Monday, May 18th 2009

Larrabee Only by 2010

Last week, Intel announced its Visual Computing Research Center at Saarland University in Saarbr├╝cken, Germany. During its opening ceremony, details emerged about when Intel plans to commercially introduce Larrabee, the company's take on graphics processing using x86-based parallelism. The company categorically stated that one could expect Larrabee to be out only by early 2010.

"I would expect volume introduction of this product to be early next year," said Intel chief executive Paul Otellini. Until now, Larrabee was known to be introduced coarsely around the 2009-2010 time-frame. "We always said it would launch in the 2009/2010 timeframe," said Intel spokesperson Nick Knupffer in an email to PC Magazine. "We are narrowing that timeframe. Larrabee is healthy and in our labs right now. There will be multiple versions of Larrabee over time. We are not releasing additional details at this time," he added. In the same event, Intel displayed a company slide with a die-shot of Larrabee, revealing what looked like the x86 processing elements. Sections of the media were abuzz with inferences drawn on the die-shot, some saying that it featured as many as 32 processing elements.Source: PC Magazine
Add your own comment

27 Comments on Larrabee Only by 2010

#1
Mussels
Moderprator
since we're in the middle of 09 now, that means 6-12 months.

That means they're competing with next-gen Nvidia and ATI products... it'll be a fun period :)
Posted on Reply
#2
btarunr
Editor & Senior Moderator
by: Mussels
since we're in the middle of 09 now, that means 6-12 months.

That means they're competing with next-gen NVIDIA and ATI products... it'll be a fun period :)
FTFY. Maybe this is why NV is going close to overkill with GT300. Can't underestimate someone like Intel.
Posted on Reply
#3
Mussels
Moderprator
FTFY? Furry tree flies... yellow?
Posted on Reply
#4

To be honest, if they will have even similar performance as we do have NOW, they will be way over my expectations. Really, who believes that lar. will compete with G300 and RV800?
Although, you don't need to be the performance leader to have profit (AMD i.e.).
#5
gumpty
by: Mussels
FTFY? Furry tree flies... yellow?
Fun Times For Yosemite?
Posted on Reply
#6
Mussels
Moderprator
by: GFC
To be honest, if they will have even similar performance as we do have NOW, they will be way over my expectations. Really, who believes that lar. will compete with G300 and RV800?
Although, you don't need to be the performance leader to have profit (AMD i.e.).
i beleive it will compete. my god, if anyone can pull off 32 CPU's matching a GPU, its intel.
Posted on Reply
#7
btarunr
Editor & Senior Moderator
FTFY = fixed that for you. Compare the post I quoted to yours.
Posted on Reply
#8
Mussels
Moderprator
oh lawl. typo for the lose.
Posted on Reply
#9
qwerty_lesh
But adding more shaders doesnt give the same peformance yeild as it once did for GPU architecture like ATI and nVidia GPU's.
I hope Larrabee doesnt turn out to be a flop, its such a unique architecture, Intels taking quite a gamble and has to fight the stigma their intergrated poopy graphics offering has left them with.
Just reading about Larrabee makes it sound ever more so awesome, built of the Pentium architecture but modified like crazy, the way it splits threads into strands and all that is cool it, doesnt use stream processors afaik.
I think PC Perspective have some detailed articles about it.

by: GFC
To be honest, if they will have even similar performance as we do have NOW, they will be way over my expectations. Really, who believes that lar. will compete with G300 and RV800?
Although, you don't need to be the performance leader to have profit (AMD i.e.).
I believe that to begin with, we'll be lucky if we see close to the same peformance of current cards, the benefit is though that unlike the card manufacturers which will have to go back to the drawing boards when slapping more SP's on doesnt make their cards faster, Intel (provided the product doesnt get canned) could in theory, just cruse along with their scalable peformance, not needing to worry about hitting some peformance wall.

Anyway, Intel to face the same conundrum they had with Itanium which I hope doesnt stop larrabee from being a big change to computing/gaming/etc.
Posted on Reply
#10
PlanetCyborg
2010 GPU market by performance 1# AMD/ATI 2#INTEL 3#Nvidia GT300=EPIC FAIL
Posted on Reply
#11
lemonadesoda
Larrabee as a GPU is a trojan horse.

With 32x 512-bit vector MIMD it will whoopass CUDA.

512-bit can handle 8 double precision (32 bit) or long integer variables. And 32x. That is equivalent to 256x the speed of a regular math unit in a single core processor.

That means for math work, Larrabee has the potential to be (256/4)=64x as fast as a quad core CPU clock-for-clock. It will probably be running at half the frequency of a regular CPU, maybe slower. But that will equate to at least 16-24x the speed of a quad core.

And math libraries can be very rapidly modified for Larrabee x86.

R.I.P. CUDA/Tesla.

nV know this. GT300 has to compete. Look at the panic in their eyes.

Moore's Law will be bust open for the 2008-2010 season. And the Soda-Darwin law applies: survival of the fastest.
Posted on Reply
#12
Mussels
Moderprator
oh and you can bet your ass intel will put out an i7 server motherboard with 4 PCI-E x16 slots just waiting for 4x larrabees to rape and pillage CPU farms everywhere.
Posted on Reply
#13
KainXS
by: lemonadesoda
Larrabee as a GPU is a trojan horse.

With 32x 512-bit vector MIMD it will whoopass CUDA.

512-bit can handle 8 double precision (32 bit) or long integer variables. And 32x. That is equivalent to 256x the speed of a regular math unit in a single core processor.

That means for math work, Larrabee has the potential to be (256/4)=64x as fast as a quad core CPU clock-for-clock. It will probably be running at half the frequency of a regular CPU, maybe slower. But that will equate to at least 16-24x the speed of a quad core.

And math libraries can be very rapidly modified for Larrabee x86.

R.I.P. CUDA/Tesla.

nV know this. GT300 has to compete. Look at the panic in their eyes.

Moore's Law will be bust open for the 2008-2010 season. And the Soda-Darwin law applies: survival of the fastest.
Nvidia switched to MIMD, but I think these cards have the potential to suprise everyone, I think they might be the first PCI-E 3.0 cards too

well, maybe not lol:D

but its really funny how nobody is talking about how Nvidia stole Intels plan to use MIMD, they obviously did, but everyone still busses on Intel for doing things different
Posted on Reply
#14
qwerty_lesh
I havent seen mention once that they will be made as a gaphics card.
Posted on Reply
#15
FreedomEclipse
~Technological Technocrat~
by: Mussels
FTFY? Furry tree flies... yellow?
Fat Turkeys For Yankies?
Posted on Reply
#16
FordGT90Concept
"I go fast!1!11!1!"
Bah, 6-12 more months? I don't know if my 8800 GT can take that much more abuse. :(
Posted on Reply
#18
Mussels
Moderprator
actually one thing gets to me.

what the hell does the "only" in the title actually mean?
Posted on Reply
#19
Breathless
by: btarunr
FTFY = fixed that for you. Compare the post I quoted to yours.
Get it right dude. It means Fluffy Truffles Fortify You.
Posted on Reply
#20
Salsoolo
by: tkpenalty
So... what about AMD?
already in the graphics business (ATi) :rolleyes:
Posted on Reply
#21
h3llb3nd4
I suppose he knew that already:)
I think he meant"what's their next move in the graphics sector?"
Posted on Reply
#22
Morgoth
good news gives me time to get my system running
Posted on Reply
#23
Suijin
I think Intel is taking too long to try to hit a moving target. Plus they haven't had a good track record with graphics performance. Nvidia and AMD will at least have revised versions of G300 and RV800 out by the time Intel releases Larrabee, and they may be well on the way to G400 and RV900 by then. Looks like G300 will be a good bit faster than G200 and AMD will be doing their thing also, I don't quite see how they will have anything better than them at release.

I do believe Intel can make a better one eventually, but they need to make the decision to put the effort and time in for the long term.
Posted on Reply
#24
FordGT90Concept
"I go fast!1!11!1!"
Intel has a great track record with graphics performance--for those that do only light gaming and no gaming at all. Their IGPs are wildly successful. Intel has only been working on this for 2-3 years at most and it usually takes about 4-5 years to develop new processors. The rate they are going at is excellent.

Again, Intel's design is superscaler. It isn't very hard for them to release a processor with far more cores but it comes at a price. Intel shouldn't have much problem staying way ahead of NVIDIA and AMD.

Remember, the only thing that's really special about GPUs is there extremely high FlOp performance. It doesn't matter how a GPU gets (only reflected in price/profit margins) it so long as it gets it.
Posted on Reply
#25
hat
Maximum Overclocker
It's probably taking them that long to develop a cooling solution for that monster seeing as they've already got the dies made.
Posted on Reply
Add your own comment