While it seems that chip industry has changed a lot in the last five years or so, that’s nothing compared to what will have to happen going forward. In the last five years the advent of iPhone — which brought real computing on a small, mobile form factor — has upended Intel’s dominance in the PC market. Just last week mobile chip maker Qualcomm surpassed Intel in market cap.

And on the server side and in high performance computing, the demand for more performance in a more efficient package has led to the adoption of new accelerator chips. The Top 500 list of the world’s fastest supercomputers came out Monday and showcases this trend with 62 supercomputers on the list using an accelerator. The fastest computer, called Titan, contains a mix of x86 chips and graphics processors to reach speeds of 17.59 petaflops. It was only four years ago that a GPU-powered computer had even made this list.

The Intel Xeon Phi coprocessor

Already the mobile industry uses a mix of cores to divide different processing jobs on a mobile device as a way to send the right job to the right processor, but also to save battery life by turning cores off when not in use and using a lower power core if possible for a job.

But accelerators can only take the chip industry so far, and are aimed at the high performance computing market. A multipetaflop machine still consumes a lot of power. One way to reduce that power consumption and boost performance is to cram more transistors on a chip by shrinking the space between transistors and reducing the overall size of the chip. This is called moving down the process node, but as the chip industry approaches feature widths of 20 and 14 nanometers, manufacturers are resorting to ever more complicated structures and materials to ensure that the chips perform well.

We’ve covered Intel’s 3-D transistors, Soitec’s new wafers, new materials and a variety of other breakthroughs all designed to keep this process shrinking. But researchers at McGill University have demonstrated that once you get to the atomic scale at levels of sub-five nanometers, the electric current on the chip gets all wonky — delivering a fourfold decrease in current. The researchers theorize when they shrink the channel that the electrons pass through they introduce “quantum weirdness.”

The “quantum weirdness” changes the way the current flows through a channel and so far those changes behave in unpredictable ways because the particles researchers are working with are at the atomic or sub-atomic scale. Which relates the research the top-level chip guys are doing to quantum theory and Schrodinger’s Cat. While Schrodinger’s famous thought experiement is an effort to articulate that the act of observing a quantum particle may change its state, the thought experiment is based on the fact that at subatomic scale materials behave differently.

From a write-up on the research:

As feature sizes in future chips shrink to the level of atoms, the resistance to current no longer increases at a consistent rate as devices shrink; instead the resistance “jumps around,” displaying the counterintuitive effects of quantum mechanics, says McGill Physics professor Peter Grütter.

This means that as chipmakers develop smaller processors or build any electronics with nano materials, the laws of physics will demand they change their materials and likely the structure of those materials, as well as conduct basic research to understand the new rules of playing at the atomic scale. Fortunately scientists at universities and researchers inside labs at place like IBM and HP are thinking about quantum physics and how it will change the rules of semiconductor manufacturing. And yes, there are some that are skipping the electronics part of the equation and skipping straight ahead to quantum computers, but I think our digital bits are here to stay for a few more decades.

Schrodinger’s cat image courtesy of Wikipedia.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Supercomputers and the Search for the Exascale Grail
• Listening platforms: finding the value in social media data
• The Internet of things: creating tomorrow’s health care

Chipmakers have been busily adding cores to their servers, but getting those cores to communicate without creating bottlenecks is a huge problem. And as the Web scales to reach billions of people, who are spending more time using online services, the infrastructure supporting those services is reaching a breaking point. Data centers that used to be the size of a corner gas station are now the size of a WalMart distribution center. Inside those centers are more servers containing many, many more CPU cores.

But at that scale communications between servers and between compute cores within servers are a problem. That’s why the IT industry is so excited about the software-defined networks (sometimes called fabrics) and OpenFlow protocols that will help make communications between servers scale. And inside servers, a similar level of virtualization and a focus on fabrics is gaining attention: What’s happening at the data-center scale is also happening inside the box.

For example, SeaMicro, the server maker that was recently acquired by AMD, built a 1.28 terabit compute fabric inside its server, which contains 256 cores. One SeaMicro box could replace 500 machines from five years ago and run at 96 percent of the power consumed by the old machines, according to a presentation the company made in January when it launched its most recent boxes. Another startup in the server space, Calxeda, which is building ARM-based servers with HP, is taking a similar approach, spending its R&D efforts on the fabric the handles communications between the many ARM chips inside its box.

Now that AMD has bought SeaMicro, which was using chips from Intel, the world’s largest chip company might be looking to make its own play in the webscale server market (as well as beef up its ability to connect a lot of cores for the high performance computing market that Cray serves). In the past Intel has said webscale will be only 10 percent of the total server market, but I think it’s wise to ensure it has a fabric technology of its own now that AMD has SeaMicro and Calxeda is in bed with ARM, Intel’s rival on a growing number of fronts.

Hence buying the engineers, IP and expertise of Cray, which pioneered interconnect technology that allows thousands of chips to communicate at high speeds. Chips are always going to be important inside servers, but now it’s time for fabrics to shine too. It’s a topic we’re going to be talking more about at our Structure 2012 event with SeaMicro’s former CEO Andrew Feldman and AMD’s Lisa Su.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• A near-term outlook for big data
• NewNet Q2: Google closes the quarter with a bang
• From car to cloud: the future of the in-vehicle app landscape

Cray's XK6 supercomputer

It looks like Oracle has some competition when it comes to selling big iron for big data. On Wednesday, Cray, the Seattle-based company best known for building some of the world’s fastest supercomputers, said it’s getting into the big data game. A new division within Cray, called YarcData, will leverage Cray’s experience working within data-intensive environments for customers such as Boeing in order to woo large-enterprises with big data needs.

Cray was short on details in a press release announcing the new division, but new YarcData SVP and GM Arvind Parthasarathi, formerly of Informatica is quoted saying, “YarcData is the nexus of the world’s most advanced technologies from Cray being applied to solve the world’s most challenging Big Data problems.” The natural leap is that Cray will design parallel-processing systems capable of incredible data throughput — something already required in the supercomputing space, where incredible processing capacity would be wasted without a steady data stream — but that will support today’s popular big data tools (e.g., Hadoop, analytic databases and predictive analytics software).

This type of system could be very valuable for organizations such as banks and intelligence agencies that want to run big data workloads as fast as possible — even process streaming data in real time– and the deep pockets to pay for Cray’s presumably pricey systems. Despite the fact that big-data framework Hadoop gained popularity in part because it’s designed to run on commodity hardware, there’s always a place for high-end hardware when milliseconds really do matter, and there’s something to be said for pre-configured systems that take the guesswork out of building a big data environment, as I explained recently in a piece for GigaOM Pro (sub req’d).

Cray isn’t alone in pushing this high-performance, enterprise-focused big data vision, though. Oracle made a splash in October when it announced a Big Data Appliance that marries Hadoop, R, NoSQL and other technologies to the high-end hardware Oracle obtained when it bought Sun Microsystems. IBM also has an extensive big data software portfolio complemented by a systems business that includes supercomputers, as well. And although it doesn’t have an HPC pedigree like the others, Teradata has years of experience building systems optimized for analytics.

Cray won’t likely become a household name in the big data world, and its notoriously secretive customers might never divulge what they’re using its analytics products for, but there certainly is a market — however small — for super-big, super-fast and super-expensive data.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Buying into big data appliances
• The importance of putting the U and I in visualization
• A near-term outlook for big data

The original Cray supercomputer

In the past decade supercomputers were dressed-up versions of Intel’s x86 machines, but increasingly supercomputers are borrowing innovations (and silicon in the form of ARM-based chips or DSPs) from the mobile and big data realms to add speed without guzzling too much power.

Prior to this century many supercomputers really were a different animal entirely, sporting specialty chips and software. But the industry turned to commodity chips in the early 2000s. Now, to meet the demands of exascale computing at low power, chip makers are taking inspiration from the cloud computing and mobile industries.

ARM tries supercomputing on for size

As the Supercomputing 2011 show gets under way in Seattle, Nvidia, Texas Instruments, ARM and others are announcing new silicon to power the machines we rely on for science, climate prediction and high-end simulations in industries that range from oil production to car design.

Nvidia is a fairly recent newcomer to the supercomputing market, but it has made huge strides since 2008, when it first starting pushing its graphics processors (GPUs) as a way to boost speed while keeping energy usage in check. It said it would use its high-end GPUs and its new GPU-plus-ARM chip to build a new supercomputer in Spain. This is the first time an ARM-based processor has made its way into a supercomputer. ARM thus far has been the chip of choice inside cell phones and tablets.

Accelerator chips advance in supercomputers

Japan's K supercomputer is the fastest in the world.

Nvidia is doing well with its GPUs, given that in the top 500 ranking of the world’s fastest supercomputers, 39 systems use GPUs as accelerators and 35 of these use Nvidia chips. The graphics processors are used in supercomputers because they can handle massively parallel tasks that high-end computing requires while using less energy than the typical CPUs made by Intel and AMD. Nvidia and its GPUs made their first appearance on the list in 2008, and the last time the top 500 list was published, six months ago, Nvidia chips were in 17 machines. To go to 35 today is a pretty big uptake.

Perhaps inspired by Nvidia’s success in getting its GPUs onto supercomputers, Texas Instruments is bringing its digital signal processors to the mix for high-performance computing. DSP chips are really good at math, and they are used in telecommunications chips and in routers. TI has been thinking about this for a while, but Monday was its first launch into the market formally.

New chips for the cloud

The same power-efficiency issues that plague those trying to advance supercomputing are hitting those who run webscale applications, from Facebook to Amazon Web Services. And while the cloud and web-scale data center operators aren’t looking for specialty gear, like Infiniband for networking, they are running one or a few applications on their hardware, similar in some ways to a supercomputer, where all workloads are optimized for speed.

This is why certain chip and hardware companies, such as Tilera, Calxeda and Applied Micro, see an opportunity to redesign the silicon and gear inside the cloud. Meanwhile, companies such as Adapteva, which makes a massively multicore chip for cell phones and HPC, see an opportunity in pushing into supercomputers and mobile handsets, where the need for more-powerful processors and lower power consumption are always at war. And with ARM piggybacking on this trend thanks to Nvidia, it’s clear that supercomputers want to be super without the influence of PCs.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• The fourth quarter of 2012 in cleantech
• Cloud computing infrastructure: 2012 and beyond
• Infrastructure Q1: IaaS Comes Down to Earth; Big Data Takes Flight

For the close to $50 million, which will be funded through the stimulus package, the labs will receive one of Cray’s XT6 supercomputers in the second half of 2010, followed by an even more powerful supercomputer with the code name “Baker” in 2011, and more high-performance computing gear in 2012. Cray, which reported pretty weak first-quarter earnings results earlier this month, says its XT6 was the first to break the petaflop barrier. While Cray didn’t say how fast the CMRS would be, the Register predicts that for $47 million, the labs will be able to buy on the order of 1 petaflop.

Cray is no stranger to barrier-breaking machines — it built the Jaguar, the world’s fastest supercomputer, which runs at 2.3 petaflops and is able to perform more than 2 million billion calculations a second (see Supercomputers and the Search for Exascale Grail, subscription required). The Jaguar is used by the Oak Ridge National Laboratory for researching various problems of world importance, including climate change research, but the CMRS will be the fastest first computer solely devoted to climate change.

Supercomputers have been used to calculate, model and forecast weather patterns, ice melt, sea level rise and other climate-changing elements for years. But the faster and more powerful the computer, the more data it can crunch and more accurate the predictions and forecasts can be. James Hack, who heads up climate research at ORNL and directs the National Center for Computational Sciences, hopes that the new climate supercomputer will “improve the fidelity of global climate modeling simulations.” The UN’s Intergovernmental Panel on Climate Change has recently come under increased scrutiny (warranted or not) and better modeling and prediction data will be able to help shrink the level of uncertainty and public backlash.

And supercomputing is just getting faster and more powerful. As Stacey has explained on GigaOM Pro: “The supercomputing industry strives to triple performance every 10 years, which means the industry needs to deliver an exaflop of performance (a billion billion calculations per second) by 2017,” (subscription required). Does the answer to the world’s warming problems lie in exascale computing? Given that humans will need to get on the path to reducing carbon emissions significantly by 2020, it probably does.

For more research on supercomputing check out GigaOM Pro (subscription required):

Supercomputers and the Search for the Exascale Grail

Image courtesy of Cray.

Some people refer to this shift as everything moving to the cloud, but whatever you call it, the trend of digitizing music, presentations and even books has made information portable and ephemeral enough that it’s rocking the world of chipmakers, device vendors and even server makers, whose products ground the cloud. In this article, I’ll talk about the effects of the cloud on the consumer and corporate client devices.

The Changing World of Devices

At the consumer and business user level, netbooks, smartphones and PCs are adapting to this new paradigm in several ways — allowing users to customize their gadgets to fit different needs. For example, a smartphone is for making phone calls, but thanks to the ease of web surfing brought on by Apple’s iPhone or even the Opera browser, such phones are getting bigger screens and more powerful application processors so they can handle nicer graphics and multiple applications.

Notebooks are becoming smaller and less power hungry — morphing into netbooks with smaller form factors and better battery life. Between the smartphone and the notebooks is another family of gadget, the mobile Internet device, or MID. In many ways, the MID is still undefined. But netbooks were one of the fastest-growing sellers in the last year, and ABI Research expects 35 million to be sold in 2009. That’s still just a fraction of the PC market, however.

As mobility becomes more important, thanks to ubiquitous wireless access, the traditional desktop PC market was finally surpassed at the end of last year by laptops. Part of this is because consumers love the convenience of mobility, but it’s also because when dealing with software programs in the cloud, the chips powering a desktop PC don’t offer as much of an advantage over the chips powering a laptop.

With the cloud fueling the growth in mobile devices, PC makers are trying two different strategies to combat erosion on the consumer and corporate front. The are making larger, more powerful workstations — sometimes called desktop supercomputers — and smaller, graphics-focused devices that can act as media servers.

Dell has shoved a bunch of graphics cards into a workstation that it plans to sell as a research-oriented superpowered desktop, and Cray has teamed up with Intel and Nvidia to produce the CX-1 desktop supercomputer. Heavy number crunchers, such as those perfecting digital special effects for movies, are the market for these desktop supercomputers. They are joined at the other end of of the spectrum by those consuming the end result of such heavy-duty computing. Later this year, consumers will be able to buy netbooks or cheap desktops that have CPUs tied to graphics processors that enable them to play HD videos delivered via the web on a home television.

Evolving Gadgets Mean a Changing Market for Chips

As the rigid lines between our mobile devices dissolve, chipmakers see an opportunity. When it comes to the brains of these gadgets, Intel, the largest chip company in the world, launched a low-power x86 chip that could act as the engine for notebooks, netbooks and even phones. However, the traditional companies making the “brains” of smartphones aren’t letting Intel enter their market without a fight. Vendors such as Texas Instruments, Qualcomm, Samsung and Freescale are building applications processors based on an IP core from ARM, that are becoming powerful enough to run mobile Internet devices, and perhaps netbooks. Even graphics chipmaker Nvidia has built an application processor for smartphones and mobile Internet devices.

This battle for the brains of these highly portable devices is a battle between these vendors, but it’s also a battle of different chip architectures: Intel’s x86 and the IP cores licensed by ARM. Intel has the software advantage — most business software is written for x86 chips rather than for ARM cores. ARM, however, has a power advantage. Its chips are built to work on battery-powered devices that people expect to run for a full day or longer between charges. Intel has lowered its power consumption considerably with Atom, but it still sucks down 2-3 times as much energy as most ARM-based chips.

For ARM, the rise of the cloud eliminates the need for x86 software. If most of a user’s applications can be accessed via the web, ARM just needs to focus on making its chips work with various browsers and common web protocols, such as Flash. Storing data in the cloud also negates the need for large hard drives for keeping files. At smaller sizes, it might be economical to put in a solid state drive, which have a higher cost per Gigabyte than a spinning disk, but are smaller and consume less power. Given that size and power consumption are two of the biggest concerns for mobile device makers, the cloud changes the game.

For the end user, digitized content accessed over the cloud enables smaller, more portable devices. It’s also changing the market for the traditional desktop PCs, since mobile devices are becoming more competitive with desktops. As these devices go mobile, Intel has a chance to move downstream into less-powerful processors and chipmakers using the ARM architecture may be able to move upstream with their low-power application processors.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Report: The Future of Netbooks!
• Who and what to watch in the new era of the living room
• CES 2012: a recap and analysis

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Who and what to watch in the new era of the living room
• The future of mobile: a segment analysis by GigaOM Pro
• The Case for Increased M&A in 2011: Actions and Outlooks

The Cray CX1 computer launched today, with specs that include either 32 or 64 Intel cores and 4 terabytes of internal storage. The new machine, which runs a new version of Microsoft Windows, is a testament to both the demand for and the democratization of computing power. Indeed, people who earlier might have turned to grids or supercomputers for their problems are building powerful desktops with accelerator chips, while less scientifically minded folks, such as traders or product designers, who want to render things in 3-D are seeking more processing power.

Cray’s CX1 is the smallest supercomputer the venerable firm has ever built, but its downmarket shift is a response to both the needs of the market and the presence of accelerator chips trying to muscle in on its scientific computing turf in the high and low end. Chips such as IBM’s cell processor or GPUs from AMD or Nvidia are being dolled up with programming tools to take on scientific computing. The multiple cores in the Cell chip and GPUs are designed to parallelize tasks and execute them faster than a general purpose CPU, like the x86 processors offered by Intel.

At the desktop level, Nvidia has been touting stories such as the €4,000 (about $5,700 today) “supercomputer” built by scientists at the University of Antwerp creating 3-D images of internal organs that uses GPUs. With the CX1, Cray is acknowledging that trend and trying to ride it.

The effort to broaden its market comes as Cray sees it dominance in the supercomputing world waning. The top supercomputer in the world runs on a combined x86 and Cell processors. In the most recent list of the Top 500 supercomputers, Cray only made 16 of the machines for a 3.2 percent share of the fastest computers in the world. That’s quite a decline from when the Top 500 organization started tracking the data 15 years ago and Cray made 205 systems on the list. So Cray is thinking small to expand its market as the market demands more computing power.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• CES 2012: a recap and analysis
• Supercomputers and the Search for the Exascale Grail
• Report: The Future of Netbooks!

Something about big, round numbers excites the computing world and a petaflop, which is a measure of how fast a computer can complete an operation, is pretty big and round. The technology industry’s excitement around Roadrunner and ASCI Red is understandable — they both signaled a big shift in supercomputing — from its core technologies to the tasks was supposed to do.

ASCI Red, with its multi-core x86 processors, signaled the future of the supercomputing industry as the computers moved away from a glamorous assortment of specialty-built processors crammed into custom cabinets running Unix. Almost a decade earlier it was a Cray computer in 1988 that beat the 1-gigaflop record.

As a general rule, supercomputers increase in performance 1,000 times every decade, although factors on the software side may limit growth in years to come.

Short History of Modern SuperComputer

Cray’s first supercomputer, which marked the beginning of the industry as we know it, was installed in 1976 and ran at 160 megaflops. It cost $8.8 million. Like IBM’s Roadrunner, it was installed at Los Alamos National Lab. It was the first to run on integrated circuits and was shaped like a “C” to keep the twisted pair connecting the processors from being too long and causing too much latency.

In 1982, Cray introduced the first multiprocessor architecture for supercomputers. The processing power in that first Cray is less than the several gigaflops most cheap PCs can run today.

That’s a common theme in supercomputing, as yesterday’s supercomputers become today’s cloud compute grids and the clusters of servers running a hedge fund’s algorithmic trading strategies.

The line between supercomputing, which was geared at solving scientific problems, and high-performance computing, which required bulk processing power and less refinement, has blurred. Many supercomputers have been lumped in with high performance computing, and because both can use commodity hardware and open-source software, their sky-high pricing has fallen.

Earlier this year, that led research firm IDC to shift its market data a bit and compress supercomputing and the high-performance computing systems costing more than $500,000 into the same category. That category, by the way, grew 24 percent last year to $3.2 billion. But since the rise of clustered computing back in 2002, most supercomputers have become less super and more like regular computers.

Unix lost out as an operating system around 2004 when more than half of the computers in the Top 500 list ran Linux. Instead of the closely linked twisted pair of Cray’s system, today’s supercomputers use Infiniband. Some of them can still costs millions to build, but when all is said and done, most are built on x86 processors running Linux.

Cell Side Computing & Beyond x86

The rise of the x86 architecture is one of the reasons Cray formed a partnership with Intel. There was a desire for a second source of chips after AMD’s production delays caused Cray a financial hiccup, but also a realization by Intel that supercomputing was now a growing market dominated by its processors.

In Nov. 2007, 71 percent of the Top 500 supercomputers contained Intel chips. Ten years ago that number was 2.6 percent, and five years ago it was 11 percent. The x86 trend and democratization of supercomputing is also a boon to makers of HPC systems, such as Rackable and Appro.

But the Crays of the world may not stand on ceremony for Intel or AMD very long. IBM’s newly launched Roadrunner, the fastest supercomputer working today (supercomputers have shorter heydays than a viral video star), runs on a combination of AMD’s x86 and IBM’s Cell processors connected using Infiniband.

One of the reasons Roadrunner is so unique is that IBM had to develop special software that would work with both types of processors. The Cell architecture was designed for the PlayStation and is now morphing into a performance chip for other applications, a process that IBM is likely to follow in the future.

Supercomputers comprised of specialized processors are an emerging trend in the high-performance computing world, with players such as Nvidia bragging about its ability to crunch scientific data faster than general purpose CPUs.

So far, a Nvidia-powered supercomputer hasn’t broken the Top 500, but Steve Conway, IDC research vice president for HPC, says such different architectures might become more important in the next few years. If it does, it will be worth watching, because trends in supercomputing generally trickle downstream to the rest of the computer-using population eventually.

photos courtesy of IBM and Cray

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• Supercomputers and the Search for the Exascale Grail
• Who and what to watch in the new era of the living room
• CES 2012: a recap and analysis

It also followed its competitors and introduced what HP believes will be the building block for the scalable data center, a new, two-in-one blade server. Like IBM’s iDataPlex, Sun’s Blackbox and Dell’s cloud computing efforts, HP is viewing the noise around cloud computing as a chance to sell more hardware — specialized, HP-built 10u racks of 32 blade servers containing 128 cores, to be exact.

I don’t know how important it is to build out scalable computing efforts with IBM’s iDataPlex or HP’s offerings rather than an array of commodity x86 boxes, but the merging of high-performance computing and cloud computing infrastructure is a triumph of the grid architecture running specialized software. It’s also the same trend that is leading Cray to work with Intel on designing the next generation of supercomputers.

HP’s blade servers are designed to save space in the data centers, but Paul Miller, a VP of marketing with HP, acknowledged that space was not at the premium that power is. Blade servers run pretty hot so it’s counterintuitive to think that cramming two of them in one blade makes much sense from an energy efficiency point of view. Miller said HP’s offering can be used with standard HP racks for water cooling or in conjunction with its Dynamic Smart Cooling technology. Without knowing how many watts are consumed, it’s hard to judge how energy efficient these blades are.

Update: HP has provided more information with regard to the server’s efficiency saying it ran in tests at 165 watts per server, and emphasizes that the servers are 60 % more efficient than stand alone boxes in part because they combine two servers into one shell, requiring one fan and power supply for double the compute power.

Fox Interactive Media is one of HP’s clients, so clearly there’s a market for HP’s brand of two-in-one blades, but HP will have to compete with existing hardware vendors such as Rackable and Silicon Metrics, who seem to be doing fine providing energy-efficient scalable hardware for Web 2.0 and cloud computing companies.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• The Case for Increased M&A in 2011: Actions and Outlooks
• Takeaways from the second quarter in cloud and data
• Cloud computing infrastructure: 2012 and beyond