Where does Tegra fit in?
Nathan Taylor wonders what Nvidia is playing at with its new Tegra CPUs. Should Nvidia stick to its graphics cards?
Computex in Taipei is done and dusted now and unsurprisingly the show was been pretty much all about small and light. Intel’s Atom was everywhere, Asus showed off several new Eee PC models (including a desktop model), MSI and Acer announced their Eee PC clones and all the talk was about this supposed (and I daresay mythical) new category of mobile internet devices.
The chip manufacturers are also boosting their low-power solutions. Most notably, Nvidia announced Tegra, a line of ARM11-based CPUs with integrated 3D cores. ARM processors, with their very low power consumption and simple RISC design, are very popular for use in mobile phones and embedded devices. Now Nvidia has taken that and added a low-power GPU to the mix.
At first glance, Tegra seems like a solution in need of a problem. It doesn’t fit into any existing market segments, and Nvidia may be hoping it can create a new one just by releasing silicon. Is it thinking 3D phones (and would anybody want one of these)? PSP competitors? Eee PC-alikes that can play Quake?
Strangely, reports from the show are indicating that Nvidia see this as a product aimed squarely at Intel’s Atom – and if that’s the case then Nvidia clearly has an uphill battle on its hands. Not because Atom is inherently superior to Tegra (I expect that Atom will be faster, but Tegra will use much less power and be much cheaper), but because the Intel x86 has a much more advanced software ecosystem for PC-like devices.
It also has the mindshare, the third-party support and the momentum. Nvidia, on the other hand, would have to carve out an “embedded 3D” software ecosystem virtually from scratch, which is something it may not be capable of.
Other Blog Entries written by Nathan Taylor:
Thoughts on this article? Add a comment below.
Be the first to comment on this article.