NVIDIA has unveiled the Titan V, a new desktop GPU that’s been designed to bring massive amounts of power to those working on machine learning applications.
Announced by Nvidia founder and CEO Jensen Huang at the annual NIPS conference, the Titan V was touted as “the world’s most powerful GPU for the PC” and made to excel at computational processing for scientific simulation.
With 21.1 billion transistors delivering 110 teraflops of raw horsepower, the Titan V is said to be nine times as powerful as its predecessor, and way more energy efficient thanks to being based on Nvidia’s Volta GPU architecture.
This Volta architecture features a major redesign of the streaming multiprocessor that is at the centre of the GPU. It doubles the energy efficiency of the previous generation Pascal design, enabling dramatic boosts in performance in the same power envelope, Nvidia claims.
“Our vision for Volta was to push the outer limits of high performance computing and AI. We broke new ground with its new processor architecture, instructions, numerical formats, memory architecture and processor links,” Huang said at the conference. “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 Volta also features new Tensor Cores, which have been designed specifically for deep learning to deliver up to 9x higher peak teraflops.
“With independent parallel integer and floating-point data paths, Volta is also much more efficient on workloads with a mix of computation and addressing calculations,” Nvidia explained in a news release. “Its new combined L1 data cache and shared memory unit significantly improve performance while also simplifying programming.”
And because the Volta is fabricated on a new TSMC 12-nanometer FFN high-performance manufacturing process, which has been customised for the Titan V, it also incorporates a highly tuned 12GB HBM2 memory subsystem for better memory bandwidth utilisation.
The Titan V is available from today in the US for a whopping $2,999 (about £2,225). µ
Source : Inquirer