Huang pimps up Pascal
NVIDIA CEO Jen-Hsun Huang mentioned an upcoming mid-range GPU based on the company’s next-generation “Pascal” architecture which will not use HBM2 memory..
Out of 60 possible
Nvidia confirmed that there are 56 streaming multiprocessor (SM) units each having 64 CUDA cores enabled on the GP100 GPU. This results in 3,584 cores on the Tesla P100 GPU. However, this leaves 4 SM cores disabled as the total number of SM’s is 60.
Still no NVLINK support for consumer x86 CPUs
Giant bug creates crashes and blue screens.
Game Ready driver 364.47 has caused millions of Nvidia Geforce users some major headaches.
AMD's FirePro S9300 x2 Server GPUs to drive its HPC.
A cutting edge Canadian astronomy project will use AMD chips to provide the high performance computing it needs.
Researchers use Tesla K40, Titan X, other Nvidia GPUs to accelerate scientific creativity
This year's Nvidia GPU Technology Conference starts today in San Jose, California and is an exciting opportunity for researchers to compete for their chance to win a $150,000 Nvidia research grant to drive forward groundbreaking scientific ideas aided in large part by GPU-accelerated computing.
Might be even killing some graphcis cards
It appears that Nvidia can't seem to get a break when it comes to drivers as the last Geforce 364.72 WHQL-certified drivers are apparently killing some graphics cards.
For those who can’t wait
A pair of pictures claiming to be the Nvidia GeForce GTX 1080, 1070 cooler shrouds have been leaked online.
Support for Oculus Rift, HTC Vive and some game improvements
Nvidia has rolled out its latest Geforce 364.72 WHQL drivers which bring support for Oculus Rift and an improved experience for HTC Vive, as well as some improvements in current and upcoming games.
Accelerating design workflows with datasets above 12GB
This morning, Nvidia officially took the wraps off the behemoth Quadro M6000 24GB, its Maxwell-based flagship workstation Quadro M6000 GPU with double the memory of last year's 12GB model, and perhaps the last release before its architectural successor, Pascal, is introduced next month at the company’s GPU Technology Conference in Silicon Valley.