nVidia GT300 Fermi: technical specifications
The company nVidia has published detailed specifications of the new GT300 chip, codenamed Fermi . The GPU will be executed as expected using a 40-nm process technology and will contain 3.2 billion transistors, which, by the way, is much more than 2.15 billion transistors of AMD RV870. Accordingly, Fermi is bigger in size than the competitors chip and, more importantly, more expensive to manufacture.
The total number of GT300 shader cores is 512, 32 CUDA cores for each of the 16 streaming multiprocessors. Each individual multiprocessor, by the way, is capable of performing an operation with an integer or floating point number in one clock cycle in each thread. Other features: 384-bit memory bus, 1 MB cache of the first level, 768 KB unified cache of the second level and the ability to use up to 6 GB of GDDR5 memory.
As for technology, Fermi hardware supports CUDA, C ++, DirectCompute, DirectX 11, Fortran, OpenCL, OpenGL 3.1 and OpenGL 3.2. The manufacturer notes that the GT300 is the first ever graphics processor that can execute C ++ code without any loss in performance.
The GT300 product lineup will include GeForce, Quadro and Tesla accelerators (“scientific”). The cost, unfortunately, is not yet known. One can only hope that it will be reasonable. But in general, judging by the dry figures of the technical characteristics, nVidia's answer to the successful AMD RV870 and its implementation in the Radeon 5870 was a success.
')
PS In a year, when the price of cards with this chip drops to an acceptable price, they will become very good candidates in choosing to upgrade for mere mortals.
via hothardware
The total number of GT300 shader cores is 512, 32 CUDA cores for each of the 16 streaming multiprocessors. Each individual multiprocessor, by the way, is capable of performing an operation with an integer or floating point number in one clock cycle in each thread. Other features: 384-bit memory bus, 1 MB cache of the first level, 768 KB unified cache of the second level and the ability to use up to 6 GB of GDDR5 memory.
As for technology, Fermi hardware supports CUDA, C ++, DirectCompute, DirectX 11, Fortran, OpenCL, OpenGL 3.1 and OpenGL 3.2. The manufacturer notes that the GT300 is the first ever graphics processor that can execute C ++ code without any loss in performance.
The GT300 product lineup will include GeForce, Quadro and Tesla accelerators (“scientific”). The cost, unfortunately, is not yet known. One can only hope that it will be reasonable. But in general, judging by the dry figures of the technical characteristics, nVidia's answer to the successful AMD RV870 and its implementation in the Radeon 5870 was a success.
')
PS In a year, when the price of cards with this chip drops to an acceptable price, they will become very good candidates in choosing to upgrade for mere mortals.
via hothardware
Source: https://habr.com/ru/post/71119/
All Articles