NVIDIA Announces Volta-based Tesla V100 Accelerator

Written by Michael Larabel in NVIDIA on 10 May 2017 at 03:32 PM EDT. 13 Comments
NVIDIA
NVIDIA CEO Jen-Hsun Huang used the company's GPU Technology Conference to today announce the Volta V100 accelerator for data centers and HPC workloads.

The V100 as the first Volta-based graphics processor is quite a workhorse. The GV100 GPU has 21.1 billion transistors on a 815 mm2 die. The GV100 is manufactured on a 12nm TSMC process and adds on many features over the Pascal-based GP100. In some deep learning workloads, the V100 can be 2.4~3.7x faster than the already mighty powerful GP100.

Volta brings a new streaming multi-processor, second-generation NVLink interconnect, HBM2 memory (16GB HM2 memory delivering 900GB/s), a Volta Multi-Process Service, enhanced unified memory, new capabilities with CUDA 9, and more.

The V100 has a 300 Watt TDP and is rated for 7.5 TFLOPS of double precision compute, 15 TFLOPS of FP32, and 120 Tensor TFLOPS.

More details on the V100 accelerator and the Volta architecture via the NVIDIA blog.

NVIDIA GeForce Volta desktop graphics cards are expected to succeed Pascal in late 2017 or early 2018.
Related News
About The Author
Michael Larabel

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 20,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter, LinkedIn, or contacted via MichaelLarabel.com.

Popular News This Week