Question 'Ampere'/Next-gen gaming uarch speculation thread

Page 12 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Ottonomous

Senior member
May 15, 2014
559
292
136
How much is the Samsung 7nm EUV process expected to provide in terms of gains?
How will the RTX components be scaled/developed?
Any major architectural enhancements expected?
Will VRAM be bumped to 16/12/12 for the top three?
Will there be further fragmentation in the lineup? (Keeping turing at cheaper prices, while offering 'beefed up RTX' options at the top?)
Will the top card be capable of >4K60, at least 90?
Would Nvidia ever consider an HBM implementation in the gaming lineup?
Will Nvidia introduce new proprietary technologies again?

Sorry if imprudent/uncalled for, just interested in the forum member's thoughts.
 

lobz

Platinum Member
Feb 10, 2017
2,057
2,856
136
I'll add a few,
Big navi will be as fast as a 3070, use 35% more power ,and need a price drop to compete.
Nobody knows how big Navi performs, much less how efficient will RDNA2 be. Yet you alrady seem to know that it will be as fast and use more power than an even less known, previously unheard of GPU, which may or may not be even decided at a final design or market position level. With that you claim to have more information than most NVIDIA engineers themselves, who have worked on the next generation architecture (still remains to be seen if it will in fact be Ampere).

This thread quickly turned from speculation to pointless bragging over who claims to be more in the know, with each post looking more and more ridiculous.
 
Reactions: Elfear

lobz

Platinum Member
Feb 10, 2017
2,057
2,856
136
So, just as a point of order, IHVs don’t just 're-tape' an chip. They have to redesign to the according to the rules of the new PDK for the new process and then tape-out the new chip. Now a days, I’d think almost all that work would be done by computer, but the company would also spend allot of time redoing sims for verification.
The part of designing new changes are being much more reliable than in the past is totally correct. You will, however always have to tape them out after you are satisfied with the simulations. But thankfully it's way ahead of F1 for example, where the wind tunnel simulations can still be very unreliable and misleading - the nature of aerodynamics is a bit more cruel.
 

lobz

Platinum Member
Feb 10, 2017
2,057
2,856
136
Says the guys whose only source is some moron on Twitter, great evidence indeed, but you are still wrong

HAHAHAHAHA, some heads will roll for sure, you guys are pathetically funny ..
You're not a very pleasant person to have a conversation with, are you?
 

Glo.

Diamond Member
Apr 25, 2015
5,761
4,666
136
Certainly less stupid than the people who said Navi was going to be 200-250 dollars with rtx 2080 performance while taking into account the cost of 7nms.


Nvidia does not need to use the rumor mill and a guerrilla marketing plan like AMD.

If anything, it is in Nvidia's best interest to prevent leaks unlike AMD because they have an entire lineup of cards selling well and any news of a new card on the horizon is detrimental to their sales and devalues their current inventory. They are not in the same situation as AMD which uses leaks, fake leaks and a misinformation campaign to their advantage. This is clear if you look at the length of bread crumbs leading up to any AMD release.

AMD has used guerrilla marketing and the rumor mill for years because since Maxwell AMD has been late to launch card compared to Nvidia. Haven't you noticed that with every AMD card launch, there is a very aggressive rumor marketing campaign that are designed to hype up AMD's next release well well before launch and these are timed right after Nvidia launches their cards. Why is this the case?

This is to stall sales of Nvidia cards and to put the blame of any hype and misinformation on the rumor sites and on forum posters.

Nvidia controls and prevents leaks from occurring because leaks are detrimental when your cards are selling well. On the other hand if your cards are not selling well and only your competitors have new cards on the market, it can help stall your competitors sales, particularly if these rumors are placed on cards which your existing cards don't compete in. i.e the high end for AMD(fiji, Vega and somewhat Navi).

The point I am trying to make is we cannot base Nvidia release dates based on rumors because Nvidia is very good at controlling rumors until the launch date is near. Similarly, you can't predict the launches of AMD based on rumors because the rumors are not designed with any real information to give an accurate gauge of performance. They are designed to get people to wait as long as AMD needs to get their cards out.
Riiight. You say that AMD has guerilla marketing, but you do not see the hype that is created right now for upcoming Nvidia GPUs?

What was it? 50% faster while consuming 50% less power? Q2 2020 release for whole next gen lineup?

Have you ever considered the fact that this is exactly the thing that Nvidia does, that you accuse AMD of doing?

Why would they do it, you may ask?

Maybe because Samsung's process failed, and because of it, they are one year late to the party, and need to keep interest in their products, because so far, even without halo product, AMD has been outplaying them, which RX 5600 XT is the best example of? Maybe because they have nothing for time being to counter AMD upcoming products?

Everything has been laid out by people who know. Again, its up to you guys to cope with reality.

There will be new GPUs from Nvidia this year. But there are only two possibilities. RTX 2080 Ti Super, or GA100 based Titan A, with eye watering price.
 
Last edited:
Reactions: JPB

lobz

Platinum Member
Feb 10, 2017
2,057
2,856
136
That is simple manipulation tactic. Everybody who ever have read any book about manipulation will know this thought pattern.
Seeing how we both manipulated you into writing this comment, you may be right.

Joking aside, yes, and I think it has to be commented on calmly. UNDERSTOOD?????!!! Also, the more arrogant the tactic is, the better it feels to watch it fail
 

Glo.

Diamond Member
Apr 25, 2015
5,761
4,666
136
Seeing how we both manipulated you into writing this comment, you may be right.

Joking aside, yes, and I think it has to be commented on calmly. UNDERSTOOD?????!!! Also, the more arrogant the tactic is, the better it feels to watch it fail
The best way is to simply ignore those jabs.
 
Reactions: JPB

insertcarehere

Senior member
Jan 17, 2013
639
607
136
The funniest part is that you assume that only Komachi and Kopite have sources.

Kopite Account hasn't been suspended. He has Nvidia sources, whether you LIKE IT or not. If he says that next gen. Gaming GPUs have not been taped out, yet - it means they have not been taped out. If he says that There is no Samsung 8 nm, and GA103 and GA104 chips, and that GA100 is TSMC 7 nm - it is true.

When he posted actual insider information about Nvidia, he has never before been incorrect.

Deal with it guys. Its up to you to cope with reality.

Extraordinary claims require extraordinary evidence, unless you can prove that statement with a long list of track records it would be wise to stop shouting down anyone who thinks otherwise.
 

beginner99

Diamond Member
Jun 2, 2009
5,223
1,598
136
Yeah, and AMD and Sony and Microsoft are creating RT cores for the same reason too! do you hear yourself talking mate?

It's for the marketing checkbox and it's not clear if AMD even adds dedicated hardware for this. Same marketing BS like current consoles can do 4k. Right yeah...with up scaling from 720p at 30 fps....
 

Glo.

Diamond Member
Apr 25, 2015
5,761
4,666
136
Extraordinary claims require extraordinary evidence, unless you can prove that statement with a long list of track records it would be wise to stop shouting down anyone who thinks otherwise.
Start following him, then. His Twitter does not require more evidence than itself.
 

Ajay

Lifer
Jan 8, 2001
16,094
8,104
136
The part of designing new changes are being much more reliable than in the past is totally correct. You will, however always have to tape them out after you are satisfied with the simulations. But thankfully it's way ahead of F1 for example, where the wind tunnel simulations can still be very unreliable and misleading - the nature of aerodynamics is a bit more cruel.
Wasn't talking about new features, but the move from Samsung to TSMC, if, in fact, that is what happened. For large companies, don’t know about small, extensive simulations generally mean that the A0 stepping is good to go (with some firmware fixes and errata).
 
Reactions: lobz

lobz

Platinum Member
Feb 10, 2017
2,057
2,856
136
The man, the legend, good ol Moonbogg. He kept his end of the bargain.

The good old days...I miss thee
That was really epic. Back in the day I was just reading and laughing a lot And of course crying a lot, when I had to observe your fights with The Windmill, The Strongman himself
 

Saylick

Diamond Member
Sep 10, 2012
3,385
7,149
136

SteveGrabowski

Diamond Member
Oct 20, 2014
7,117
5,994
136

Amol S.

Platinum Member
Mar 14, 2015
2,397
709
136
I only get a new laptop with descrete GPU when the laptop dies, just dumb to buy a new laptop when the GPU still works.

On a side note, NVIDIA only stated Ampre, 7nm, and Samsung and that is it, unless New York Times or Forbes comes out with an article saying more info, thats the only info we know about the Ampre that is confirmed.
 

Adonisds

Member
Oct 27, 2019
98
33
51

Next-generation NVIDIA GPU in a supercomputer to be delivered this summer. It is allegedly 75% faster (at something) than current generation (Volta).
Just a very quick and simple estimation:
Taking the average of the die sizes of GTX 680 and GTX 1080, the last GPUs on a new node, you get 304 mm2.

If RTX 3080 is 304 mm^2 in standard TSMC 7nm, that should be around the same number of transistors as a 912 mm^2 die in the previous node (I couldn't find an exact density increase data, should be about 3x).

That's 67% more transistors than RTX 2080. So 75% more powerful seems plausible.

Anyone with better estimations?
 
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/    |