Depth

In Depth: GPU in the cloud: what does it mean?

The new Kepler GPU that Nvidia recently announced has been five years in the making.

It will be at the heart of supercomputers that will help make scientific discoveries as well as powering gaming clouds and high resolution remote computing. But why is Kepler more than just another really powerful, really expensive GPU?

If it was just really powerful, Kepler would still be impressive. Demonstrating a combination of fluid simulation and ray tracing, Nvidia CEO Jen-Hsun Huang pointed out that "Doing ray tracing for films takes up the vast majority of processing time – the hours and hours that are necessary to render a frame – and with Kepler we’re able to do ray tracing in real time.

"These are real time simulated effects that are only possible because of high performance computing only possible because were really doing fluid simulation, light simulation. Simulation and computer graphics are merging; in a few years computer graphics will look nothing like the easily shaded graphics we see in console games today."

Maya on Mac

Faster and lower power

Architecturally, Kepler is both faster than the previous Fermi GPU and lower power; there are many more cores but they run at 750MHz rather than 1.3GHz.

Two GPUs on a graphics card like the Kepler-powered GTX 690 will be able to communicate directly with each other; they can also communicate with up to 32 CPU cores instead of just one CPU at a time, and data parallelism means the GPU can look at the results of computations and decide what to do next instead of sending information back to the CPU and waiting for instructions.

It also has a memory management unit; combined with Nvidia’s hypervisor and VGX architecture, that lets Kepler be a virtual GPU for remote access with a tool like Citrix Receiver on a tablet or Microsoft RemoteFX on a thin client – or power gaming cloud services that Nvidia is calling GeForce Grid.

Not all of that is in the first Kepler GPU, the Tesla K10 that’s just started shipping, but all the features will be in the Tesla K20, coming in the fourth quarter of 2012.

Services like Playcast and Gaikai will use Kepler GPUs later this year to let you play console-style games on any device with an H.264 decoder. That’s similar to the OnLive service but Nvidia General Manager Phil Eisler says GeForce Grid will be much more efficient to run.

Gaikai

"With the first generation of cloud gaming that’s out there, you pretty much take a one to one ratio of one computer, one graphics card to one game, which is pretty expensive. The new Kepler architecture is much more power efficient; we can actually render a game in half the power.

"Plus the built in encoder means you can offload encoding from the CPU so you can run many more games per server; you can go from what is effectively one game per server to about eight games per server and that reduces the cost by that much and reduces power by half."

The cost of running a service will be low enough that Nvidia CEO Jen-Hsuan Huang told TechRadar the expects the monthly price for access to mainstream games will be the same as streaming films from Netflix. "Our goal is to be streaming at a cost level like Netflix. In which case you’ll be able to enjoy hundres of games, thousands of games in a library for a month. And for blockbuster video games the moment that it comes out, the nanosecond it comes out, you’ll be able to enjoy that for some premium charge."

Huang thinks that cable TV companies and Internet TV providers will offer their own gaming services. "They offer different channels and instead of ABC and CBS there would be potentially a channel that says GeForce GRID and has a whole bunch of games inside."

Kepler is going to power high resolution remote computing for work and high performance gaming in the cloud, but what about putting it in your home PC and having your own cloud? Huang likes the idea but he’s realistic about how well it would work in practice.

"The challenge is you want to be able to stream at a very low latency and that PC sitting in a den somewhere is literally right in front of you but we need to stream that over the clumsy Wi-Fi in people homes so there’s a lot of obstacles. That’s exactly the PC I want at home though. I want a PC with three GTX 690s – because that’s the most you can put in a PC- and put that in the basement somewhere and just stream it to wherever our family happens to be."

One thing Nvidia isn’t talking about this week is whether any of the same technology powering Kepler is going to show up in the ARM CPU it promised to build back at CES 2011, but Project Denver is still going strong according to Chief Scientist Bill Dally.

"It’s an ARM core with performance better than you can get with cores availability from ARM and it has substantially better energy efficiency even at this higher performance. That’s all we’re saying about it now, because we don’t want to tip our hand and have our competitors know what we’re doing."

Huang is making his usual bold predictions about Project Denver though; "You are going to be so happy," he promised. It doesn’t sound as if they’ll be ready for the Windows RT launch though.




TechRadar: computing components news

In Depth: Apple WWDC 2012: what to expect

It’s nearly time for WWDC 2012, Apple’s sold-out World Wide Developers Conference, and that means the Apple rumour factory is in full flow.

There’s a difference between a wish list and rock-solid predictions, however, and the internet has more of the former than the latter. So what can we really expect from this year’s WWDC?

OS X Mountain Lion at WWDC

We know about this already: Gatekeeper security, iCloud integration, the new notification and game centres, AirPlay mirroring… OS X Mountain Lion is looking pretty tasty, and it’ll be in near-final form at WWDC.

A launch date announcement is almost certain and a public beta a distinct possibility, but our favourite rumour is that Mountain Lion will be a free upgrade. That’s not as far fetched as it sounds: Apple is giving free copies of Snow Leopard to MobileMe users who haven’t switched to iCloud, and of course iOS upgrades are already free.

WWDC unveiling of iOS 6

This one’s a given: Apple’s on a yearly release schedule for iOS, and the whole thing will be signed off and ready for the expected iPhone 5 launch in October. There are all kinds of tantalising possibilities: more Siri, both in terms of device support and software integration; NFC; some kind of dual-app multitasking for iPads so you can look at two things at once; Apple’s long-rumoured mapping API; and perhaps an improved notifications area with support for more widgets and the ability to access commonly-used features such as Airplane Mode. Can we make our annual request for multiple user accounts on the iPad, please? Thanks.

WWDC hardware announcements

WWDC is primarily a software event, but that doesn’t mean we won’t see new kit: Apple has unveiled important products there in the past such as the iPhone 4 and the 2009 MacBook Pro. There are four key hardware rumours this year: the new iPhone, Retina MacBook Pros, Apple TV and the iPad Mini.

The new iPhone, aka the iPhone 5, at WWDC

It’s coming, we know, but the D in WWDC stands for Developers, not "Dude, it’s the new iPhone!" Unless the incoming iPhone 5 is significantly different from a developer’s perspective — that is, if it has a completely different aspect ratio or other significant hardware change, or if it runs Android — then we don’t think the new iPhone’s going to make an appearance. Others, however, beg to differ.

WWDC unveiling of Retina MacBook Pros

They’re coming, we know, but the big question is when: while OS X already contains a HiDPI mode for retina-style displays, they’re still very challenging bits of hardware to make. The MacBook Pro is certainly due a refresh, but a retina refresh might be pushing it for 2012.

A new Apple TV at WWDC

We’re not feeling this one. Apple TV is still officially a hobby, and while it runs a variant of iOS Apple hasn’t opened it up to developers yet. That may well change at WWDC, but we a significant Apple TV announcement is a long shot.

The iPad Mini at WWDC

It exists, and it’s rumoured for a 2012 release, so why not unveil it at WWDC? Assuming that a 7.85-inch iPad Mini has been given the green light, a June unveiling would generate enormous excitement, annoying Amazon, Android manufacturers and Windows 8 OEMs simultaneously without overshadowing the Autumn launch of the iPhone 5. If Apple’s going to embrace the entire tablet market as it did the digital music market with its various iPods, then the iPad Mini is inevitable.

TechRadar: All latest Laptops news feeds

In Depth: 10 best free product key finders

10 best free product key finders

Reinstalling Windows is always a hassle, but if you’ve lost a few product keys then it could become a real nightmare. Are they on a CD case, a manual, in an old email somewhere? You might not be able to get your system working properly again until you can track them down.

It doesn’t have to be this way, though. If you install a product key finder now, then it will scan your PC, and report on any product keys it finds (expect the list to include Windows and Microsoft Office as a minimum, and often many more). Print out the report or save it to disc and you’ll always have your keys to hand, should disaster strike – much more convenient.

Which is the best product key finder, then? Good question – there’s a lot of competition – but we put 10 of the best free key finders to the test in an effort to find out. Keep reading to find out what we discovered.

1. Belarc Advisor 8.2.7.7

Total keys supported: 100+
Supported products include: Windows, Office, CyberLink apps, VMware Workstation, Nero Burning ROM

Belarc Advisor

Free for personal use only, Belarc Advisor is a powerful system information tool which builds up a very detailed picture of your PC hardware and software. This is way more than we need, but you don’t have to pay attention to that information if you don’t want to – just click Software Licences and you’ll find keys for Windows, Office, CyberLink applications, Norton Internet Security and more.

Score: 4/5

Free PC Audit 2.1

Total keys supported: 10+
Supported products include: Windows, Office

Free PC Audit

Run Free PC Audit and it’ll immediately display a summary of your PC hardware, installed and running software. The program only managed to display the Windows and Office product keys on our test PC, but it could still be useful to see and save the full list of your other installed applications. The program doesn’t require installation, making it convenient to use, and doesn’t include annoying adware – rare amongst this type of tool.

Score: 3/5

KeyFinder Thing 3.1.6

Total keys supported: 90
Supported products include: Windows 7, Office 2010, Visual Studio 2005, Adobe CS2-CS5 products

KeyFinder Thing

KeyFinder Thing is a basic key finder tool. It’s a little dated now – there’s coverage for Microsoft Visual Studio, for instance, but only up to 2005 – so is really only useful as a basic product checker for Windows and a few old games. Even then, the program doesn’t fully work with 64-bit systems, and it comes bundled with the AVG Security toolbar for extra irritation.

Score: 1.5/5

LicenseCrawler 1.9.255

Total keys supported: 200+
Supported products include: Windows, Microsoft Office, CyberLink applications

LicenseCrawler

The free-for-personal-use LicenceCrawler takes a unusual approach to finding product keys, simply scanning the Registry and displaying likely-looking values. This can make for a complex report, sometimes including entries which aren’t product keys at all, and an in-your-face nag screen is another irritation. The program can find a lot of keys, though, and these are easily saved to a text file for later reference.

Score: 3.5/5

Magical Jelly Bean Keyfinder 2.0.8

Total keys supported: 300
Supported products include: Windows, Office, Nero Burning Rom 5-7

Magical Jelly Bean Keyfinder

Like many of the competition, Magical Jelly Bean Keyfinder is a little out-of-date; it’ll give you your Windows 7 and Office 2010 keys, but for instance couldn’t display our Nero 11 key as it doesn’t support anything later than Nero 7. Unusually, though, the program has an editable configuration file, so if you’re willing to do some work then you may be able to add support for one or two extra keys yourself.

Score: 3/5

MSKeyViewer Plus 2.2.0

Total keys supported: 101
Supported products include: Windows, Microsoft Office, SQL Server 7/2008, WinZip 8-14

MSKeyViewer Plus

MSKeyViewer Plus 2.2.0 is a simple tool which is mainly useful for displaying a few key Microsoft product keys: Windows, Office 97-2010, and so on. There are a few others, but these are notably getting a little dated now (there’s support for WinZip 8-14, for instance, but the current version is 16.5). Still, it’s portable, easy to use, and will copy your keys to the clipboard with a click for easy saving in some other document.

Score: 3/5

Product Key Finder 2.2.3

Total keys supported: 200
Supported products include: Windows, Microsoft Office

Product Key Finder

Its attempts to install a browser toolbar didn’t get Product Key Finder off to a good start. And the program’s product support isn’t exactly up-to-date, either: it managed to find the keys for Office 2010 and Windows 7 on our test PC, but that was all. It’s extremely easy to use, and can save whatever it finds in a CSV file as a record, but that’s not really good enough. You’ll get better results elsewhere.

Score: 2/5

ProduKey 1.53

Total keys supported: 15
Supported products include: Windows, Microsoft Office, SQL Server 2000/2005, Exchange Server 2000/2003

ProduKey

ProduKey is a tiny product key finder which only supports a few Microsoft products: Windows, Microsoft Office (2000-2010), SQL Server (2000/2005) and Exchange Server (2000/2003). Fairly basic, then, but the lack of any annoying adware bundled with the program is a plus point. And it has some useful command-line options, which include the ability to display product keys for all the computers on your network from one location.

Score: 3.5/5

SIW Home 2011 (build 1029i)

Total keys supported: 150
Supported products include: Windows, Office, Visual Studio, CyberLink PowerDVD

SIW Home 2011

SIW Home is a free-for-personal-user system information tool. It’s actually best at telling you everything there is to know about your PC hardware, but it’s not bad at software, either (click Software > Licenses), providing 7 product keys on our test PC and supporting 150+ products overall. This free version can’t export your licences as a report, but you can still copy them to the clipboard so they’re easy enough to save.

Score: 4/5

Windows Product Key Finder Pro 2.3.0.0

Total keys supported: 10
Supported products include: Windows XP/ Vista/ 7/ Server 2003/ 2008, Office XP/ 2003/ 2007/ 2010

Windows Product Key Finder Pro

Care is required when installing Windows Product Key Finder Pro, as it tries to install no less than two browser toolbars. Once you’ve got through setup, though, the program proves a good basic key finder, able to locate product keys for both Windows (including Server 2003 and Server 2008) and Office XP/ 2003/ 2007/ 2010, and save and print them all with a click.

Score: 3/5

Conclusion

If you’re looking for a simple product key finder, which will just report the keys for Windows and Microsoft Office, then just about any of our 10 will do the job. But our pick would probably be NirSoft’s ProduKey. It’s small and basic, but doesn’t come bundled with annoying adware (a rarity in this area), and can collect keys from across your network.

If you’d like to try to record more product keys then we’d recommend either SIW Home 2011 or Belarc Advisor. Both are superb system information tools which can also record quite a few software licence details: they’re powerful, yet easy to use.

But if you’re just after finding the maximum number of product keys alone then an honourable mention has to go to LicenseCrawler. The program’s report looks like a dump of your Registry, and really isn’t for PC beginners. But if you’re an experienced user then you’ll find this finds and reports more product keys than any other free tool, and the report can easily be saved to a text file for quick reference when you’re next reinstalling.




TechRadar: computing components news

In Depth: Intel Ivy Bridge: what you need to know

Intel 3rd Generation Core Microarchitecture

Intel doesn’t make desktop processors and hasn’t done for years. It makes mobile CPUs. And it makes server chips. But that’s it.

This, people of TechRadar, is the gospel truth.

Of course, Intel certainly markets a full range of processors for desktop PCs, but every last one of them started out as something else.

Mainstream favourites like the Core i5 2500K are high end laptop chips tweaked for the desktop. High end beasts, including the new Core i7 3960X, are thinly disguised server CPUs.

That’s important because it makes Intel’s latest family of CPUs, like the Intel Core i7 3770K and Core i5 3570K, much easier to understand.

It explains why the new Ivy Bridge generation in desktop trim is getting little to nothing by way of added cores or clocks. It even just about justifies Intel’s claim that Ivy Bridge constitutes the third generation of its Core processor line, despite the fact that it’s a die shrink and not an all new architecture.

New process

But let’s not get ahead of ourselves.

First, let’s tour the highlights of Intel’s latest CPU family. In Intel’s Tick-Tock parlance, Ivy Bridge is a Tick and that means a new process. In simple terms, it’s the 22nm follow up to Intel’s searingly successful 32nm Sandy Bridge processors, which launched a little over a year ago.

According to Intel, it’s a little more complicated than that.

For starters, Intel reckons the shift from 32nm to 22nm is something a bit special. Typical die shrinks involve making things smaller. When that happens, you usually get processors with more transistors, better power efficiency and higher clocks, but the most of the basic principles remain largely the same.

Not so for the new 22nm process, says Intel.

The big change is the introduction of what it calls 3D Tri-gate transistors. The details are mind bogglingly complex, but the simple version goes something like this: in conventional transistors, the gate oxide and inversion layers which essentially channel and control electrical current are flat and planar with relatively low surface area.

Planar vs. Tri-gate transistors

In 3D Tri-gate transistors, it’s as if the gate oxide and inversion layer has been flipped up on its side and joined by two chums.

That means much great surface area and in turn brings a load of benefits. Firstly, you get more control over current and thus much lower leakage. Less leakage means less power consumption and less heat which is just bonza for laptop CPUs.

Alternatively, it also allows for greater current flow, which makes higher clockspeeds possible. Think desktop chips.

In short, 3D Trigate-gate transistors are better at everything that matters.

In the desktop context, what we’ve got is a new process that ought to allow for more features, be they cores or something else, and higher clocks.

The other half of the equation is the architecture.

Intel 3rd Generation Core Microarchitecture

As above, Ivy Bridge is not all new. On the CPU side, not a lot has changed. The execution engines are carried over with only very small tweaks to the FP/integer divider, which has twice the throughput compared with Sandy Bridge, and a couple of other upgrades that involve data structure sharing and better handling of MOV operations.

If that doesn’t mean much to you, don’t worry, the proof is in the performance, the details are relatively academic.

Elsewhere on the CPU side, Intel has upped Ivy Bridge’s security ante with a hardware random number generator, which is handy for encryption, and a hardware-enabled supervisory mode that helps prevent malicious code from being executed.

But this is the kind of stuff businesses will hook into rather than anything home users will automatically benefit from.

Finally, Intel has revised Ivy Bridge’s overclocking set up.

The basics are the same, so overclocking is effectively something that can only be done via the multiplier and that means only fully unlock K series models are pukka overclocking candidates. But the absolute multiplier limit for K series chips has been increased from 57 to 63, something that’s really only of interest to extreme enthusiasts.

More relevant is the addition of real-time multiplier tweaking from inside Windows. If nothing else, it will help cut out all that tedious rebooting.

No more cores

What Intel hasn’t done, however, is add any more cores.

We’ll come to the detail momentarily, but the top Ivy Bridge model, like the Intel Core i7 3770K, sticks with four cores, just like existing 2nd Gen mainstream Core i7 chips for the LGA1155 socket.

Still, at least the good news is that we’re still talking about LGA1155 chips. BIOS updates permitting, they theoretically drop into any 6 Series motherboard, including those based on the H67, P67 and Z68 chipsets. It works the other way, too.

Ye olde Sandy Bridge processors jive just fine with the new 7 Series boards, including the awesome new Z77 covered recently like the MSI Z77A-GD65, and the excellent Asus Sabertooth Z77 and RoG Maximus V Gene motherboards.

Intel Z77 Express Chipset

If that’s the traditional CPU side covered, it’s the graphics part of the equation where things get really interesting.

Well, relatively speaking.

As before, a full function graphics core is integrated on-die. As before, it comes in two version. And again as before, the entry-level model, now known as HD graphics 2500, has six execution. But the top HD 4000 model now has 16 instead of 12.

That’s not all. Intel says each of those units are more powerful than before and now supports DirectX 11, including tessellation. That’s enough, Intel says, to see the six-unit HD 2500 out perform the old six-unit HD 2000 by 10 to 20 per cent.

Along with quicker 3D rendering, Intel has given the broader graphics package a polish. The QuickSync video transcode gets a once over for better performance, for instance. Native support for up to three displays is another first.

That, pretty much, is your lot.

Which begs the question of whether Ivy Bridge deserves its status as the "3rd Generation" of Intel’s Core processors. Intel says it’s justified by the major graphics overhaul, but we think it’s a pretty odd thing to claim.

It certainly adds to expectations. As you’ll see when you peruse the benchmarks, that may not have been wise.

If that’s the broader architectural low down, what about the processor models themselves?

Here again, there’s a lot of similarity with the existing Sandy Bridge generation. Once again we have Core i5 and i7 chips and as before it’s the i5s and i7s you’ll be interested in. Similarly, the i5s get four threads from four cores and the i7s four eight threads from four cores thanks to Hyperthreading.

At launch, there are nine new models to choose from. Putting the specialist low-power chips to one side, there are five you need to know about.

The fun starts with the Core i5-3450, with four cores, 6MB of cache, HD 2500 graphics, a base frequency of 3.1GHz and a top Turbo of 3.5GHz. Next up is the Core i5-3550, which ups the clocks to 3.3GHz and 3.7GHz but is otherwise identical. The Core i5 3570K takes things to 3.4Ghz and 3.8GHz but also adds HD Graphics 4000 and of course that fully unlocked and overclock-friendly multiplier.

Then there’s a pair of i7 models. The i7 3770 hits 3.4GHz and 3.9GHz with 8MB and Hyperthreading. The Intel Core i7 3770K ups the base clock to 3.5GHz and adds the unlocked multiplier.

Cross reference the new chips with the old Sandy Bridge processors and you’ll see the clockspeeds haven’t budged.

That’s a big disappointment given the hype surrounding Intel’s 22nm process and the fact that once again we’re not getting extra cores.

Any increase in performance will need to be architectural. And that’s a big ask for what is, on the CPU side at least, largely a die shrink.

And what about AMD?

Ivy Bridge may be a bit late (it was due out at the beginning of the year), but it’s still miles better than anything AMD can currently offer.

Is there hope for tougher competition from AMD any time soon?

In a word, no.

AMD FX-8150

For starters, AMD recently said it no longer sees the fight with Intel for PC dominance as relevant. Instead, it sees mobile computing as the future. That, frankly, is a little disingenuous.

Sure, mobile is where the growth is for the computing industry at large, but AMD would dearly love for its Bulldozer FX processors to be taking the fight to Intel.

As it is, Bulldozer turned out to be another dud. AMD needs something dramatically different. And it’s not coming any time soon.

Next up is Piledriver, due later this year if AMD hits its targets, which it usually doesn’t.

Architecturally, Piledriver is no big shakes. But there is one feature that might just make things interesting.

Known as resonant clock mesh, the idea is to use capacitance to capture clock power and recycle it, reducing power consumption by as much as 10 per cent.

According to Cyclos Semiconductor, the oufit responsible for the new tech, it can also be used to push clockspeeds beyond 4GHz.

Of course, the top Bulldozer chip already exceeds 4GHz in Turbo mode. So it’ll have to be well, well in excess of 4GHz. In truth, Piledriver needs to hit 5GHz to really put a bat up Intel’s nighty.

Can you see that happening? We can’t.




TechRadar: computing components news

In Depth: Best of the best: 10 top high-performance computing upgrades on test

Introduction

The high performance PC is dead. If you’re a gamer, that certainly seemed like one of the take home facts from last month’s astonishing performance comparison exposé.

An exotic PC with £3,000 worth of top-end components took on a gaming-focused £300 system and a quartet of keen gamers couldn’t tell the difference. Sobering stuff, but actually very good news for those of us living in the real world and subject to financial realities.

Building a PC on a limited budget is the reality for most. The thing is, our gaming PC comparison was all about subjective performance. That means broader system performance was only tangentially part of the mix. Even more importantly, it means outright performance wasn’t a factor.

That fact matters because while the two rigs often served up a similar experience, the benchmark results showed that the high-end system pumped more than twice the number of frames per second. Objectively, by the benchmark numbers, it was miles faster.

That’s precisely the sentiment we’re taking into this much broader look at high performance computing. Without question, outright performance matters when it comes to the sort of heavy duty number crunching involved in video encoding, image rendering and full on multi-tasking. With gaming, there’s arguably a cut-off point at around 60 frames per second on average. Anything above that is probably performance wasted – you won’t be able to see or feel a difference.

Not so for something like video encoding. The faster an encode job completes, the sooner you can watch the video or start the next encode project. Similarly, if you’ve a limited amount of time available, the more performance your PC has to offer, the better the quality of encode it can execute.

Theoretically, there’s no limit to the additional benefit brought by more performance. However, that doesn’t mean you should simply go out and spend the absolute maximum.

The question of bang for buck remains: which platforms deliver the most for the least? Likewise, what should you make of the promise of hardware acceleration offered by graphics cores? If the graphics chip inside a cheap Intel CPU is faster at the jobs that matter most to you, what’s the point in forking out for a seriously expensive multi-core beast?

Then there’s the minor matter of offloading compute-intensive tasks to the cloud. There’s plenty to consider.

Spend and save

SSD

So, you’re in the market for a performance PC. We’ve established that high performance computing is a very different box of SATA cables from the pure gaming performance, which only needs to be good enough for smooth frame rates. Question is, how and where do you spend you money?

The first conundrum to conquer is the CPU vs GPU question. Plenty of new technologies for the PC have experienced troubled births.

The first solid state drives, for instance, were absolutely awful, but it’s getting on for a decade since GPU makers began bigging up the idea of using graphics chips for general purpose processing, and we’re still waiting for the number of so-called GP-GPU applications to hit critical mass. That’s not just disappointing, it’s also a little peculiar.

On paper, general-purpose processing on the GPU makes an awful lot of sense. For starters, CPU themselves are increasingly turning to parallel processing to improve performance. Which just so happens to be the thing GPUs are really good at. Similarly, many of the most CPU-intensive applications around today are heavy in floating point maths, which is essentially the core task at which modern GPUs are designed to excel.

Now, that’s not to say there’s no GP-GPU-compatible software out there. GPUs are doing some pretty stunning work currently when it comes to industrial and scientific computation. To take just one example, the world’s largest human genome sequencing centre (BGI in Shenzhen, China) slashed the time taken to analyse a genome from four days to just six hours thanks to a switch from CPUs to GPUs.

Likewise, if we were to print a list of every PC application with at least some GP-GPU support, it would look pretty darn impressive. Highlights include a healthy list of video encode, transcode and enhancer applications, along with professional rendering, image editing and password cracking tools, plus a few specialised favourites like Folding@home.

However, courtesy of a combination of mixed performance and a less than crystal clear situation on the support side, both in terms of hardware and software support – questions over whether AMD or Nvidia GPUs work with a given application, for instance – GP-GPU still hasn’t taken off.

Unfortunately, that’s not something that’s changed thanks to Intel’s QuickSync technology, which arrived with the Sandy Bridge generation of Core i3, i5 and i7 CPUs and offers specialised circuitry within the integrated graphics core to accelerate video encoding. It’s a promising development but currently boasts a very modest list of supporting applications. The day when you can rely on a fast GPU for all your high performance computing needs seems as far away as ever.

With that in mind, it becomes a question of platforms and, in turn, the key components you slot inside them. Currently, it’s a choice of three platforms: two from good ol’ Intel and one from AMD.

We weren’t happy when Intel originally switched to two platforms on the desktop with the LGA 1156 and LGA 1366 sockets back in 2009, and our attitude hasn’t changed a great deal with the more recent introduction of LGA 1155 and LGA 2011. It makes life a lot more complicated for serious PC users.

Pick a platform

X79 Closeup

But what are the differences, and how do they affect overall performance? In simple terms, LGA 2011 is really a thinly disguised server socket and is only available with a single chipset, known as X79. It therefore majors in superfast interconnects and memory bandwidth.

First up, you get a quad-channel memory controller. That’s great news in terms of bandwidth, and with memory prices as they are, it’s not even that expensive to ensure there’s a DIMM in each channel. On the other hand, it’s doubtful whether desktop applications really need so much raw memory throughput. Even the old triple-channel arrangement on the LGA 1366 socket was overkill. While four channels is a boon for multi-socket servers, it’s borderline silly on the desktop and only serves to increase cost and complexity.

Much more relevant are the 40 PCI Express 3.0 channels served up by X79. That’s enough to guarantee optimal operation of just about any combination of add-in cards you can imagine, including multi-GPU setups, super-fast PCI Express storage solutions and more.

Next up is full support for the latest 6Gbps version of the SATA interconnect, which is critical for getting the most out of the latest and fastest solid state drives. Unfortunately, you only get six ports as standard. That may sound reasonable. But in a scenario where you’re mixing SSDs and magnetic drives and perhaps chucking an optical drive into the mix, six ports get saturated pretty quickly.

Still, while Intel’s own X79 motherboard is limited to six ports, several third party boards bung in an additional SATA controller and entirely sidestep the issue.

Another obvious X79 shortcoming is the lack of native USB 3.0 support. Again, pretty much all retail X79 boards add USB 3.0 courtesy of a daughter chip, but it’s a feature that really ought to have been part of the native feature set on what is, after all, Intel’s premium, highest performing platform.

The last big piece of the puzzle is, of course, the CPU. And this is where things get really intriguing, both for the better and for the worse. First, it’s absolutely undeniable that the fastest currently available PC processors can only be had in LGA 2011 trim. Those will be the two new six-core Core i7 3900 series based on the latest Sandy Bridge E processor die: the 3930K and the 3960X.

As you’ll know from our coverage, while the 3960X is the undisputed heavy champ of the PC processing world, it still managed to disappoint us. That’s because it’s really an eight-core chip with two cores disabled. At launch time, Intel told us that’s because the balancing act between operating frequency and core count shook out in favour of six cores. Put simply, the more cores you enable, the greater the power consumption and heat dissipation. That in turn puts the kybosh on clock speeds. Sounds reasonable, doesn’t it?

The problem is, Intel has just released a series of Xeon-branded chips based on the very same 32nm Sandy Bridge E die with all eight cores enabled. The fastest is the Xeon 2687W. And it clocks in at 3.1GHz. So that’s 33 per cent more cores running six per cent slower.

Intel will no doubt argue that the mean old eight-core Xeon is rated 20W higher than the Core i7 3960X at 150W. But again, that’s an increase in power consumption of just 15 per cent in return for that extra pair of cores.

If all that makes Intel’s argument seem seriously specious, here’s the good news. In theory, you can drop a 2687W straight into any X79 motherboard and let rip. The only snag is the price, which we expect to be in the region of £1,500. Yes, £1,500 for a processor.

Intel’s Xeon pricing structure is scary territory for a desktop user. The Xeon 2687W isn’t just an eight-core beast with 20MB of cache, it’s also compatible with Intel’s dual socket server platform and that commands an even greater price premium.

There’s one more CPU-related issue to consider when it comes to the LGA 2011 socket and the X79 chipset: you don’t get Intel’s QuickSync hardware encode acceleration. This is only available on chips for the LGA 1155 socket.

As we said earlier, QuickSync hasn’t yet developed into a killer technology, but it’s nevertheless useful for some video encode tasks and it would certainly be galling to pay £750 or more for an LGA 2011 chip, only to find that it lacks a feature that comes with measly £100 Core i3 processors.

Next up is Intel’s LGA 1155 socket. In our view it’s Intel’s bona fide desktop platform, and it differs from LGA 2011 in a number of crucial ways beyond the minor matter of pin incompatibility.

First, instead of just one chipset, there are several. In the high performance computing context, the best choice is clearly the Z68. It does everything the P67 and H67 chipsets can manage and throws in a few extras to boot.

The OC

One of the most important features is full access to overclocking settings. Overclocking might sound like a dubious practice in the context of serious computing, but trust us on this, Intel’s CPUs are very, very conservatively clocked.

Assuming CPU support – which we’ll come to in just a moment – you can almost always add an extra 500MHz and maintain complete stability. It’s often possible to add a full 1GHz and remain stable.

The Z68 also offers Smart Response, Intel’s SSD caching technology. The idea is to combine a small SSD with a larger magnetic hard drive and enjoy most of the performance of the former and all of the capacity of the latter while avoiding the punitive expense of a really large solid state drive. In practice, it delivers decent results even if we’d prefer a full-on SSD wherever possible.

Still, it’s worth considering if you’re building on a tight budget and want to absolutely maximise your bang for buck. Critically, the Z68 does all of that at the same time as allowing full access to the integrated HD Graphics core and QuickSync video acceleration engine found in all Core i3, i5 and i7 chips for the LGA 1155.

You can’t say the same for the P67 and H67 chipsets. The former offers overclocking support but not HD Graphics and QuickSync, while the latter does the graphics part but not the overclocking.

Thread count

Missing cores

Common to all three chipsets is the choice of CPUs. In a high performance computing context, we think maximising the number of threads is all-important here.

For that reason, your choice here is a simple one. You want one of the quad-core, eight-thread Core i7 chips: either the 2600, the 2600K or the 2700K. Unfortunately, Intel doesn’t offer anything more than four cores for the LGA 1155 socket, despite the fact that the dual-channel memory configuration could easily handle more.

Pricing is similar on all three – in and around the £250 mark – so we think it makes sense to go with the 2700K with its 3.5GHz basic clockspeed and overclocking-friendly unlocked multiplier.

That’s right, we’re not recommending that champion of gaming chips, the Core i5 2500K. It’s actually based on the same silicon as the 2700K, but HyperThreading isn’t enabled so it only serves up four threads.

Going any further down the Intel price list doesn’t make much sense either. Instead, it’s better to shift your attention to AMD and its very competitively priced quad and six-core chips. Thanks to the recent introduction of AMD’s FX-branded Bulldozer processors, the number of old school Phenom II processors has dwindled significantly, but you can still pick up the Phenom II X4 960T quad core chip for an attractive £95.

The six-core Phenom II X6 is still available in a few flavours too. As with the Core i7 chips, pricing is similar across the range, so you may as pick up the quickest of the remaining X6 chips, the 3GHz 1075T.

But what about Bulldozer, you ask? Surely with its eight-threaded architecture it’s a no brainer for high performance computing? Certainly, the weak per-thread performance of the Bulldozer architecture and the FX chips it sired matters less here than it does in games. The top FX 8150 chip makes a good case for itself against the more expensive Intel LGA 1155 chips. Much depends on the particular mix of applications you plan on playing around with.

Board games

MSI mobo

For motherboards and sockets, AMD’s strategy of broad compatibility means there’s only one socket you need to worry about: AM3+. Chipset wise, things have also simplified with Nvidia pretty much pulling out of the desktop market. You’re therefore left with a choice between AMD’s own 7, 8 and 9 series chipsets.

In terms if the underlying silicon, there’s little or no difference between the three ranges. Given the choice, we’d go for the latest 9 Series boards, which come in three flavours: 970, 990X and 990FX. There’s not a huge amount between these three, the only major differentiator being ever more PCI Express lanes as you scale up through the range.

One thing you don’t get with any of them is native USB 3.0 support, so we recommend you keep your scanners peeled for boards with a USB 3.0 upgrade chip. If that’s all the different platforms covered, it’s time for a tour of our favourite components for each.

Components on test

1. Asus P9X79 Pro

Price: £205
Chipset: X79

Asus P9X79

For many Intel’s top-rung X79 platform will be right at the ragged edge of what your wallet will tolerate, so every little thing will help to make the numbers add up. That’s where the Asus P9X79 Pro comes in.

It’s not the cheapest choice of motherboard you can buy based on the Intel X79 chipset, but the extra £30 over the likes of the Gigabyte X79-UD3 buys you a number of attractive features.

The most conspicuous feature is the support for solid state drive caching. In an ideal world, you’d simply plug in the biggest SSD you could find and enjoy some serious solid state speed. The problem is, large SSDs come with equally hefty price tags. The ability to pair a smaller SSD with a large conventional hard disk, therefore, makes for a very sensible compromise between storage capacity and cost aiming for maximum bang-per-buck. We’re still years away from solid state drives that are both large and affordable.

The P9X79 Pro also benefits from Asus’s graphical UEFI BIOS, which might just be the best in the business. Apart from the snazzy looking and responsive interface, you get screenshot capability, easy updates via USB and an auto-overclocking option that ramped our Intel Core i7 3960X processor up to 4.3GHz. The latter is a function also available via the physical TPU switch, so you don’t even need to jump into the BIOS.

Read the full Asus P9X79 Pro review

2. Gigabyte X79-UD3

Price: £175
Chipset: X79

Gigabyte X79-UD3

Plotting a performance PC? Then snag a high-end motherboard, right? That’s the conventional wisdom directly challenged by the new Gigabyte X79-UD3.

Of course, any board based on Intel’s X79 chipset hardly rates as a budget item. At £175, the Gigabyte X79-UD3 ain’t exactly cheap, but it is within a fiver of the cheapest X79 motherboards on the market. Everything, therefore, is relative.

Consequently, the Gigabyte X79-UD3 is flagrantly frills-free, but with so many features now finding their way onto the CPU die itself – including the memory controller and PCI Express bus – you could argue that motherboards in general are less critical.

Gigabyte’s task is to deliver quality and performance where it matters, without going overboard on the corner-cutting compared with more expensive X79 models such as the Asus P9X79 Pro and MSI X79A-GD65 8D.

Ultimately, the verdict on the Gigabyte X79-UD3 will come down to what it does and doesn’t do. What it undoubtedly does is deliver performance pretty much indistinguishable from any other X79 board in the known universe. These days, we’re accustomed to pretty consistent performance across motherboards sharing the same chipset. The X79-UD3 is no exception to this.

Read the full Gigabyte X79-UD3 review

3. MSI X79A-GD65 8D

Price: £225
Chipset: X79

MSI X79

Can there be such a thing as too much system memory? In the context of the new MSI X79A-GD65 8D motherboard that’s the first question that leaps to mind.

As an X79 board compatible with the latest Intel Core i7 processors for the LGA2011 socket, it forms part of the highest performing PC platform on Earth, but you still have to wonder whether support for 128GB of DDR3 memory split over eight DIMM slots is really rational. Sure, for server PCs running multiple virtualised operating systems and a whole hill of applications, that much memory is a boon. But for desktop PCs, even those running heavy duty content creations apps, 8GB or 16GB is usually plenty.

In its fisticuffs with the Gigabyte X79-UD3 and Asus’s P9X79 Pro, the MSI X79A-GD65 8D will need a few more tricks up its sleeve. Moreover, the X79A-GD65 8D costs that little bit more than the P9X79 Pro, which in turn is priced at a marginal premium to the X79-UD3.

Is it a case of incremental upgrades all along the line, or has MSI done enough to put this X79-based board in another class altogether? Maybe that old MSI favourite, the OC Genie button, can make the difference?

Read the full MSI X79A-GD65 8D review

4. Intel Xeon 2687W

Price: £1400
Socket: LGA 2,011

Intel Xeon

Say hello to the real Sandy Bridge E, for it is this Xeon processor that truly reveals what Intel’s ultimate 32nm technology is capable of. Up to a point, anyway.

Yes, the Core i7 3960X is an impostor – a cut-down shyster of a chip. Back when Intel launched the six-core 3960X, we were told that the decision to switch off two cores in the shiny new eight-core Sandy Bridge E die was all part of a balancing act. Intel had weighed up the conflict between clockspeed and cores, and decided that the best overall compromise was six cores at 3.3GHz with a little Turbo action on top.

Running eight cores would have meant a significant drop in clock speed and therefore compromising per-core performance. At the time, frankly, we weren’t buying it. Even if opening out all eight cores would mean a big drop in the clocks with all cores heavily loaded, surely the whole point of Intel’s Turbo technology is that the chip could still clock up when only a handful of cores were doing the heavy lifting?

Well, now the fastest eight-core Xeon iteration of precisely the same Sandy Bridge E processor die has arrived and the truth is out. The Xeon 2687W is rated at 3.1GHz, just 200MHz slower than the six-core Core i7 3960X. Thus, the 3960X runs just six per cent faster while the Xeon 2687W has 33 per cent more cores.

Read the full Intel Xeon 2687W review

5. Asus P8Z68-V LX

Price: £75
Chipset: Z68

Asus P8z68

A budget board with a premium chipset – is that the most effective combination for achieving maximum bang-for-buck? If that is so, then Asus P8Z68-V LX is positioned perfectly.

It sells for as little as £75 but it packs Intel’s Z68 chipset. Okay, that means at best you’re stuck with mainstream LGA 1155 processors and a quad-core cap, rather than the six and eight-core (the latter in the form of Xeon CPUs) beasts available for the monstrous LGA 2011 bucket of pins.

But as LGA 1155 chipsets go, the Z68 is easily the pick of the bunch. You get full access to overclocking features, the ability to run a discrete graphics card and still use Intel’s QuickSync video transcode engine and some nice little extras, including Intel’s SmartResponse SSD caching technology.

The prospect of a Z68 board for just £75, then, is a question begging for an answer. Asus may have managed to to squeeze in a few of our own particular treats. But what has been chopped from the P8Z68-V LX?

Read the full Asus P8Z68-V LX review

6. Gigabyte GA-Z68XP-UD3-ISSD

Price: £155
Chipset: Z68

Gigabyte Z68

Double your pleasure. Double your fun. With Gigabyte’s double-priced Z68 board. Deftly dropping the DoubleMint gum ditty into a motherboard review may be beyond our wits, but the real problem is whether Gigabyte has a shot at justifying the fact that the tediously-monikered GA-Z68XPUD3- iSSD costs twice as much as Asus’s P8Z68-V LX.

One thing’s for sure, Gigabyte isn’t going to get the job done based on raw performance. There’s virtually nothing in it, and even when a small differential is detectable, it isn’t always in Gigabyte’s favour. We couldn’t discern a significant difference during overclocking either. Both boards extracted the same 4.5GHz from our Core i7 2700K test chip.

Gigabyte is, therefore, left with one remaining hope: ye olde feature set. Out of the box, things don’t look great. We’re pretty partial to hardware power, reset and Clear-CMOS switches – it’s the least you’d expect from a £150-plus board. We can’t help noticing the lack of DVI or eSATA ports on the back panel, too.

Dig a little deeper though, and you begin to identify where the extra cash is going. For starters, Gigabyte gives you proper multi-GPU support with one 16-lane socket and one eight-lane. Both Nvidia’s SLI and AMD’s CrossFireX are supported.

Read the full Gigabyte GA-Z68XP-UD3-ISSD review

7. Intel Core i7 2700K

Price: £255
Socket: LGA 1155

Intel Core i7

This is awfully familiar – Intel’s Core i7 2700K is saddled with Intel’s mainstream LGA 1155 socket. In theory, the exciting stuff all happens on LGA 2011.

What’s more, in a gaming context, we’ve never jived with the 2700K and its dual threads per core. That’s because games don’t scale enormously well across multiple threads, and the Core i5 2500K has all the per-core, single-threaded oomph of its much more expensive Core i7 cousins, be they in LGA 1155 or LGA 2011 format.

It’s all the gaming chip you’ll ever need. But is the 2700K back in the hunt if you shift the context to high performance computing? It’s certainly a much more cost effective option than the LGA 2011 alternatives.

You can pick up a very respectable LGA 1155 motherboard for just £75, whereas a basic LGA 2011 item is more like £175. Then there’s the chip cost itself. Even at £255, you’re looking at half the cost of the cheapest six-core i7 model, much less the preposterously pricey Xeon eight-core.

Read the full Intel Core i7 2700K review

8. Sapphire Pure Black 990FX

Price: £135
Chipset: 990FX

Sapphire Pure Black

Your eyes do not deceive you. Do not adjust your set. The Sapphire PURE Black 990FX motherboard really does have six PCI Express x16 slots.

That doesn’t mean, of course, that you can run six graphics cards in parallel. Not in the conventional multi-GPU sense, since the maximum number of cards supported by AMD’s CrossFireX tech is four, and SLI isn’t on the menu at all.

Still, if running a veritable army of displays is your bag, the sextet of slots offers plenty of potential. More to the point, it means you have endless options in terms of how you arrange your add-in boards, though the fact that the final two are only x4 electric does limit your options somewhat.

The lack of PCI connectivity of any kind also rules out any dusty old legacy cards you might be thinking about bunging in.

Expansion aside, the PURE Black 990FX is arguably up against it from the off. That’s because it’s an AMD AM3+ board, and neither the new AMD FX nor ye olde AMD Phenom II chips really threaten the top of the performance table. If we’re honest, they’re not exactly terrorising the mid-range either.

Read the full Sapphire Pure Black 990FX review

9. AMD Phenom II X6 1090T Black Edition

Price: £110
Socket: AM3

AMD Phenom

AMD’s shiny new Bulldozer FX processors have been released into the wild for some time now, so you might be wondering what this crusty old Phenom II processor is doing sullying this showcase of white-hot, high performance computing platforms.

Well, it all depends on pricing and product availability. We’re not sure if AMD is still cranking out the Thuban processor dies that form the basis of the Phenom II X6 1090T Black Edition, though we believe that to be the case, if only for manufacturing server processors.

Read the full AMD Phenom II X6 1090T Black Edition review

10. AMD FX 8150

Price: £196
Socket: AM3+

AMD FX 8150

Sadly, in what appears to be an increasing, and worrying, tradition for the ‘other’ CPU manufacturer, the launch of the AMD FX processor was something of a debacle. AMD’s much feted new eight-threaded modular architecture delivered in neither in real-world performance nor efficiency.

In fact, it was so underwhelming, it left us with the nagging suspicion that an eight-core Phenom II would actually be a better bet. That’s quite a disturbing notion, given the general consensus that the Phenom II’s micro-architecture was no longer competitive.

Things went from bad to bizarre when it emerged that the FX’s transistor count was not actually two billion, as originally claimed, but closer to 1.2 billion.

Read the full AMD FX 8150 review

Benchmarks

Bench analysis: Making sense of an awful lot of numbers

This is all rather different to our traditional, gaming-centric set of benchmarks, and shows the productivity prowess of the real top-end platforms on the market. The eight-core Intel Xeon dropped into a desktop X79 board, like the excellent Gigabyte X79-UD3, makes for the most powerful desktop solution around.

For any video encoding, database-crunching or image manipulation tasks you can’t get quicker. That said the cheaper 3960X does a good job of getting close and the AMD FX 8150 actually takes the lead in our Photoshop tests. You can put together a decently priced AMD workstation, but the top-end Xeon-powered beast will cost you.

bench 1

bench 2

bench 3

bench 4

bench 5

Verdict

And the winner is… Gigabyte X79-UD3

Gigabyte X79

Last month our gaming performance exposé blew apart expectations, slaughtered sacred cows and generally caused a kerfuffle. We proved there was very little benefit to be gained from unloading a whole hill of cash on the finest PC components on the market.

When it comes to high performance computing and particularly digital content creation, however, things are very different. The argument goes something like this: If you’re playing a game, the performance metrics are framed in terms of fast enough. When you’re cranking out 60 frames per second, an extra 30 gets you absolutely nowhere.

Not so with, say, video encoding where every frame per second gets the job done quicker. That’s useful if you’re honing your own video, iteration after iteration, and find yourself twiddling thumbs during the encode process.

The same goes for tasks, such as professional rendering or heavy duty office apps and big database processing in Excel. The faster your PC, the more work you can get done.

In theory, the money spent on a more powerful machine is an investment in long-term productivity. Put it this way, when we told one of our back-office number-crunching brainiacs just how fast the Xeon eight-core processor tore through the huge Excel spreadsheet he gave us for testing, he nearly cried. The Xeon was 11 times faster than his Core 2 Duo box. Remarkable.

The right combo

That said, not all applications scale so nicely. Photoshop is a perfect example of a mixed workload application; not all of its filters and transformations are well threaded.

Still, the first conclusion we can draw is that the high end clobber does have something to offer. Okay, some aspects of the Intel X79 platform make no sense on the desktop. We compared, for instance, a Core i7 3960X running in dual-channel and quad-channel memory modes. The latter offered no real-world benefit – it only showed a difference in memory bandwidth tests.

But overall, there’s no doubt that the X79 combined with an Intel six-core i7 or eight-core Xeon processor is by far the fastest system you can buy. Whether the Xeon is worth double the i7, however, is another matter.

If you’re willing to overclock the Core i7, you can close most of the performance gap on the locked-down Xeon. If you’re unwilling to compromise stability and reliability, the Xeon processor is unbeatable.

The mid-ranger

Further down the scale, the Intel Core i7 2700K combined with the aggressively priced Asus P8Z68-V LX makes an impressive mid-range solution at around £325 combined. Throw in a little overclocking and you have a very quick content creation system.

As for the AMD alternative, the FX is very handy with efficiently threaded software. If, for instance, you want to build an affordable video encoding box, you could do a lot worse. However, if you are after a multi-purpose PC, we’d argue you either spend a little less and go with the cheapest AMD Phenom II X6 or step up to the Core i7 2700K.




TechRadar: computing components news

Calendar

May 2012
M T W T F S S
« Apr    
 123456
78910111213
14151617181920
21222324252627
28293031