Tuesday, May 25th 2010
NVIDIA Releases GeForce GTX 480M, World's Fastest Notebook GPU
NVIDIA made its GeForce GTX 480M GPU official today. The DirectX 11 compliant GPU is based on the GF100 core and packs all the features of its desktop counterpart, such as decentralized hardware tessellation, next-generation CUDA and DirectCompute 5.0. The GF100 core has a configuration similar to the GeForce GTX 465 desktop GPU. It has three of its four graphics processing clusters (GPCs), and 11 out of 16 streaming multiprocessors (SMs) enabled, giving a CUDA core count of 352. To reduce the overall board footprint, the GPU makes do with a 256-bit wide GDDR5 memory interface, with 1 GB of memory.
To make keep up with the electrical constraints of notebooks, the GTX 480M uses much lower clock-speeds than any desktop product that uses GF100. The core is clocked at 425 MHz, shader domain at 850 MHz, and memory at 600 MHz (real) or 2.40 GHz (effective), which gives a memory bandwidth of 76.8 GB/s. As mentioned earlier, the full feature-set of its desktop counterparts is packed with the GTX 480M, including support for NVIDIA 3D Vision, PureVideo HD, PhysX, and CUDA. It can pair with up to two boards of its kind in 2-way SLI. Constraints of the notebook form-factor won't allow any more boards, anyway. The GPU is open to Notebook manufacturers to plan their designs around. NVIDIA claims the GTX 480M to be the fastest notebook GPU. It finds direct competition in the ATI Mobility Radeon HD 5870, which is based on the 800 stream processor-laden Juniper core.
To make keep up with the electrical constraints of notebooks, the GTX 480M uses much lower clock-speeds than any desktop product that uses GF100. The core is clocked at 425 MHz, shader domain at 850 MHz, and memory at 600 MHz (real) or 2.40 GHz (effective), which gives a memory bandwidth of 76.8 GB/s. As mentioned earlier, the full feature-set of its desktop counterparts is packed with the GTX 480M, including support for NVIDIA 3D Vision, PureVideo HD, PhysX, and CUDA. It can pair with up to two boards of its kind in 2-way SLI. Constraints of the notebook form-factor won't allow any more boards, anyway. The GPU is open to Notebook manufacturers to plan their designs around. NVIDIA claims the GTX 480M to be the fastest notebook GPU. It finds direct competition in the ATI Mobility Radeon HD 5870, which is based on the 800 stream processor-laden Juniper core.
55 Comments on NVIDIA Releases GeForce GTX 480M, World's Fastest Notebook GPU
Jared says 15% faster than a 5870, just like i said.
I never said it's not possible to have a laptop with such a high power usage. I said it's crazy.
I really don't see the point of a 8kg laptop. Why do they even call it a laptop. Anybody crazy enough to put one of these on their lap is going to be sterile afterwards.
Some people mentioned LAN parties but i think a game system built in a micro-ATX case is much more efficient.
And you reference to multi GPU configs to be as power hungry. True, but it's easier to implement efficient cooling of two separate 50W GPU's instead of one 100W GPU in a laptop.
If you check out something like an Alienware laptop with multi-GPU, you'll see that they put the two MXM modules far from eachother. Each being cooled by a separate cooler and heatsink. It's becomes a bigger problem when all this heat is coming from one spot (in a laptop i mean).
As you see in Anand's post, there won't be an Optimus enabled GTX480M laptop.
So what advantage does it hold over a 5870X2 setup? Because that's what i keep refering to and that's what you keep dismissing. Same money, same heat, no battery life but faster.
If you want the fastest, no matter the weight, then that would be the 5870X2.