Nvidia is contemplating its very own x86-compatible processor core. in theory, this core could combine with Nvidia graphics technology to create system-on-chip (SoC) silicon that competes in the rapidly expanding low-power handheld-device market. According to a report from the The Wall Street Journal, Mike Hara, Nvidia's …
BUY AMD =D
Why the fuck should they need a licence anyway, just to make an x86- compatible processor?
It's going to get to the point soon where you'll need to licence pet names. You want to call your dog "Rover", well, there's a fee for that, sir, depending what breed it is .....
The idea that "ideas can be owned" is one that people need disabusing of, by whatever means necessary.
As AMD own ATI, and ATI is realistically the only other GPU company*, Wouldn't that be a monopoly?
* What's the type of company called? It's not manufacturer is it, because that will be the companies that actually make the GPU, such as LeadTek, MSi, etc? Honest question, I forgot.
GPU taking over massively parallel tasks from the CPU
Hmm like graphics rendering perhaps?
I'm not sure what else would benefit in a netbook. Graphics cards run hot and eat lots of power. That's why we don't put them in netbooks.
I can see how they might be used in servers, but I'm at a bit of a loss to see the advantage in low power devices.
I suppose they could strip them down and tune them so that they run vista or kde with all the 3d stuff enabled, but not much more. Though it would seem to be more sensible to switch 3d off entirely when running on batteries.
Paris, batteries, its obvious really.
Spot the pattern?
Intel/TSMC announce that they will allow select customers to design and build x86 SoCs and fab them at TSMC. One day later, NVIDIA (TSMC's largest customer) say they will make x86 SoCs in 2-3 years.
El Reg conclusion: NVIDIA will make it's own CPU.
Try joining the dots guys...
Yes yes YES!
I'm liking this idea, more competition for Intel is always a good thing - lets hope the licensing doesn't throtte them too much.
I think Nvidia have the expertise to pull something like this off really well, what with the history of their nForce chipsets, its the next logical step.
Does beg the question though does this exclude 64bit architecture - i only saw x86 mentioned, not x64.
@AJ Stiles - Well of course they'll need a license, in the same way if you pay billions over the years to come up with a very complicated big money design of something, you wouldn't want any old tom dick and harry using it for their own gains. Its a far throw from not being able to call your dog Rover now isn't it!?
Jeez . . . some people just dont understand this whole free-enterprise thing!
Why the licensing deal?
Because many of the technologies existent in today's x86 processors were developed internally by Intel---AND PATENTED. AMD does possess licensing to some of Intel's juicier secrets while having home-brewed solutions of its own. And now possessing ATI, they (like Intel with its progress towards Larabee) possess both CPU and GPU tech needed to produce a System-on-a-Chip. nVidia lacks the CPU end and needs it--quick--before AMD's Fusion and whatever Intel dubs its SoC chips corner the market. Everyone realizes this will be the next evolution of the x86 line--SoCs whose GPUs can do basic graphics on the low end and can provide parallel computational boosting on the high end.
Surely it's obvious
Nvidia have to swallow their pride and cut a deal with Via. The glory days when Nvidia defined the cutting edge of consumer silicon tech are long gone. Now, if you are not integrated you will surely die. Which would be a pity since while monopolies are bad but duopolies ain't much better.
I can't see how they'd bother with x86 - unless in conjunction with a x64 processor [since x64 builds on x86 for backwards compatibility.
@Samson Chan: LeadTek, MSi, etc. don't make the GPU, just their own board. If the card is using a [for example] Radeon GPU, they supply the board and drivers.
x64 is a M$ invention.
As for GPGPU computing, isn't that just replacing one CPU with another? But shhh... don't tell nVidia.
x64 is a M$ invention.
The x86-64 specification was designed by Advanced Micro Devices (AMD), who have since renamed it AMD64. AMD licensed its x86-64 design to Intel, where it is marketed under the name Intel 64 (formerly EM64T)..
Use OpenSPARC and pay NO ONE...
I don't think the world needs a 3rd x86 player, given Intel is about to switch to Nehalem family.
I think Nvidia mostly need an x86 system as a boot, compile and control environment for code they want running on their families of GPUs.
Why not use an OpenSPARC implementation for that ? In Sun's implementations (the Niagara family) they are relatively power efficient and low in the GHz stakes. The control OS could be Solaris (if Sun ever got their a** into gear and finished a binary Open Solaris distro that wouldn't cost Nvidia anything either). There *are* ports of Linux to SPARC but ironically the ecosystem of things people actually use like Apache, Java, compilers etc is far more mature and complete on Solaris-on-SPARC than on Linux-on-SPARC (with the reverse being true on x86).
So if the PLAYstation is where work stops, then Nvidia could reinvent the WORKstation as a true computing device, rather than today's bastard child of a general purpose traffic light controller.
The terms these days are synonymous, since any contemporary consumer-grade x86 processor is expected to be 64-bit-capable. Perhaps the one exception is the low-power chips such as the Atom where efficiency takes precedence over performance. Anyway, like I said before, compatibility relies on being able to perform certain techniques that Intel has patented. They sure as blank can't go to AMD since it's a direct competitor (they now possess ATI, nVidia's chief GPU rival). And Intel won't grant the license itself because they're horning into nVidia's market itself with Larabee, making them direct competitors also.
Each computing architecture has its own advantages. Current CPU designs are meant to handle almost anything computational and thus are best suited for general and unpredictable tasks, such as tasks involving human interaction. Whereas the parallel nature of GPUs are best employed on highly-structured, predictable jobs. That's why they're math whizzes (math is highly-structured and thus predictable).
@AJ Stiles -
"Why the fuck should they need a licence anyway, just to make an x86- compatible processor?"
Yes, because they'd use Intel IP, the x86 insctructions set. It's not the idea, but the implementation which is licenses, here, so there's no abuse.
But if they want, they could also do as others have done, come up with an entirely new instruction set, call it NV86 ! But then, they would have either to wait a decade before seeing customers adoption, or emulate x86 atop, which is back to the license.
- Microsoft: We're hiking UK cloud prices 22%. Stop whining – it's the Brexit
- Despite best efforts, fewer and fewer women are working in tech
- And so we enter day seven of King's College London major IT outage
- Thanks, IoT vendors: your slack attitude will get regulators moving
- AMD is a rounding error on Intel's spreadsheet and that sucks for us all