Vega/Navi Rumors (Updated)

Page 114 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Status
Not open for further replies.

Mopetar

Diamond Member
Jan 31, 2011
8,110
6,754
136
I was under the impression the exact opposite was true. All future products are coming on GF 14nm LPP and the WSA was amended to lessen the financial blow of all the new console contracts being on TSMC's 16nm. I could be wrong but I thought the point was to increase overall fab capacity while not being penalized as much as before for needing to use another process.

The silence on Vega details is really starting to flirt with being dangerous. Some teasers would be good right about now, nothing performance related but something to tell the public waiting that Vega is coming very soon with full details to follow. Hell I'd take a 10 second snippet with a "catch us at E3!" right now.

I don't think that GF LPP is good enough for Vega. Even with the recent Polaris refresh it's pretty obvious that the process won't cut it if AMD is trying to make a competitive high-end GPU. Even with design improvements to allow it to clock higher, it would have to max out the power draw to hit the suspected clocks. AMD needs any edge they can get and I suspect that Samsung's latest generation of their process would give them some extra wiggle room. Even if GF wants to grow their process, now that AMD has a worthwhile CPU, they can actually move product and they're going to need additional capacity for their server chips and APUs that will be coming out in the near future as well.
 

tamz_msc

Diamond Member
Jan 5, 2017
3,865
3,729
136
Not sure if it there is one, sebbi made a post about how Vega is really GCN 5, but that seems to contradict what Lisa Su said about Vega being a ground up design.
It is more likely that even if Vega is a completely new design, they cannot abandon the progress they have made with GCN, just like Volta - even if it is a completely new design NVIDIA cannot abandon the perf/watt gains they have made since Fermi.
 

piesquared

Golden Member
Oct 16, 2006
1,651
473
136
I don't think that GF LPP is good enough for Vega. Even with the recent Polaris refresh it's pretty obvious that the process won't cut it if AMD is trying to make a competitive high-end GPU. Even with design improvements to allow it to clock higher, it would have to max out the power draw to hit the suspected clocks. AMD needs any edge they can get and I suspect that Samsung's latest generation of their process would give them some extra wiggle room. Even if GF wants to grow their process, now that AMD has a worthwhile CPU, they can actually move product and they're going to need additional capacity for their server chips and APUs that will be coming out in the near future as well.

We have seen GF's 14nm at 4GHz for 2 months already. Clearly there is no problem with the process hitting higher clocks, especially 3.5 and lower with very good efficiency.
 

beginner99

Diamond Member
Jun 2, 2009
5,231
1,605
136
Outside of tech forums, I don't feel Async is as desired by casual joe. At least not until it's featured in consoles.

In my case i decided I prefer blur reduction over async since sadly both is not possible at the same time. Advantage being that such a monitor is cheaper and GPU vendor agnostic.
 

tential

Diamond Member
May 13, 2008
7,348
642
121
Want some anecdote feedback from such users here. I feel I know more people with a non-Async Monitor + AMD GPU than I do FreeSync Monitor + AMD GPU users.

Hell, I'm starting to see more FreeSync monitor + NV GPU users based on my forum adventures.

Outside of tech forums, I don't feel Async is as desired by casual joe. At least not until it's featured in consoles.
All of what you said is also my findings. AMD would be best served in pushing freesync and showing "parity" between its gpus and nvidia at a lower cost point overall....
 

w3rd

Senior member
Mar 1, 2017
255
62
101
It is more likely that even if Vega is a completely new design, they cannot abandon the progress they have made with GCN, just like Volta - even if it is a completely new design NVIDIA cannot abandon the perf/watt gains they have made since Fermi.

I am just a gamer, but isn't that the point of AMD's 'Next-Generation Compute Unit', which can also do CGN on the fly..?


Hmm.. I wonder if their NCU is smart enough to mimic cuda or physx..?
 

wege12

Senior member
May 11, 2015
291
33
91
If Navi is truly the first AMD GPU built from the ground up by Raja, then I'll skip Vega. I'm okay with waiting anyways since I have a decent gpu (Fury X).

Do you guys think Navi will be able to consistently achieve 4k 60fps in AAA games?
 

mohit9206

Golden Member
Jul 2, 2013
1,381
511
136
If Navi is truly the first AMD GPU built from the ground up by Raja, then I'll skip Vega. I'm okay with waiting anyways since I have a decent gpu (Fury X).

Do you guys think Navi will be able to consistently achieve 4k 60fps in AAA games?

Yes on 1 or 2 settings below ultra.
Even your fury x can do 4k 60fps if you play on medium settings but most people have OCD that a game isn't worth playing if its not at Ultra high settings.
 

Snarf Snarf

Senior member
Feb 19, 2015
399
327
136
It is more likely that even if Vega is a completely new design, they cannot abandon the progress they have made with GCN, just like Volta - even if it is a completely new design NVIDIA cannot abandon the perf/watt gains they have made since Fermi.

This was my line of thinking, it is a huge departure from GCN but they can't abandon the strength in compute performance GCN had for the pro-segment of the market. 4 Years is plenty of time for this to be Raja's first project that was completely under his control, even if Navi is the "true" next gen, there is no way his fingerprints are not all over Vega. Those among us that think a single engineer can't change the fortunes of a company have never worked with a true visionary. Great leaders can make or break companies, and Raja is a brilliant engineer that understands what AMD needs to change to be competitive again, I just hope he had the resources to execute this generation.
 

Glo.

Diamond Member
Apr 25, 2015
5,802
4,776
136
There's no way they haven't nailed down the final marketing brands if the launches will happen when this guy says they will. These things should already be in volume production.
Or maybe he was not informed about the marketing names?
 

swilli89

Golden Member
Mar 23, 2010
1,558
1,181
136
Or maybe he was not informed about the marketing names?
Maybe its just a random dude on the internet posting a completely unsubstantiated "leak" with uncompetitive pricing and stupid names. Calling it fake is doing it too much justice as its not even a rumor, just a pointless clickbait post someone either trolling or desperate for internet points.
 

Glo.

Diamond Member
Apr 25, 2015
5,802
4,776
136
Maybe its just a random dude on the internet posting a completely unsubstantiated "leak" with uncompetitive pricing and stupid names. Calling it fake is doing it too much justice as its not even a rumor, just a pointless clickbait post someone either trolling or desperate for internet points.
You may have a point, however I think that AMD marketing team right now looks like this:

https://twitter.com/_youhadonejob1/status/862250826592641024
 

Snarf Snarf

Senior member
Feb 19, 2015
399
327
136
Those names are so bad this could honestly be true lol.

The alternative was "Dwarf" "Super" "Hyper" based on the Hertzsprung–Russell diagram which the engineers were in favor of but marketing department not so much.

This little bit right here is what makes me think this isn't total BS. We know for a fact that AMD's engineers love to make up silly code names based on random science things, like the capsaicin thing, Vega, Polaris etc. Also that pricing isn't noncompetitive, it's basically what Nvidia is asking for their performance tiers minus the 1080ti being almost $150 below aftermarket MSRP. Ultimately I give it a 6/10 effort-wise, probably false but entertaining enough.
 

swilli89

Golden Member
Mar 23, 2010
1,558
1,181
136
Those names are so bad this could honestly be true lol.



This little bit right here is what makes me think this isn't total BS. We know for a fact that AMD's engineers love to make up silly code names based on random science things, like the capsaicin thing, Vega, Polaris etc. Also that pricing isn't noncompetitive, it's basically what Nvidia is asking for their performance tiers minus the 1080ti being almost $150 below aftermarket MSRP. Ultimately I give it a 6/10 effort-wise, probably false but entertaining enough.
The two lower tiers were absolutely uncompetitive pricing where yes the 1080ti equivalent pricing would be excellent.
 
Mar 10, 2006
11,715
2,012
126
Please note: The RX Vega subnames were still being finalized by the boardroom at the time so they may have changed by now.

Haha! "Boardroom" -- yes, the board of directors is "finalizing" the names. LOL, this is so fake.
 

DDH

Member
May 30, 2015
168
168
111
Im more inclined to believe this than any other of the rumors. My first thought was a controlled leak. We'll find out in a few weeks
 

Paratus

Lifer
Jun 4, 2004
17,123
14,491
146
M
or it's a common euphemism for executives in committee.

as a happily whipped man I may use the word committee in the following way.

"I'd like to request the committee to approve my purchase of a Vega 10.

Thank you dear. "

 
Status
Not open for further replies.
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |