Technology news
Loading...

NVIDIA launched graphics card which can change human world

Tesla P100 is the name of a completely new graphics cards from NVIDIA which uses the wolrd’s most modern technology

At this time the demand for PC is declining because of "encroaching" of smartphones and tablets on entertainment and the dominance of the consoles in the gaming industry, GPU - graphics processing unit – has had constant breakthroughs in recent years. One of the main reasons is because of the high adaptability, the ability to undertake other tasks outside the picture.

And NVIDIA  company plays an improtant role in this revolution with its CUDA platform.

And recently, NVIDIA has officially informed about its desire to dominate the hardware market for database super centers, particularly in developing artificial intelligence by producing a completely new product called GPU Tesla P100.
 The Tesla
The Tesla P100 is the first full-size Nvidia GPU based on the TSMC 16nm FinFET manufacturing process—like AMD, Nvidia has been stuck using an older 28nm process since 2012—and the first to feature the second generation of High Bandwidth Memory (HBM2). HBM2 is abig boost in performance over Nvidia's current performance champs like the Maxwell-based Tesla M40 and the Titan X/Quadro M6000. Nvidia says the P100 reaches 21.2 teraflops of half-precision (FP16) floating point performance, 10.6 teraflops of single precision (FP32), and 5.3 teraflops (1/2 rate) of double precision. By comparison, the Titan X and Tesla M40 offer just 7 teraflops of single precision floating point performance.

There's a core clock of 1328MHz and a boost clock of 1480MHz—both much higher than Maxwell-based GPUs—along with a 300W TDP. Pascal features 64 FP32 CUDA cores per SM, compared with 128 on Maxwell, with each of those SMs also containing 32 FP64 CUDA cores. That results in the 1/2 rate performance of double precision floating point. Pascal is also able to pack two FP16 operations inside a single FP32 CUDA core. The HBM2 memory is laid out in four 4GB stacks, each with a 1024-bit width for a total 4096-bit memory bus.

 NVIDIA's CEO said
NVIDIA's CEO said "DGX 1 is made to a single goal is to open the ultimate power of technology to solve issues and problems of all humanity".
And users do not have to wait too long to master the ultimate power when in this May, NVIDIA will release advanced graphics cards based on Pascal's background which are GTX 1080 and GTX 1070.

  • What You know about the supper airport ship USS George Washington?

    What You know about the supper airport ship USS George Washington?

    As one of America's legendary battleship, the supper airport ship USS George Washington has speed moving 56 km/h and propulsion uses 2 nuclear reactors

  • ►Microsoft has added the Microsoft Translator which translates handwritings in the photograph

  • ►Google Goals - filling gaps tool for schedules