NVIDIA Details Pascal GPU at GTC Japan

NVIDIA Details Pascal GPU at GTC Japan

NVIDIA Details Pascal GPU at GTC Japan

NVIDIA Details Pascal GPU at GTC Japan

 

NVIDIA has detailed their Pascal GPU architecture at GTC Japan, saying that it will offer 2x the performance per watt of their already efficient Maxwell architecture and will contain a max of 16GB of HBM2 memory for consumer GPUs. 

Nvidia's Pascal GPUs will be built using TSMC's 16nm process, which is not just a smaller processing node, but a process which uses FinFET transistors, which will offer a great performance leap over the 28nm planar transistors used in current generation GPUs. 

  NVIDIA Details Pascal GPU at GTC Japan  

The move to 3D memory from traditional planar GDDR5 memory will not only give a massive leap in GPU memory performance, but also allow increased capacities, with 4x4GB HBM2 memory giving consumer Maxwell GPUs up to 16GB of VRAM. 

NVIDIA’s Marc Hamilton had this to say about HBM and Nvidia's NVlink:

 

“Using 3D memory, not only the memory capacity will go up, the memory bandwidth will go up significantly. With a much faster GPU, and higher memory bandwidth, the existing interconnects in the server are just plain outdated. So, we had to develop our own interconnect called NVLink, five times faster than existing technology.”

 

NVIDIA Details Pascal GPU at GTC Japan  

The next generation of GPUs from both AMD and Nvidia will be very interesting indeed, with both sides saying that they will get a 2x jump in performance per watt, moving to FinFET transistors and moving to use HBM 2.0 memory. 

These next generation GPUs are expected to come in early to mid 2016. 

 

You can join the discussion on Nvidia's Pascal GPUs on the OC3D Forums

 

 

«Prev 1 Next»

Most Recent Comments

18-11-2015, 08:56:56

SpencerUk
Looks like HBM is here to stay then eh!Quote

18-11-2015, 10:47:11

Kilbane
Quote:
Originally Posted by SpencerUk View Post
Looks like HBM is here to stay then eh!
Huge leap in memory performance. Plus HBM 2 has double the bandwidth maximum of HBM. Big, big leaps forward.Quote

18-11-2015, 14:17:38

NeverBackDown
I predicted upto 16GB hbm2 and 16nm for quite some time now.. if all seems likely AMD will probably go to 14nm. This will be a pretty interesting gen of cardsQuote

18-11-2015, 14:23:50

Zoot
Quote:
Originally Posted by NeverBackDown View Post
This will be a pretty interesting gen of cards
It's sure shaping up like that.

I'm planning a GPU upgrade next year from my aging GTX 780, it'll be a great time to be in the market for one.Quote

18-11-2015, 14:32:19

NeverBackDown
Quote:
Originally Posted by Zoot View Post
It's sure shaping up like that.

I'm planning a GPU upgrade next year from my aging GTX 780, it'll be a great time to be in the market for one.
I plan on upgrading from my Fury X. Probably not a top of the line card since a mid tier card could probably get the same performance as mine now and mostly due to funds for a toon tier cardQuote
Reply
x

Register for the OC3D Newsletter

Subscribing to the OC3D newsletter will keep you up-to-date on the latest technology reviews, competitions and goings-on at Overclock3D. We won't share your email address with ANYONE, and we will only email you with updates on site news, reviews, and competitions and you can unsubscribe easily at any time.

Simply enter your name and email address into the box below and be sure to click on the links in the confirmation emails that will arrive in your e-mail shortly after to complete the registration.

If you run into any problems, just drop us a message on the forums.