Mountain House (CA) - Earlier today we learned that Intel is already heavily pitching its Larrabee technology to partners, but the technology foundation largely remains a mystery. German publication heise.de now provides more clues with a rather interesting note that Larrabee is built on Intel’s nearly two decade-old P5 architecture.
According to Heise author Andreas Stiller, possibly the most prominent person to cover computer hardware in Germany, Intel dipped into the bin of obsolete technology (Intel’s phrase for replaced technology) to come up with a technology base for the Larrabee cGPU. While attending Intel’s 40th anniversary briefing (Intel will celebrate its 40th birthday on July 18), Stiller apparently found out that the Larrabee cores will be built on the P54C core — which was the code-name for the second-gen, 600 nm Pentium chip.
The first Pentium core (P5, 800 nm, 60 and 66 MHz) was in development since 1989 and was introduced in 1993. The P54C was launched in 1994 with speeds up to 120 MHz, while the succeeding 350 nm P54CS reached 200 MHz. The 55C core (280 nm up to 233 MHz) followed in 1995 and was replaced with the Pentium II in 1997.
Stiller added that Larrabee will debut with 32 cores that "are likely" to be equipped with MMX extensions, which would mean that Larrabee will actually be based on a modified, 45 nm P54CS core. The cores will also support 64-bit. If you count in the fact that the MMX part was replaced with a 512-bit wide AVX (Advanced Vector Extensions) unit, Stiller comes up with a theoretical performance of 32 flop/sec. per clock, topping the 2 Tflop/sec. mark at a clock speed of 2 GHz.
If this is true, then Intel may be able to hit about twice the performance in single precision calculations as Nvidia and AMD achieve today. However, both Nvidia and AMD were able to double their floating point performance between 2007 and 2008 and we have reason to believe that once Larrabee will be available, GPUs may be hitting 3 to 4 Tflop/sec. in single GPU configurations. AMD’s dual-GPU ATI Radeon 4870 X2 (clocked at 778 MHz) is estimated to hit 2.49 Tflop/sec. when it debuts within the next few weeks.
It looks like that Intel should be aiming for at least 4 Tflop/sec. for the second half of 2009.