New Nvidia GPU turns PC into AI supercomputer

December 11, 2017 // By Rich Pell
Nvidia (Santa Clara, CA) has announced what it says is the world's most powerful graphics processing unit (GPU) for the PC.

Excelling at computational processing for scientific simulation, the TITAN V graphics card can deliver 110 teraflops of computing power - 9X that of its predecessor - and "extreme energy efficiency." It is driven by the company's NVIDIA Volta AI microarchitecture.

"Our vision for Volta was to push the outer limits of high performance computing and AI," says Nvidia founder and CEO Jensen Huang. "We broke new ground with its new processor architecture, instructions, numerical formats, memory architecture, and processor links. With TITAN V, we are putting Volta into the hands of researchers and scientists all over the world. I can't wait to see their breakthrough discoveries."

The new GPU's Volta architecture features a major redesign that the company says doubles the energy efficiency of the previous-generation Pascal design. New Tensor Cores designed specifically for deep learning deliver up to 9x higher peak teraflops, and independent parallel integer and floating-point data paths enable Volta to be much more efficient on workloads with a mix of computation and addressing calculations.

Volta's new combined L1 data cache and shared memory unit significantly improve performance while also simplifying programming. Its highly tuned 12GB HBM2 memory subsystem enables advanced memory bandwidth utilization.

TITAN V is fabricated on a new TSMC 12-nm FFN high-performance manufacturing process customized for Nvidia. It is available for $2,999 from the NVIDIA store in participating countries.

Nvidia

Related articles:
Nvidia introduces compact single-chip AI platform
Deep learning teaching kit educates on GPU-accelerated computing
Nvidia to launch cryptocurrency mining graphics cards
Nvidia credit card-sized IoT platform enables 'AI at the edge'


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.