NVIDIA To Unveil New "Optimus" Mobile Technology At CES
With CES scheduled to begin in just two days, NVIDIA has begun publicly hinting about the technology it plans to display at the trade show this year. According to a recent blog post, the company will showcase a new mobile technology under the "Optimus" brand name. Details are scarce; the blog only states the following: "NVIDIA Optimus technology works on notebook platforms with NVIDIA GPUs. It is unique to NVIDIA. It is seamless and transparent to the user. Its purpose is to optimize the mobile experience by letting the user get the performance of discrete graphics from a notebook while still delivering great battery life. Look for more details next month."
That's quite vague, even by the standards of pre-CES announcements. Team Green is evidently trying to whip up a bit of hype over this new, battery-life-enhancing technology, but it hasn't actually said anything about its capabilities. If we had to hazard a guess at the new major feature of Optimus, assuming there is one, we'd bet NVIDIA has developed a way to shut down significant parts of the GPU when those areas of the chip are not in use.
This would be a logical step forward. GPUs are implementing more CPU-like features with every generation; moving towards this type of power saving mirrors the development of CPU technologies like SpeedStep over the past ten years. The ability to shut down specific parts of a GPU could also be viewed as an extension of Hybrid SLI, which allows users to pair an integrated and discrete GPU for 3D performance, while shutting the discrete card off completely when in 2D mode in order to reduce power consumption. Blending that functionality into a single chip would reduce motherboard complexity and thereby manufacturing cost, while offering the "seamless and transparent" operation NVIDIA refers to in the blog post above.
NVIDIA's original ION chipset. Ion 2 will be more GPU-centric, as Intel has integrated additional chipset functionality into the latest iteration of the Atom processor.
Don't be surprised if Ion 2 and Optimus turn out to be linked at the hip. Ion was a major item of interest at CES 2009 and consumer interest in Atom shows no sign of slowing. NVIDIA will undoubtedly be talking about both Ion 2 and Fermi, but interest in the former is directly linked to the positive perception of its predecessor. Fermi, no matter how aggressively NVIDIA might talk up the product, is months behind schedule and not expected to be available in volume until March at the very earliest. Given the option, we expect NVIDIA will play to its strengths, promised "sneak peeks" at its new GF100 technology notwithstanding.
That's quite vague, even by the standards of pre-CES announcements. Team Green is evidently trying to whip up a bit of hype over this new, battery-life-enhancing technology, but it hasn't actually said anything about its capabilities. If we had to hazard a guess at the new major feature of Optimus, assuming there is one, we'd bet NVIDIA has developed a way to shut down significant parts of the GPU when those areas of the chip are not in use.
This would be a logical step forward. GPUs are implementing more CPU-like features with every generation; moving towards this type of power saving mirrors the development of CPU technologies like SpeedStep over the past ten years. The ability to shut down specific parts of a GPU could also be viewed as an extension of Hybrid SLI, which allows users to pair an integrated and discrete GPU for 3D performance, while shutting the discrete card off completely when in 2D mode in order to reduce power consumption. Blending that functionality into a single chip would reduce motherboard complexity and thereby manufacturing cost, while offering the "seamless and transparent" operation NVIDIA refers to in the blog post above.
NVIDIA's original ION chipset. Ion 2 will be more GPU-centric, as Intel has integrated additional chipset functionality into the latest iteration of the Atom processor.
