We are not talking theorethical AMD/NVIDIA PR performance here, lets compare the numbers in SGEMM:
http://www.lockergnome.com/theoracle/2009/12/05/what-is-intel-doing/
1. Intel Larrabee [LRB, 45nm] - 1006 GFLOPS
2. EVGA GeForce GTX 285 FTW - 425 GFLOPS
3. nVidia Tesla C1060 [GT200, 65nm] - 370 GFLOPS
4. AMD FireStream 9270 [RV770, 55nm] - 300 GFLOPS
5. IBM PowerXCell 8i [Cell, 65nm] - 164 GFLOPS
What was that?
Intel suddenly layning the smack down on GPGPU....in their first go.
No wonder NVIDIA wan't Fermi out...before Intel sits itself on the HPC market.
AMD, so far, are the only one not playing the game...unless you think a single R800 GPU can do the same?
(Which by AMD PR is a +3 TeraFlop card )
I was very clear that I was talking about *GAMING* performance, but please, continue to link to irrelevant crap.
From the article you linked to:
So it would seem that for High Performance Computing the Intel part walks all over the competitors, but in the real world of retail wants and needs, the part is seriously lacking as a video chip. tradeoffs were made, and they seem to have been the wrong ones, as far as discrete video graphics cards are concerned.
Great, Intel made a discreet video card aimed at competing with ATI and Nvidia's latest and greatest and then forgot about the "video" part, super.
Also:
We dont have information about SGEMM performance of Evergreen GPUs [5700, 5800, 5900 series] ...
So it isn't even compared to the current best, just last gen.