Just after ATI was beaming with the performance of their dual-GPU monster graphics card ATI Radeon HD 5970, Nvidia has quietly decided to push in their Fermi-architecture based GPUs. Nvidia PR guys posted an image of Nvidia GeForce GF100 GPU based graphics card running Unigine Heaven DirectX 11 Benchmark on Twitter and Facebook.
Nvidia unveiled their next generation 40nm process technology involving Fermi architecture last month . As per the recent photo of GF100 GPU shown, the graphics card uses PCI-Express eight-pin adapter to the left and six-pin adapter to the right. This means existing power supplies could be used for supplying power to this monstrous card.
Nvidia GF100 GPU was being tested on Asus Rampage II Extreme supporting Intel LGA 1366 socket couple with Intel Core i7 CPU and DDR3 memory. However, there is speculation over the web that Nvidia will demo a working GeForce Fermi GPU at Super Computer Convention 2009 in Oregon, US.
Nvidia Fermi platform specifications leaked earlier:
-3 billion transistors
-40nm Silicon die
-384-bit memory interface
-512 shader cores [renamed into CUDA Cores]
-32 CUDA cores per Shader Cluster
-1MB L1 cache memory [divided into 16KB Cache - Shared Memory]
-768KB L2 unified cache memory
-Up to 6GB GDDR5 memory
-Half Speed IEEE 754 Double Precision
No comments:
Post a Comment