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

Page 76 - 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.
 

Stuka87

Diamond Member
Dec 10, 2010
6,240
2,559
136
Now, that is a surprise. The AIB will love it, but what made Nvidia change their minds? AIB backlash? But after 4 years of F's Editions why show AIB some love now?

Maybe they know something about RDNA2, or want to pre-empty the new consoles? Or has Zen given AMD better a relationship with Taiwanese OEMs as most AIBs also make motherboards, and Nvidia fear this?

Anyway, good news for buyers.


Sorry, but I keep seeing this mistake being made in far too many places. PSU efficiency does not work that way:
1000W PSU can output 1000W. If it is 80% efficient it would draw 1250W (1000 / 0.8) leaving it to get rid of 250W of waste heat somehow (noisy).
A more realistic 90% efficient PSU would draw 1111W leaving it get rid of 111W of waste heat.

He said 90% load. You never ever want to run a PSU at 100% load. Typically 80% is the max you want, but its not uncommon to see 90% on devices with a fixed power draw.

As for efficiency, its not always the case of drawing more at the wall. I have seen PSU's wall to output ratio vary depending on the load being applied. This is with using a power analyzer to measure both.
 
Reactions: Konan

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
He said 90% load. You never ever want to run a PSU at 100% load. Typically 80% is the max you want, but its not uncommon to see 90% on devices with a fixed power draw.

As for efficiency, its not always the case of drawing more at the wall. I have seen PSU's wall to output ratio vary depending on the load being applied. This is with using a power analyzer to measure both.

That is normal, all PSUs have a efficiency to load curve. Like the one bellow.

 

GodisanAtheist

Diamond Member
Nov 16, 2006
7,058
7,478
136
We don't actually know die sizes. I would expect them to be of similar size. The smaller node just lets them get more onto that size die.

- I think this is what we're going to see. Unfortunately Turing dies were so large that even a straight shrink would still result in historically large dies at each tier. Wonder if were going to see a more Maxwell-esq 600/400/200mm2 breakdown this time around.

You get a shrink, you get to pack some more stuff on, you still have room for 750mm2 monster die refresh...
 
Reactions: Stuka87

MrTeal

Diamond Member
Dec 7, 2003
3,584
1,743
136
He said 90% load. You never ever want to run a PSU at 100% load. Typically 80% is the max you want, but its not uncommon to see 90% on devices with a fixed power draw.

As for efficiency, its not always the case of drawing more at the wall. I have seen PSU's wall to output ratio vary depending on the load being applied. This is with using a power analyzer to measure both.
He actually did both, he used 258W * 0.9 (load) * 0.9 (eff) to arrive at the 208W number. Still, it's not a huge difference either way since the assumptions likely have way more variability in them than the 10%. If you really want to talk SoC draw, you're still going to have another loss getting down to ~1V and so there will be another factor in there anyway. You'd usually ignore that for making a comparison to a GPU though, as we're usually looking at card draw @ 12V there.
 
Reactions: Stuka87

raghu78

Diamond Member
Aug 23, 2012
4,093
1,475
136
Sorry, but I keep seeing this mistake being made in far too many places. PSU efficiency does not work that way:
1000W PSU can output 1000W. If it is 80% efficient it would draw 1250W (1000 / 0.8) leaving it to get rid of 250W of waste heat somehow (noisy).
A more realistic 90% efficient PSU would draw 1111W leaving it get rid of 111W of waste heat.

Thanks for the correction.
 

BenSkywalker

Diamond Member
Oct 9, 1999
9,140
67
91
But your 20% faster is a typical red-herring you choose randomly so you can claim you're right.

"NVidia killer"

I don't work for AMD, so I'm not sure why you think I made that claim. They did not call it nVidia competitor or nVidia beater, they call it a nVidia killer, but you think being competitive somehow makes it a killer? Really?

I think 20% is a very low bar for a "killer".
 

Det0x

Golden Member
Sep 11, 2014
1,055
3,087
136
"NVidia killer"

I don't work for AMD, so I'm not sure why you think I made that claim. They did not call it nVidia competitor or nVidia beater, they call it a nVidia killer, but you think being competitive somehow makes it a killer? Really?

I think 20% is a very low bar for a "killer".

Can you please tell/link me where AMD called it anything other then "big NAVI" or "NAVI 2X" ?
No you cant, because they never said anything of the sorts. Please stop making up stuff to fit your narrative.

The "nvidia killer" comes from "leakers" on Youtube, not AMD.
I think the first one to mention it was redgamingtech where he said he had heard "rumours" about a "NAVI23" which was the "nv killer", where he in later videos clarified it was in regards to performance/price, not absolute performance
 
Last edited:
Reactions: Gideon and Glo.

Glo.

Diamond Member
Apr 25, 2015
5,761
4,666
136
Can you please tell/link me where AMD called it anything other then "big NAVI" or "NAVI 2X" ?
No you cant, because they never said anything of the sorts. Please stop making up stuff to fit your narrative.

The "nvidia killer" comes from "leakers" on Youtube, think the first one to mention it was redgamingtech.
Paul from RedGamingTech claimed that his sources told him, that "Nvidia Killer" Exists, and it is ... Navi 23.

Sub 300 mm2 die. Not the Big Navi.
 
Reactions: Konan

nurturedhate

Golden Member
Aug 27, 2011
1,761
757
136
That wasn't a full node drop and the 200mm part was $249 in "full" mode- also, I don't recall people being overly excited about the non Ti when it came out and the launch MSRP of the 1080 was $600(still was a bad deal). To be fair, in retrospect every card that generation was wildly under priced due to the mining boom.

This generation should be interesting, with AMD having, at the bare minimum, a 20% performance lead from top to bottom(nVidia killer) it should be interesting to see where prices land.
"NVidia killer"

I don't work for AMD, so I'm not sure why you think I made that claim. They did not call it nVidia competitor or nVidia beater, they call it a nVidia killer, but you think being competitive somehow makes it a killer? Really?

I think 20% is a very low bar for a "killer".
Low bar indeed.
 

nurturedhate

Golden Member
Aug 27, 2011
1,761
757
136
Low bar indeed.
When hyperbolic fans claim 5-10% is demolish, what can we think of as a killer?
Apologies Maddie, I was not talking about the difference in performance between upcoming Nvidia and AMD releases. What would I consider a killer though, nothing really otherwise I'd be one of those hyperbolic fans. Could simplify things and say a killer would be whatever I spend my money on. Honestly? I kinda hope Nvidia's cards are power hungry just so we get post after post about how power efficiency never mattered in the first place.
 

DooKey

Golden Member
Nov 9, 2005
1,811
458
136
Apologies Maddie, I was not talking about the difference in performance between upcoming Nvidia and AMD releases. What would I consider a killer though, nothing really otherwise I'd be one of those hyperbolic fans. Could simplify things and say a killer would be whatever I spend my money on. Honestly? I kinda hope Nvidia's cards are power hungry just so we get post after post about how power efficiency never mattered in the first place.

Power efficiency doesn't matter if it's performance mirrors that power usage.
 

Hitman928

Diamond Member
Apr 15, 2012
5,593
8,770
136
Power efficiency doesn't matter if it's performance mirrors that power usage.

This statement doesn't make sense. Power efficiency is performance / power so you are basically saying power efficiency doesn't matter if the power efficiency is good. Perhaps you meant to say power usage doesn't matter if the performance is high enough but then that just returns us full circle to power efficiency being important.
 
Reactions: maddie and Campy

DXDiag

Member
Nov 12, 2017
165
121
116
NVIDIA being so aggressive in marketing Ampere is due to one thing: they are conifident they will win this round hands down through a combination of: superior RT performance, DLSS 2 and superior rasterization performance.
 
Reactions: DooKey

DooKey

Golden Member
Nov 9, 2005
1,811
458
136
This statement doesn't make sense. Power efficiency is performance / power so you are basically saying power efficiency doesn't matter if the power efficiency is good. Perhaps you meant to say power usage doesn't matter if the performance is high enough but then that just returns us full circle to power efficiency being important.

I mean if a card has the highest power draw but is the fastest card available then efficiency doesn't matter to me. I buy highest end cards and don't worry about power.
 
Reactions: pcp7

BenSkywalker

Diamond Member
Oct 9, 1999
9,140
67
91

If anyone else claims I made that up I will link a hundred or so sites calling it that before I ever mentioned the term.

One anonymous tweet says Samsung 8nm and you all treat it as the holy grail, hundreds of references to " nVidia killer" and I must've made it up.... Y'all getting desperate.
 

Stuka87

Diamond Member
Dec 10, 2010
6,240
2,559
136
NVIDIA being so aggressive in marketing Ampere is due to one thing: they are conifident they will win this round hands down through a combination of: superior RT performance, DLSS 2 and superior rasterization performance.

You forgot the /s at the end of your post.

Literally anybody that is in marketing would say the exact opposite. Its the reason bad movies have twice the marketing of amazing movies. That doesn't mean nVidia won't come out on top, but when competition increases, marketing equally increases.
 
Reactions: Glo.

BFG10K

Lifer
Aug 14, 2000
22,709
2,979
126
If you have to go all the way back to Athlon 64 to find CPU leadership for AMD then why did you miss the Radeon 9700 Pro (R300) and its successor Radeon 9800 Pro/ Radeon 9800 XT (RV350).
Huh? Your original question was Did AMD have a counter to Intel before Zen, which I answered.

So do not make it look like AMD were more competitive against Intel in CPUs than they were against Nvidia in GPUs.
What are you babbling about? I never made nor implied such a claim. I answered your Intel comparison question and pointed out Intel stagnating whenever AMD wasn't competitive on the CPU front.

This is not a leaked spec.
Yes it is. Until we see real benchmarks of real hardware running real games, it may as well be fiction.

If you saw the Series X teardown video you would have seen the PSU rating. Do the math and you will see the Series X is delivering 12 TF at 140-150w compared to Radeon 5700XT's 9 TF at 225w. Thats 2x the perf/watt.
Absolutely meaningless. "Doing the math" tells you nothing about the real world. We saw this with the failure that was Vega.

Perf/mm2, perf/watt, FLOPS, etc are all worthless marketing garbage. The only thing that matters is how the card actually behaves when tested with real games, and how much it costs.

Anyway in a couple of months AMD is likely to launch RDNA2. So you can bookmark all these posts and revisit.
Oh absolutely, I will. Just like revisiting the posts telling us Mantle was going to "kill" DX11 and allow AMD to dominate Android. Or when nVidia was "doomed" because they didn't have full async capability. Or that other time when CUDA was a "dead end" because it was proprietary.

This forum has a history of fictional delusion that doesn't reflect reality, and I've lost count how many times nVidia was "doomed".

Today's reality shows nVidia with record discrete GPU market share, record profits, and four GPUs that AMD can't touch for performance, which lets nVidia overprice them as they please. That's the danger of delusion instead of competition.

Nvidia might have made a strategic blunder by betting on Samsung 8nm instead of TSMC 7nm and they are like to pay for that mistake.
It's true that I'm expecting an overpriced furnace from Ampere, but I also expect the top 1-2 parts to be faster than anything from AMD. And that's a problem because once again it lets nVidia dictate pricing on their terms.
 
Reactions: Martimus

arandomguy

Senior member
Sep 3, 2013
556
183
116
Now, that is a surprise. The AIB will love it, but what made Nvidia change their minds? AIB backlash? But after 4 years of F's Editions why show AIB some love now?

I think people are reading too much into things.

Techpowerup as an example had multiple RTX 2080/ti AiB cards reviewed alongside the FE cards at launch - https://www.techpowerup.com/review/msi-geforce-rtx-2080-ti-duke/36.html

It was really only the GTX 1080/1070 that had a real delay for AiB cards and that was when the term FE was first introduced. Prior to that, and even still now, it was always just somewhat expected that initial cards were from either Nvidia or AMD with customs coming afterwards.

If anything the real concern at the moment is still supply chain disruption and potential further impacts from Covid19. While chip production itself is not an issue (other than demand possibly outpacing supply) there is still ongoing issues with respect to everything else that goes into making the end graphics card as well as shipping issues. As such you'd want to hedge by having partners going full bore ASAP to navigate the issues and beat any potential future disruptions (2nd wave). 2nd wave Covid disruptions would be a more devastating in terms of business impact then any competitor issue, the latter of which I've always felt enthusiasts tend to overstate the impact of (eg. how much sales are impacted because a product reviews somewhat better, enthusiasts tend to think it should result in a massive market and mindshare swing, but that is never the reality).

Not to mention without trade show commitments and etc. this year the logistics of any launch is going to be rather different.

As for everyone reading into the marketing, is this launch really all that different? Covid19 has disrupted the possibility of going with a more traditional launch event so I guess you'll see more of an online and social media approach to marketing (which in general over time has been gaining preferences over the more traditional tech media focused marketing). Pascal from what I remember had a similar cryptic (or even more) ARG campaign leading to it's launch. Or what about this hype Twitter post? -
Maxwell and Pascal had dedicated events that tech media was flown out to launch. Turing was launched with Gamescom and SIGGRAPH, with the latter being a stronger focus in which Nvidia was keynote due to the benefits of the ray tracing hardware for rendering/content creation workflow.

So somehow this online campaign, in large part due to circumstance, is really all that different?

In general I feel people read too much into past trends as well. There is really a sample size issue with respect to using the past to predict going forward. Both Nvidia and AMD change up a lot of how each launch goes, so people should not overly rely on past launches in terms of execution to predict what the next one looks like. Just looking at Nvidia they've done large branding changes for the past 2 launches already, who's to say the Ampere lineup gets named completely outside expectations as well?
 

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
It's true that I'm expecting an overpriced furnace from Ampere, but I also expect the top 1-2 parts to be faster than anything from AMD. And that's a problem because once again it lets nVidia dictate pricing on their terms.

They will dictate pricing only if AMD is not competitive in all segments not because NVIDIA will have 1 or 2 top parts on the top.
What if AMD has faster cards on all of the lower segments bellow those 1-2 parts ???
 

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
My prediction, AMD will compete up to RTX3080, that is the reason NV using A102 for RTX3080 this time.

Im expecting something similar to RTX2060 Super vs RX5700XT in price/perf across all the line of GPUs up to RTX3080.
NV will still have the 3080Ti unchallenged again but this time the competition will not stop at the $400 mark.
 

BenSkywalker

Diamond Member
Oct 9, 1999
9,140
67
91
They will dictate pricing only if AMD is not competitive in all segments not because NVIDIA will have 1 or 2 top parts on the top.

That isn't how it ends up working though. If nVidia has a $1500 card up top, and a $1k card second and then their third card is $700- AMD might launch at $650(if that's where they are competitive). If nVidia launches at $1k, $750 and $600 AMD won't be launching at $650.

NVidia does dictate pricing, between launching first and owning the top tiers, they set the market.

To be completely fair, inflated prices from nVidia helps AMD a lot more then just letting them sell more, what if the 2080Ti was $700, 80S $500, 70S $350 and the 60S $249- what would that have done to AMD's margins?
 
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/    |