It’s rare that we see a review system that doesn’t pack an overclocked punch, but the launch of AMD’s Bulldozer-powered FX processors saw the firm use gallons of liquid nitrogen to break the world record for the highest frequency computer processor – previously held by a Celeron – and run its new FX-8150 at a ridiculous 8.429GHz.

That potent fluid is the preserve of the world’s most skilled overclockers and, before its record-breaking attempt, AMD held a test run in front of a small London audience – one of the first times, in fact, that the firm’s overclocking guru Sami Makinen had pushed Bulldozer to its limits.

While Makinen didn’t hit the same heights he managed during the Guinness-monitored attempt, he still took the new chip to a staggering 8GHz clock speed. He tried for 8.2GHz, but the sample he was using begun to crash.

Take a look at our pictures to see exactly what’s involved with extreme overclocking, from putty around the CPU to canisters of potent LN2 – and check out that temperature, too: a chilly -180°C.

Yesterday I returned from the Intel Developer Forum to be greeted by some interesting news that definitely wasn’t mentioned at IDF. In case you missed it, the CPU Goliath has started selling upgrades to its low-end Pentium CPUs in the form of scratch-cards – in the US, at least.

It’s a simple idea. The processor ships at a low price with some of its capabilities disabled, and these cards – which sell for $50 – reveal a code to download a software tool that unlocks those extra capabilities.

Not everyone approves. Some commenters (on more hysterical forums than ours) see this as an outrageous way to treat customers. “They’re selling deliberately crippled parts!” they cry. “They want to charge you twice for the same thing!” And, to an extent, they have a point.

A simpler, more flexible family

But for decades it’s been absolutely standard practice – and not just at Intel – to selectively disable CPU features, and restrict clock speeds, so as to sell the same basic chip at both the high and low ends of the market. All that’s new here is an officially-supported way to restore some of those features after purchase. If you think about it, it’s actually more empowering for the customer than the old way.

In fact, I’d love to see this approach applied across all processor families. Choosing a CPU need no longer be a leap of faith: you could start with a cheap model and add more power as you needed it.

It could simplify things too: instead of bamboozling customers with numerous poorly-distinguished CPU families, Intel could offer just three designs – say, an Atom, an LGA 1156 part with up to four unlockable cores and an LGA 1366 part with all the top-end features waiting to be enabled.

Technical challenges

Of course, there are potential technical challenges to such an approach. In the olden days, some slower and less capable chips were sold not just as part of a market strategy, but because they weren’t fully functional (the Intel 80486SX comes to mind). Obviously this would be no good for a user-upgradeable CPU: every chip sold would have to be capable of running at full speed with all its features enabled.

Every chip sold would have to be capable of running at full speed with all its features enabled.

But in 2010 this shouldn’t be a show-stopper. At the Westmere launch last year, Intel engineers confirmed that modern designs enjoy a huge amount of headroom — and indeed we’ve seen more than one Core i3 system running stably at 4GHz and above.

As for hardware defects, it’s hard to gauge how much of an issue this might be, as Intel doesn’t publish failure rates; but let’s just say it’s a long time since the company had any visible difficulty producing fully working chips.

The size of a die

Another consideration is die size. If every chip in a family had to support the maximum available feature-set, they’d all have to be built on comparatively large slices of silicon. The most lightweight LGA 1156 part, for example – the Core i3-530 – is etched on an 81mm² die. To match the features of the flagship Core i7-880, it would have to grow to 296mm² — more than a threefold increase in area. And, as chip manufacturers keep reminding us, a bigger die means a higher price.

But the silicon itself is nowhere near as expensive as you might imagine. It’s impossible to put a firm price on a square millimetre of wafer, especially since Intel does its own chemical processing; but in 2006 the website EE Times reported that 300mm silicon wafers – now the standard, but at that time still an upcoming format – were selling for $200.

If we assume (conservatively) that the price has remained the same, that means 81mm² of CPU-grade silicon would cost very roughly 57¢, while a 296mm² die would come in somewhere around the two-dollar mark.

Yes, it’s a price rise, but hardly one large enough to wreck the business. And the machining costs (which do represent a substantial investment) would be lower, because there’d be no need to set up a separate dual-core design. Intel could see a market benefit too, from offering a more flexible line-up, and enjoy a new revenue stream from customers unlocking processor features.

Catching on

For all these reasons, I dare to hope that the Pentium scratch-card represents a toe in the water, and that the approach will soon be extended to more aspirational processors.

If I’m honest, though, the possibility I’m most interested in is, from Intel’s perspective, the one that could kill the idea stone dead. Right now it’s physically impossible to turn a lowly Core i3 into a powerful Core i7; but in the model I’m imagining it would be a simple matter of entering a code. And, as we’ve seen with CSS, AACS and most recently HDCP, where there’s a code, there’s a concerted effort to crack it.

After all, you can already download dodgy code generators to unlock features in software. How many of us would scrupulously resist downloading a code for a free processor upgrade? And what on earth would that do to the CPU business?

This prompted one commenter (giving his name as Wilbert3) to raise an insightful point. Hyper-Threading is great for everyday multi-tasking: for example, it lets a dual-core Core i5 CPU service four concurrent processes. But it works by presenting each core’s spare execution capacity to the OS as a virtual second core. Under heavy load, where there is no spare capacity, it would seem unable to offer any benefit. In such cases we shouldn’t expect to see a Core i5 achieve performance anywhere near what a true quad-core architecture would provide.

That analysis sounds persuasive, but is it borne out by the evidence?

To find out, I’ve done some tests on our standard Core i7-920 test rig, using our highly parallel 3D rendering benchmark and selectively disabling physical and virtual cores. Here are the results, in seconds, showing how long it took to render the same scene in different CPU configurations:

For the record, this was tested on a 32-bit Vista Home Premium installation, running at 2.66GHz with 4GB of DDR3-1066 RAM and a 1TB Seagate Barracuda 7200.12 hard disk.

Clearly, Hyper-Threading does help, cutting the dual-core render time for our test scene from 185 seconds to 165 seconds. It seems even highly parallel tasks waste some execution capacity that Hyper-Threading can exploit. But when we switched off Hyper-Threading and stepped up to four physical cores, render time was slashed to just 118 seconds — a performance boost more than three times greater than that offered by Hyper-Threading.

(Update: At the request of some readers, I subsequently repeated the four-core test with Hyper-Threading enabled. This brought render time down to 107 seconds, representing a speed improvement of 10% — almost exactly the same proportional change, to within 1%, as observed in the two-core tests.)

The conclusion is clear: Hyper-Threading can eke some extra performance out of even the most demanding tasks, and to that extent it’s certainly a plus point for Intel’s architecture. It’s also clearly worth having if you need to service many parallel lightweight demands — in a server, for example. But when it comes to proper grunt-work, it’s no substitute for real silicon.

My final shopping list – after taking suggestions from the helpful comments of Grimer, E and Ian Devlin, among others – looks like this:

• Intel Pentium Dual Core E5200 2.5GHz
• Asus P5K motherboard
• 2GB 800MHz DDR2 RAM
• ATI Radeon HD 4350 512MB graphics card
• 320GB hard disk
• DVD+/-RW writer
• An Akasa cable management kit to keep everything tidy and tied down.
• And the astonishing piece of engineering genius that is the Eye T Warrior gaming case.

I spent yesterday morning putting the rig together – without doing any tidying or cable-tying, just in case things went wrong – to make sure that everything works, and I’m pleased to report that it does. I’ve also split the hard disk in two and installed Windows 7 on one partition and Ubuntu on the other, so I’ll now be able to start filling the Open Source OS with the best free applications and updating Windows 7 with the frenzied fervour of progress.

After that, the testing begins in earnest. My processor is an extremely capable overclocker – even with the standard Intel heatsink in tow – and so I anticipate that it won’t be too difficult to get it running stably at 3GHz. I’ll then be trying to get it even higher; I’ve seen a Pentium Dual Core E2200 reach 3.3GHz, so perhaps 3.5GHz isn’t out of the question with my chip. I hope I’m not being too optimistic.

Even a few minutes spent with my machine reveals where my last £10 needs to be spent, though. It’s not a particularly hot machine but it is one of the loudest I’ve ever heard. A quick investigation inside of the chassis reveals that it’s not the CPU fan or the passively-cooled GPU making the noise. Instead, it’s the three case fans whirring away. The fans are arranged in a slightly strange way, too: there are two at the front of the machine, towards the bottom of the chassis, and another on the side of the case directly opposite the CPU.

I’m planning to buy three Ebuyer Extra Value case fans and put one at the front of the case and another at the rear – there are mounts for fans but none were included at the back – with another on the side, seeing as there’s a space for one there. It seems that this system will result in slightly better airflow through my chassis and, if the customer reviews are accurate, then they’ll be quieter than what I’m using at the moment.

As usual, though, I’m open to suggestions. If you know of any cheap – preferably colourful – and extremely quiet case fans that I’m overlooking, please let me know in a comment below.

I’m also still looking for a name. While Kuryakin’s suggestion of ‘The Mandelson’ is excellent, I’d like some more contenders – so throw your various hats into the ring below, too.

I loaded up Steam for the first time in a while last night and was promptly asked to participate in Valve’s ongoing hardware survey. I’ve done this before, and the results are always fascinating, so I jumped right in. A few clicks later, and a quick scan of my cobbled-together PC, and I got to see the breakdown of nearly 1.8million gamers’ systems – with some surprises.

Just 41% of polled users have made the much-needed step to a dual or quad-core processor – the norm in pretty much all new PC systems sold today – and 38% have shelled out on 2GB or more of RAM. Assuming a correllation between the two, that leaves a huge proportion of PC players who are still trundling along on 1GB of RAM or less and a single-core CPU.

Monitors are also an interesting point. Despite the fact that we almost never review them any more, and few manufacturers are even pushing new models today, a startling 75% of polled users are still playing on 4:3 monitors. Of those that have moved to widescreen, nearly 35% have opted for screens sized 24in or larger, while nearly 70% are at 20in or larger – if you’re going to upgrade, you may as well aim big.

The graphics card section is out of date, with no entries for ATI’s HD cards or Nvidia’s 9-series or faster, so can be ignored, but there are still more interesting stats to be gleaned from the survey:

• Intel leads AMD roughly 60-40
• An awful lot of people don’t upgrade their graphics drivers
• 1,396 polled gamers have less than 10GB of total hard disk space in their PC
• Nearly 3% of polled users still don’t have a DVD drive
• 8,105 Steam users speak a language called ‘Simplified Chinese’

And then there’s the old Vista issue. How many gamers do you think have upgraded to Microsoft’s flagship – with DirectX 10 it’s surely a gamer’s paradise, right? Wrong. Of the 1.8million Steam users polled, more than 80% are still running trusty old Windows XP. Ouch.

Admittedly, this Steam survey has been running for nearly a year now, and some of the categories and entries could certainly do with updating and starting afresh, but as a snapshot of a community made up almost entirely of gaming PC users it’s fascinating.

Journalists like us can sometimes get carried away in the constant hunt for bigger, faster, better, forgetting the fact that the vast majority of users don’t want to spend money on their PCs every five minutes, and that for many, running Crysis at Low settings is good enough to get enjoyment out of it (strange people).

But mostly a survey like this just highlights the problem that will always exist for PC and component manufacturers: that consumer inertia is just as powerful as technology in determining their bottom lines.

I was curious to see how well this veteran CPU had aged (and it’s not like I had anything else to do this week), so I dropped it into our testing rig and kicked off the benchmarking process. A few hours later, the results were in: the Pentium Extreme Edition 955 had scored 1.19. That’s far from disgraceful, but today, you can get a CPU that achieves that sort of score for as little as £90. To put that into context, I’ve tweaked our CPU graph (click for full-sized version) to show how the 955 would fit into the mainstream market if it were launched today.

If you take any sort of interest in computing – and let’s face it, you’re reading the PC Pro blog – you’ll have seen similar scenarios play out many times before. I remember my father paying £100 (around £350 in today’s money) for our first family computer, a Sinclair ZX-80. A year later, the ZX81 appeared, costing half as much and bringing numerous technological advances, including floating point arithmetic and a screen that didn’t go blank every time you pressed newline.

A more recent example: three months ago, I reviewed the Samsung 1TB Spinpoint F hard disk. I liked the drive, but felt that at £185 it was too expensive. Today that drive is selling for £96. Now it looks like a bargain – but of course in another few months we’ll be looking back at the days when we used to pay £100 for a terabyte drive and laughing at how naïve we were.*

So when I realised that some sucker had probably actually shelled out £600+ for the deeply average processor sitting before me, my first instinct was to feel bad for him.**

But although the constant downward procession of prices can seem profoundly depressing when it catches you out, in reality it’s a wonderful thing. Because it means the horizons of what you can do at a given price point are constantly expanding. Of course, it’s a gradual process: maybe next month a £699 PC will raise the performance ante by a few percent, or a Blu-ray burner will come along that’s £5 cheaper than the last one. But over time these small cumulative increments open up whole new avenues of creativity and productivity. Case in point: ten years ago, real-time non-linear video editing was a high-end specialist application. Today, my girlfriend does it on her laptop.

Of course, all this isn’t much help when you’re actually buying, say, a CPU or a graphics card. Unless you go for a real pocket-money model to start with, you just have to accept that, a few months down the line, you’ll be able to get the same part, or a comparable one, for less.

But the thing to remember is that, whatever may happen in the future, at the moment you put down your cash you’ll be getting more for that money than at any previous point in history. Where once £650 would only buy you a Pentium Extreme Edition, it’ll now get you a Core 2 Extreme. And what my father once paid for a ZX-80, adjusted for inflation, will buy you not only a fully-featured 15.4in laptop, but also a copy of Vista to run on it, giving you a range of useful features that even the ZX81 never equalled.

Put it like that and a few hundred quid here or there suddenly doesn’t seem like a screw-over. In fact, it looks like a very small price to pay.