You have to remember that was due to TSMC having some issues on their end. GF on the other hand skipped 10nm and has been working on straight on 7nm. Although this is with DUV, I suspect the 7nm+ will be 7nm made with EUV.
-
Competitor rules
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
AMD VEGA confirmed for 2017 H1
- Thread starter Doom112
- Start date
- Status
You have to remember that was due to TSMC having some issues on their end. GF on the other hand skipped 10nm and has been working on straight on 7nm. Although this is with DUV, I suspect the 7nm+ will be 7nm made with EUV.
Permabanned
- Joined
- 12 Sep 2013
- Posts
- 9,221
- Location
- Knowhere
+1
Nvidia call them GTX cards and they have gaming driver support.
If that wasn't the case why would they remove the first Titans workload capabilities and release the unlocked TxP straight after the 1080ti if not to maintain it's fastest card position?
It's NVIDIA themselves saying it's not a gaming card in their reviewer briefs though; then they slap on the GeForce drivers and branding.
No wonder there's confusion.
Permabanned
- Joined
- 12 Sep 2013
- Posts
- 9,221
- Location
- Knowhere
As a great man once said "That was a waste of a perfectly good explanation".
DUV?
EUV?
You'll have to excuse me while I go and read up on it...
This is what I thought was the case, but again I need to go have a read.
Some basic reading suggests that 7nm is nowhere near ready for prime time; ditto EUV. Wiki (I know) suggests 7nm won't be available until 2020 in high volume.
Actually there is a feature added in DX12 as MANDATORY but also optionally available in DX11 called Tiled Resources. I quote from Microsoft:
Tiled Resources decouple a D3D Resource object from its backing memory (resources in the past had a 1:1 relationship with their backing memory). This allows for a variety of interesting scenarios such as streaming in texture data and reusing or reducing memory usage.
I have said several times that I would be surprised if HBCC worked without support from software and it seems to me that AMD are probably exploiting somethings like this. If the game supports this feature (whether DX11 or DX12) the AMD driver should be able to exploit the HBCC.
Not true. If the HBCC was unaware of VRAM access patterns it would need to start transferring data after a 'cache miss' meaning it is too late already: there will be latency and min FPS drop.
Last edited:
As a great man once said "That was a waste of a perfectly good explanation".
DUV?
EUV?
You'll have to excuse me while I go and read up on it...
It is to do with the way a integrated circuit design is transferred to the silicon - dies are made using a process not a million miles removed from old film photography - grossly simplified DUV and EUV refer to the light used to expose the design involved in this.
Just saw http://pro.radeon.com/en-us/vega-frontier-edition/
I couldn't help thinking "yes, because by then Voltas will be available..."
I couldn't help thinking "yes, because by then Voltas will be available..."
Volta won't be available in June.
That might be the case for the Titan Xp, but as I've said people have been saying this since the very first Titan came out about 4 years ago.
Obviously nVidia are talking ***** now though, given the fact that it's a GTX and runs GeForce drivers as you said.
As a great man once said "That was a waste of a perfectly good explanation".
DUV?
EUV?
You'll have to excuse me while I go and read up on it...
This is what I thought was the case, but again I need to go have a read.
It's basically how they etch the designs into the silicon using lasers, DUV is deep ultraviolet and has been used for a good while so is more mature, while EUV is extreme ultraviolet which should allow less complexity for smaller nodes but development on this has been pretty hard and slow.
GF estimates 7nm with DUV by H2 2018, which does kind of match with Navi's release, which I suspect would be delayed anyway: http://www.anandtech.com/show/10704/globalfoundries-updates-roadmap-7-nm-in-2h-2018
Caporegime
- Joined
- 8 Jul 2003
- Posts
- 30,063
- Location
- In a house
Im calling it now, Vega for gaming, July onwards. 
Here's a basic explanation of it and why it's a pita on NV to code for
https://www.eteknix.com/pascal-gtx-1080-async-compute-explored/
There is a lot of confusion on this subject - it is worth reading up on Kepler's 2nd DMA engine (disabled on GeForce) as that kind of leads into a better understanding of the issue and why what you are saying is both right and wrong.
There is a subtle difference a lot trip over between the two aspects of you can process both graphic and compute tasks but you can't mix graphic and compute tasks.
Last edited:
You also called Vega a 1070. What a load of ********Im calling it now, Vega for gaming, July onwards.
Note no mention of gaming in that slide.It is in same niche as Titan Xp.
I'm guessing Frontier belongs to >$500 spot on this picture.
Note no mention of gaming in that slide.
That's the Enthusiast parts, it's there in the yellow with the workstation parts.
Vega confirmed for $200 - $500
?Im calling it now, Vega for gaming, July onwards.
Release date, or on your doorstep?
- Status