Nvidia just announced their next-gen architecture after Maxwell, Volta codenamed after Alessandro Volta.
http://en.wikipedia.org/wiki/Alessandro_Volta
Nvidia just announced their next-gen architecture after Maxwell, Volta codenamed after Alessandro Volta.
http://en.wikipedia.org/wiki/Alessandro_Volta
UniversalTruth
Veteran
What year should we be expecting this for? 2020? 
What year should we be expecting this for? 2020?
Next high performance process node succeeding TSMC 20nm. 2016?
Last edited by a moderator:
What year should we be expecting this for? 2020?
There are enough interested parties for stacked DRAM that I think something will come up before then.
One key thing is that making Volta's marketing bullet point stacked DRAM is that this can be relatively agnostic to the GPU architecture it is attached to. Delays in architectural design would be one possible source of schedule slippage that won't be a barrier to releasing something with stacked DRAM and calling it Volta.
Every other challenge to implementing the solution would remain, but everyone wants the bandwidth and power savings. They are going to be hard-pressed to get it any other way.
Last edited by a moderator:
Should be by 2015. Most of the fabs have been developing 16nm/14nm in parallel to 20nm as they need to close the gap with Intel. (As much as they can at least). Hopefully they won't split and 20nm might actually be a pretty short lived node.
Yeah, I believe so. To achieve 1 TB/sec, they would need an extremely wide bus like 1024-bits at 8 Gbps IO. I think that would be very cost prohibitive.
GDDR6 would be out by then, so the scenario isn't quite as grim.
iMacmatician
Regular
On the GPU roadmap slide, is the y-axis DP GFLOPS/W? Seems like it at least from Fermi and Kepler's placements.
UniversalTruth
Veteran
Yup, I remember discussing this here. If so, I guess late 2015/ early 2016 for Volta.
Ninjaprime
Regular
Looks like all the memory is stacked, or at least they are showing 24 RAM chips, which is about right.
DavidGraham
Veteran
So what advantage does Stacked memory hold over standard memory ? less latency? faster access times? or just plain old increase in frequency ?
Didn't Amkor show off a future AMD GPU with an interposer and stacked memory a couple years ago? I was wondering when we'd be hearing more about this.
Edit: Found it http://sites.amd.com/la/Documents/TFE2011_001AMC.pdf, page 8
http://www.computerbase.de/news/2011-10/amd-gpu-mit-stacked-memory-gesichtet/
Edit: Found it http://sites.amd.com/la/Documents/TFE2011_001AMC.pdf, page 8
http://www.computerbase.de/news/2011-10/amd-gpu-mit-stacked-memory-gesichtet/
