Our forum users were quick to tease Intel...
Despite the fact working samples had already been shown, that Intel executives had continually promised it would change everything, and that it was planned for release in 2010, the Intel board of directors has decided to shelve Larrabee, its consumer graphics chip. Instead Larrabee will now be made available as a software development platform:
Larrabee New Instructions (LRBni).
CNet obtained a quote by Intel spokesman, Nick Knupffer, who late on Friday said that;
"
Larrabee silicon and software development are behind where we hoped to be at this point in the project. As a result, our first Larrabee product will not be launched as a standalone discrete graphics product."
It maybe more than a decade since the last Intel discrete graphics card was available -
the i740 - but we'll have to wait a little longer for the reintroduction of Intel graphics, despite the billions of dollars already sunk into the project by Intel.
Lacklustre appreciation of the
live demo at San Francisco IDF 2009, combined with an
epic die size and multiple delays have all taken its toll on the project.
Over the weekend, Tim Sweeney, the author of the extremely popular Unreal Engine, who has long been an advocate of the Intel Larrabee project, has
piped up to comment as well:
"
I see the instruction set and mixed scalar/vector programming model of Larrabee as the ultimate computing model, delivering GPU-class numeric computing performance and CPU-class programmability with an easy-to-use programming model that will ultimately crush fixed-function graphics pipelines. The model will be revolutionary whether it's sold as a [PCI] Express add-in card, an integrated graphics solution, or part of the CPU die.
[...]Today's GPU programming models are too limited to support large-scale software, such as a complete physics engine, or a next-generation graphics pipeline implemented in software. No quantity of TeraFLOPs can compensate for a lack of support for dynamic dispatch, a full C++programming model, a coherent memory space, etc."
We should point out that at the moment, Intel has only confirmed that the
consumer part has been shelved, meaning that the HPC/GPGPU server/workstation design is still in progress, to be released somewhere down the line. Intel Senior Fellow and CTO, Justin Rattner, recently showed Larrabee could crack the 1TeraFLOP mark at SC09 using a standard HPC benchmark (SGEMM 4Kx4K calculation). Compare this to ATI's
Radeon HD 5870, which hits only 544GigaFLOPS, and Larrabee is clearly a HPC monster. That said, the Radeon has been available for nearly two months already. Nvidia claims its forthcoming Fermi chip is capable of between 900GFLOPs to 1.2TFLOPs, although no actual benchmarks have yet been shown.
Is Intel's entire Larrabee project destined for complete failure? Are you unhappy that we won't have a third player in the graphic market? Or is for this news to be welcomed, the better to protect your beloved ATI/Nvidia from the big brute that is Intel? Let us know your thoughts in
the forums.
21 Comments
Discuss in the forums ReplyThere is already a thread about this:
http://forums.bit-tech.net/showthread.php?t=179314
I, for one, think this is sad news. I'd hoped for Intel to come through with their Larrabee project. I still hope they will, somewhere down the line.
Well it looks like Intel would now have even more motive to buy Nvidia if the opportunity arose, GTX400 at 32nm would be nice.
nVidia are pushing the boundaries?
Hardly, rebranding is their biggest "thing" currently.
Other than that, they're not really doing anything.
Foni hardly counts considering it's looking like they're having a really hard time with it.
i think this is also a degree of what's going on at intel; why release an underperforming flagship product? all they need to do is wait it out, learn something off the back of the server/workstation chip and iterate it until its something enthusiasts want.
Tim Sweeney is one of the guys you can't ignore too, so unless Intel bunged him some epic cash he's probably got a point (although i won't pretend to having a valid opinion on what he said).
I am sorry but Nvidia doesn't simply re brand.. every newer GPU has new features and optimizations.. if you choose to ignore them, then it's not my problem.
The only thing Intel is good at is their x86 architecture CPU's.. no other CPU, or other product. And at least with Nvid aand ATI, you are assured that any software that require a GPU, will run and not crash because it's not part of Intel, now hidden, software compatibility list. Because when Intel makes drivers, it's not for a universal purpose but rather per applications basis.
I think their canceling is a good move:D
Larrabee's future is still behind the fog and the dark now.:)
I don't hate it (I'm fan of Intel), but can't imagine how people could get around with it without any fear:o
Oh well, we still got Lucid to look forward to.
GO NVIDIA!
Take the hole Ati/nvidea situation. Because ati/amd has upped the bar with it's last two gen's (4890 & 5890) this has caused Nvidea to focus!!
Nvidea know's it's loosing popularity, so my gess is taking it's time perfect fermi and make it something "awsome"
Nvidea know's damn well this card need's to be something special or the 5870's will become the high end gpu off choice. (wich up to know has been the gtx 280/285. depite what cpc may have led you to beleive!)
Their TOP TIER card is $600. Nvidia is the one who roams freely at $700+ GPU's. Like the GTX 295 which was $700. I'm sure the price is lowered now, but this is the first time ATI hit a price that high. And guess what, it's STILL lower than what nvidia charges for their top tier cards, and it's STILL faster.
PFFFT.
Are you kidding me? Were you around during the creation of the X1900XTX and the X1800XTX? Those things cost an arm and a leg, they did pretty much wreck the G70, although it was interesting to see the role of uber-chip maker reverse and be handed down to Nvidia after ATi's reign with the RV400 and the RV500.
At any rate, I don't find ATi pushing up the prices too distressing it's expected especially if the competition has no answer.