the topic said all, NVIDIA released Tesla K80, GK210 based card with 2x 12GB of vRAM
here's official site to read a bit =) http://www.nvidia.com/object/tesla-servers.html
and some thoughs via .@anandtech http://www.anandtech.com/show/8729/nvid ... -gk210-gpu
& tom's hardware http://www.tomshardware.com/news/nvidia ... 28086.html
"It's highly doubtful that we'll see a GeForce card ever carry the GK210, but when we asked, the company didn't rule out the possibility of a future Titan card powered by this graphics processor."
& few pics to illustrate:
NVIDIA released Tesla K80, GK210 based card with 2x12GB vRAM
You do not have the required permissions to view the files attached to this post.
Last edited by glimpse on Tue Nov 18, 2014 7:43 am, edited 1 time in total.
- Seekerfinder
- Posts: 1600
- Joined: Tue Jan 04, 2011 11:34 am
Wow. Less cuda cores than a Z, it's the 12GB ram that caught my attention. No wonder the Z prices have been dropping. But Kepler?? What's going on with these guys...?
Price tag? I'd be surprised if it's under $7K.
It would be interesting to see what the new year holds for GTX cards. Who knows, perhaps there's even a pre-Christmas release.
Seeker
Price tag? I'd be surprised if it's under $7K.
It would be interesting to see what the new year holds for GTX cards. Who knows, perhaps there's even a pre-Christmas release.
Seeker
Win 8(64) | P9X79-E WS | i7-3930K | 32GB | GTX Titan & GTX 780Ti | SketchUP | Revit | Beta tester for Revit & Sketchup plugins for Octane
- Seekerfinder
- Posts: 1600
- Joined: Tue Jan 04, 2011 11:34 am
It seems to be 12GB PER GPU. That's a total of 24GB vram. So Octane should have access to 12GB. Or am I missing something?kavorka wrote:Seekerfinder wrote:the 12GB ram that caught my attention.
Looks like it is 2 Kepler GPUs stuck together, which would mean it is actually 6 GB in Octane.
Also, these are dual slot cards, not triple slots like Titan Z. I'll take 7.
Seeker
Win 8(64) | P9X79-E WS | i7-3930K | 32GB | GTX Titan & GTX 780Ti | SketchUP | Revit | Beta tester for Revit & Sketchup plugins for Octane
12 gb for octane is already in quadro cards but this news gives us hope to see a great titan release next year - 12gb? 
Some more data
http://wccftech.com/nvidia-tesla-k80-gk ... n-compute/

Some more data
http://wccftech.com/nvidia-tesla-k80-gk ... n-compute/
3090, Titan, Quadro, Xeon Scalable Supermicro, 768GB RAM; Sketchup Pro, Classical Architecture.
Custom alloy powder coated laser cut cases, Autodesk metal-sheet 3D modelling.
build-log http://render.otoy.com/forum/viewtopic.php?f=9&t=42540
Custom alloy powder coated laser cut cases, Autodesk metal-sheet 3D modelling.
build-log http://render.otoy.com/forum/viewtopic.php?f=9&t=42540
Yeah the price probably going to be stratospherically high =) but it's kinda understandable considering where those card are targeted =) for sure SKUs will come for desktop users..with cropped DP, other drivers, higher thermal ceilings etc..-though probably with less of vRAM (as always) & a year later =) seems nVidia always kick of with most expensive stuff in PRO line..-with this in mind I don't think we are going to see "Titan II" in '14 =) maybe next year..somewhere at GTC, maybe even later..
some thought from Tom'sHardware (added to the first post =)
some thought from Tom'sHardware (added to the first post =)
I still believe we'll see 210 in gtx line. As we saw 104 and 110, now we have 204. What interesting is that this is still 28nm, which is (as I think) the reason for same or even lower cuda core numbers (heat may be an issue). This may take some time to go below 20nm. I bet 2015 is year of 210, also for gtx.
3090, Titan, Quadro, Xeon Scalable Supermicro, 768GB RAM; Sketchup Pro, Classical Architecture.
Custom alloy powder coated laser cut cases, Autodesk metal-sheet 3D modelling.
build-log http://render.otoy.com/forum/viewtopic.php?f=9&t=42540
Custom alloy powder coated laser cut cases, Autodesk metal-sheet 3D modelling.
build-log http://render.otoy.com/forum/viewtopic.php?f=9&t=42540