Tag: intel

Posted on

The Future of CPU Sales

Up until now, differentiating between CPU products has been all about getting more cores and higher speeds. If you have the money, for instance, you want to buy a CPU with as many cores as possible running at the highest speed possible in order to get the fastest performance possible. An article by J. Scott Gardener opened my eyes on how much more complicated a smart CPU buying decision will be in the future.
In the past, CPUs were clocked as high as they could go (in terms of GHz ) and priced accordingly. These days, MANY (I will exaggerate a bit and say MOST) CPUs are actually capable of reaching incredible speeds far exceeding their marketed performance grades. For instance, it is possible to take a 1.8GHz Dual-Core Intel processor and overclock it to just about 4.0 GHz. In a simple sense, smart overclocking consumer x just doubled his performance for free. So why doesn’t Intel, AMD, or VIA just sell consumer x the processor already set to 4.0GHz? Because smart overclocking consumer x had a serious heatsink or liquid nitrogen cooling his CPU. Most consumers don’t opt for a mega-large CPU cooling tower or live in Siberia (ambient temperature has a measurable impact on CPUs).

At some point in the future, stating a CPU speed at retail becomes meaningless, because the majority of the produced CPUs can all perform far beyond the cooling capacity of normal cooling solutions. What becomes the differentiating factor at that point? More cores aren’t always more useful if the CPU has to throttle itself to prevent overheating.

Personally, the only answer I can think of is some sort of thermal efficiency measurement. A higher value would mean the CPU could produce more performance for less power and less thermal output. The lower value CPU might produce similar performance, but require more power and a more vigorous cooling solution.

And, as always, this means that consumers get more for their money. Yay!

Posted on

Integrated Graphics, AMD’s PUMA

IGP (Integrated Graphics Platforms) have been the bane of gamers, especially mobile gamers, for many years. Created for use by casual computer users who want little more than to write Word documents, play flash games, and watch YouTube, they often fall well below the mark for acceptable DVD/Blueray playback and PC Gaming. For mobile users, the choice between a dedicated GPU (Graphical Processing Unit) and an Integrated GPU merits consideration. Integrated GPUs use much less power, create less heat, and result in an all around more mobile system. Dedicated GPUs use more power, create much more heat, but allow gamers on the go to play the latest and greatest with a few tweaked settings. Intel’s IGP solutions, the GMA series of integrated graphics (GMA 915, GMA 950, X3100, upcoming X4500), have been the most common and also the most frustrating. Intel doesn’t do graphics, so their IGPs are very hit and miss, especially in running games properly. ATI/AMD’s solutions, such as the X1250, as well as Nvidia’s solutions, such as the 7150, provide more acceptable gaming performance, but still not enough to play high intensity games very effectively at medium/high settings.
AMD/ATI finally broke the mold, their new 780G motherboard chipset contains the HD3200 IGP, which offers a significant performance improvement over all other IGPs. While a dedicated GPU will still perform better, the HD3200 is an important step forward. In a mobile system, the 780G is part of AMD’s PUMA platform, which also offers an external port allowing an external GPU to be connected to the laptop, something not practical or effective until this point. The following video compares the HD3200 with an older X3100 (which has been replaced by the slightly improved, though still lacking, X4500).

Posted on

Intel at it Again!

A few days back I wrote an abridged history of the CPU, spotlighting Intel and AMD in their never ending battle for supremacy. Today, one of my favorite technical/review sites (AnandTech) snagged an early revision of the Nehalem architecture (Intel’s next big chip) and ran a few benchmarks. AMD must feel crushed, because Intel pulled out ALL the stops.
Nehalem chips wont be available to consumers until then end of 2008 and beginning of 2009. They offer as many as 8 cores, each ‘HyperThreaded” (a technology used in Intel’s older Pentium 4 chips) to create twice as many logical (processing capable, virtual) cores. The biggest, baddest consumer Core 2 available today comes with a maximum of 4 cores. Testing one of the 4 Core 2.66GHz Nehalem CPUs against one of Intel’s 4 Core 2.66GHz Penryns (updated Core 2 ‘Conroe’), the Nehalem still put the hurt on Penryn on a clock for clock basis. In other words, even at the same “GHz” the Nehalem is much faster.

nehalemNehalem at Computex 2008 in Taipei, China.

To quote Anand himself, “First keep in mind that these performance numbers are early, and they were run on a partly crippled, very early platform. With that preface, the fact that Nehalem is still able to post these 20 – 50% performance gains says only one thing about Intel’s tick-tock cadence: they did it.”