NVIDIA GF100 Fermi DirectX 11 graphics card detailed
Can’t wait till March to know more about NVIDIA’s first DirectX 11 GPU? Well, we now have more information on the Fermi architecture based graphics card. The NVIDIA GF100 features four main units called the Graphics Processing Clusters (GPC). Each GPC includes 4 streaming multiprocessor cores (SP), resulting in a total of 16 SP.
Each graphics processing clusters also has a Raster Engine and a dedicated hardware tessellators, or what Nvidia calls ‘polymorph engines’, appearing one per SM.
In turn each streaming multiprocessor features 32 CUDA cores, 16 or 48KB of shared memory and 16 or 48KB of L1 cache and 4 texture units.
The NVIDIA GF100 GPU will be out in March / April.
[via CDR Info]
