveiled for student cluster warriors

SCC'13 We’re less than two weeks away from the start of the SC13 Student Cluster Competition in Denver. Right now, the 12 student teams are turning over every rock they can find in their hardware and software stack in an effort to eke (and geek) out every last bit of performance. Time is short. In a week or less, they’ll be packing up …
Moments of perspiration

WTF is WRF? Student cluster-wrestlers cram for app SMACKDOWN

SCC 2013 It’s crunch time for the students who will be competing at the SC13 Student Cluster Competition in Denver. The 11 university teams – plus one group of plucky high schoolers – are in cram mode now, trying to figure out how to wring every last bit of performance out of their gear. All teams will be running the same HPC benchmarks …

Excited students, $2,500, quivering racks and dreams of glory

SCC 2013 The new "Commodity Track" of the upcoming SC13 Student Cluster Competition has hit a chord with cluster competition aficionados worldwide and Register readers alike. I laid out the terms of this competition in a recent story, and plenty of you weighed in with recommendations on how these kids could get the most HPC bang out of …

Readers! Here's your chance to join the Celebrity Pro-Am Cluster Challenge

SCC'13 For the first time, HPC professionals will compete against the SC13 Student Cluster Competition (SCC) teams in a winner-take-all cluster showdown. The new event, dubbed the “Celebrity Pro-Am Cluster Challenge”, will begin right after the students turn in their last SCC results on Wednesday afternoon, November 20. The Pro-Am …
CatalystNVRAM

Nuke-whisperers stuff terabytes of flash into heretical 'Catalyst' super

Three technological heavyweights have come together to spin-up a radically different supercomputer cluster designed to crunch "big data" workloads rather than the simulation and modeling jobs of typical HPC rigs. The collaboration between Lawrence Livermore National Laboratory, Intel, and Cray was announced on Monday and sees …
Jack Clark, 4 Nov 2013

Cray scoops Brit switch maker staff and assets from administrator

Cray, the supercomputer maker, has bought intellectual property assets from the collapsed UK switch maker Gnodal and is taking on "the vast majority of staff" to bulk up its European R&D team. Bristol-based Gnodal, a small start-up with just 15 employees, was venture-backed so we infer that it failed to get a new funding round …
Drew Cullen, 4 Nov 2013

Number-crunching quant cooks up gambling machine, promises untold RICHES

HPC blog Have you ever wanted to lay a bet down on the Las Vegas sports books? Or take a bundle of money from the suckers in your office's Final Four betting pool? Is it possible to win sports bets consistently over the long haul? According to the guys at PredictionMachine.com, the answer is yes. Their secret weapon? Numbers, baby – it’s …
Openstack log

Mellanox bakes self into OpenStack, hopes world+dog bytes

Ahead of next week's OpenStack summit in Hong Kong, Mellanox has let it be known that it's baked itself into OpenStack, then baked OpenStack into several of its products. The Hong Kong gabfest is the coming out party for Havana, the eighth release of OpenStack. Everyone who's anyone in the world of cloud is piling in to pop …
Shows a rack of Azul appliances.

Cash-strapped students hungrily eye up old, unloved racks

SCC'13 How much supercomputing can you do with $2,500 worth of hardware? The four teams competing in the SC13 Student Cluster Commodity Track Competition will answer precisely this question - and more. The Commodity Track is a new addition to the SC Student Cluster Competition event this year. We all know and love the Standard Track: …

Intel: Our first five parallel-computing schools are open for business

Chip giant Intel has begun funding research into ways to make applications easier to write for parallel processing systems, and to teach those methods to future generations of computer engineers and scientists. The first five institutions to qualify as Intel Parallel Computing Centres are: the Konrad Zuse Information Technology …
Tony Smith, 24 Oct 2013
Hadoop Elephant

Avert your eyes! Hortonworks mates Hadoop beast with SAS

Hadoop company Hortonworks is teaming up with SAS on a strategic partnership to integrate its analytics platform with SAS's suite of data technologies. The alliance was announced on Friday and will give enterprises a "SAS/ACCESS" interface into the Hortonworks Data Platform, which will let them run tools such as Visual Analytics …
Jack Clark, 19 Oct 2013
Elephant

Hadoop 2 stampedes onto world's mega compute clusters

The Apache Software Foundation has branded the data analytics Hadoop platform with version 2 and sent the Elephant-logoed system stampeding out into the wild. The second version of the open-source technology comes with a refreshed compute engine via the YARN data processing and service engine, and the addition of high- …
Jack Clark, 16 Oct 2013
Predator drone, credit Wikipedia

How were your hols, cluster kids? Oh, partied, studied... did we mention WE BUILT DRONES

HPC blog Among the five teams who will be defending America’s Big Iron honour at the upcoming Student Cluster Competition (SCC) are a few students who skipped the keg parties to, er, build, fly, program and optimise the performance of unmanned aerial vehicles. These students will do battle, beginning on 18 November at the SC13 conference …

Students schlep from afar to join the quest for international HPC glory

SCC'13 Three teams of students will be jetting in from overseas to enter this year's Student Cluster Competition, due to kick off on November 18 at the annual SC13 Supercomputing Conference.</p? The teams will be competing in the Big Iron division where undergraduate students design, build, and tune their very own HPC clusters. They’ll …
Team Tsinghua, Overall Winners at the ISC 2012 Student Cluster Competition

Students prep for battle of wits, MIPs and watts: It's student cluster-wrestling time

SCC'13 The countdown is on. Twelve university teams are preparing for another epic battle at the student cluster-wrestling match, the SC13 Student Cluster Competition (SCC). The gig will take place during the 2013 Supercomputing Conference in Denver, Colorado, beginning 18 November. The teams will compete on the SC13 exhibition hall …
A boffin

'Computer GEEKS' snatch NOBEL Prize for chemistry - without using chemicals

Three chemists have been awarded the Nobel Prize in their field, not for arcane experiments with bubbling beakers but for writing software to make computers do all the hard work. "In the 1970s, Martin Karplus, Michael Levitt and Arieh Warshel laid the foundation for the powerful programs that are used to understand and predict …
Iain Thomson, 9 Oct 2013

Cray turns cluster crank with ScaleMP

Does your performance in the datacenter suffer because you don’t have enough memory to really get the job done? Do you have apps that don’t perform well on clusters, or don’t parallelize at all? If this describes you or a loved one, read on, because Cray thinks it has the solution for you. Cray, with partner ScaleMP, recently …
Artist impression of Bristol's quantum chip

Quantum computing gets recursive

When a quantum computer can produce results that would take thousands of years to produce out of a classical computer, an obvious question arises: if you've given the wrong answer, how would you know? That's a question to which University of Vienna boffins have turned their attention to. A computation involving a handful of …

EMC snaps up ex Symantec veep to rule new HPC skunkworks

EMC has recruited an ex-Symantec exec to lord it over its Emerging Technology Products division. His product brief includes "hybrid Cloud Gateways and High Performance Computing storage" which is fine ... except EMC hasn't got any such products. Chirantan “CJ” Desai will be the president of the newly-formed Emerging Technology …
Chris Mellor, 27 Sep 2013

StorNext gets revamp, Quantum claims 5x data throughput boost

Quantum has taken its StorNext file management system and updated it from top to bottom, making it multi-core processor aware and more scalable so it can handle five times more data than StorNext 4. The company says workflows in the digital media and entertainment business are becoming more complex, involving bigger files, …
Chris Mellor, 23 Sep 2013
Hadoop elephant

Apache Foundation embraces real time big data cruncher 'Storm'

The Apache Foundation has voted to accept the “Storm” real time data processing tool into its incubator program, the first step towards making it an official part of the Foundation's open source offerings. Storm aims to do for real time data processing what Hadoop did for batch processing: queue jobs and send them off to a …
Simon Sharwood, 19 Sep 2013

Memory muddle muddies Intel's Exascale ambitions

IDF13 Intel's lofty attempt to make a supercomputer capable of an exaflop by 2020 while consuming a mere 20 megawatts of power is running into major problems due to the pesky laws of physics. When Intel announced its exaflop goal back in 2011, the chipmaking giant talked up a variety of technologies it was bringing to bear on the …
Jack Clark, 14 Sep 2013

The future of PCIe: Get small, speed up, think outside the box

IDF13 The near-ubiquitous PCI Express interconnect – aka PCIe – is finding its way into mobile devices, working its way into cabling, and is on schedule to double its throughput in 2015 to a jaw-dropping 64 gigabytes per second in 16-lane configurations. So said Ramin Neshati, the Marketing Workgroup Chair of the PCI-SIG, when The Reg …
Rik Myslewski, 13 Sep 2013
IBM logo

IBM forges NextScale servers for HPC and hyperscale cheapskates

IDF13 Concurrent with Intel's launch of the "Ivy Bridge-EP" Xeon E5-2600 v2 processors in San Francisco today, Big Blue trotted out its most vanity-free machines to date, the NextScale line. The new systems are designed specifically to compete with low-cost, stripped down alternatives from Hewlett-Packard, Dell, Silicon Graphics, and …
AMD Llano vs Intel Sandy Bridge notebook chips

Wanna boost app speed? Think of the server, and tune 'er to NUMA

HPC on Wall Street The HPC on Wall Street conference was hosted in the Big Apple on Monday, and while there was a lot–and we mean a lot–of talk about big data, one presentation stood out as being potentially much more useful in the long run than all of the big data bloviations. The talk was given by one of the founders of a financial services …
ARM versus Atom

Intel's Avoton Atoms give microservers muscle – and Xeon-class features

With the launch of the "Avoton" Atom C2000 server chips, Intel is putting its second-generation of 64-bit, server-class Atom processors into the field - and what is arguably the first such Atom that is truly designed for modern server workloads. The C2000 has enough computing oomph, enough memory capacity, and integrated memory …

Fujitsu to push 28 nanometer limits with Sparc64 X+

Hot Chips Fujitsu wants to squeeze more performance out of its homegrown Sparc64 X processor for commercial and supercomputing workloads, and it can't wait until Taiwan Semiconductor Manufacturing Corp, its foundry partner, gets 20 nanometer processes into the field and ramped. So the engineers at Fujitsu have gone back over the design …

Intel bakes super-snooper to stop industrial espionage

Intel has created a Hadoop-based rig that analyses just about every network event in the company – four to six billion of them on business days - in close to real time so it can spot threats including industrial espionage. Intel officials declined to name the tool, saying it would not be "productive" to disclose its name, but …
Simon Sharwood, 21 Aug 2013
Hadoop Elephant

Intel adds Lustre support to Hadoop

World+dog agrees that Hadoop is a very fine tool with which to tackle map reduce chores, but the software has a couple of constraints, especially its reliance on the Hadoop Distributed File System (HDFS). There's nothing wrong with HDFS, but its integration with Hadoop means the software needs a dedicated cluster of computers on …
Simon Sharwood, 21 Aug 2013

VLSCI fires up 20 teraflop Barcoo

The Victorian Life Sciences Computation Initiative – VLSCI – has gone live with its latest big iron, Barcoo, an x86 architecture machine with double the capacity of the facility's Merri x86 system. The 70-node Barcoo runs 1,120 Sandy Bridge cores (16 cores per node), with 20 Xeon Phi 5110P cards distributed across ten nodes. …

Cray posts modest loss, awaits Q4 revenue wave

Supercomputer maker Cray turned in a slightly better than expected second quarter, with a modest bump in revenues and a slight loss. This is a win in the ever-choppy supercomputer racket – and particularly for Cray in a second quarter. For the past three years, Cray has been cramming a large portion of its sales in the final …