Sandy Bridge is Intel’s latest CPU with a twist. Sandy Bridge is not simply a 32nm CPU. Sandy Bridge also contains an on-die GPU that shares the L3 cache of the CPU. This on-die GPU doubles the performance of Intel’s HD Graphics today. The GPU makes use of fixed function hardware, which is the opposite design approach for many GPUs today. The idea behind this was that with fixed function hardware increases the performance efficiency and die area. The downside is that you lose some flexibility. Not everything in the GPU is fixed function hardware. The GPU does come with programmable shader hardware which is called Execution Units (EUs). When Sandy Bridge is launched, it will come with two different configurations for the GPU. The first version will have 6 EUs while the second version will have 12 EUs. Sandy Bridge will start showing up in systems during the first quarter of 2011. AnandTech has posted a great review of the Sandy Bridge architecture.
The largest performance improvement on Sandy Bridge vs. current Westmere architectures actually has nothing to do with the CPU, it’s all graphics. While the CPU cores show a 10 – 30% improvement in performance, Sandy Bridge graphics performance is easily double what Intel delivered with Clarkdale/Arrandale at the beginning of the year.
The Sandy Bridge GPU is on-die built out of the same 32nm transistors as the CPU cores. The GPU is on its own power island and clock domain. The GPU can be powered down or clocked up independently of the CPU. Graphics turbo is available on both desktop and mobile parts, and you get more bins with graphics turbo on Sandy Bridge than you did with Arrandale.
