Navi 21/23 Cards Rumored (aka "Nvidia Killers" xD)

[Dabombinable]

On 8/24/2019 at 1:08 PM, DrMacintosh said:

Which the *vast majority of consumers don’t use. That “industry” isn’t that big. 

*if you count Mac OS users

[Dabombinable]

22 hours ago, mr moose said:

Maybe they wouldn't do that if they considered RT cores as simply an extra processing option that greatly accelerates some workloads (just like GPGPU's are too CPU's). But that would require people to be rational and not blinkered.

This topic is taking me back to the days of HW T&L. When Nividia were the first to have it fully functional (and when we got the first proper GPU).

[Bananasplit_00]

6 hours ago, GamerDude said:

And the RTX2080 Ti isn't? I'm waiting for NAVI 23 myself, to complement my 3900X.....actually, I'm waiting for PowerColor NAVI 23 Red Devil (5900XT Red Devil if that's what it'd end up being called).  I seriously doubt that it'd cost more than an RTX2080 Ti (or an RTX3080 Ti) even if it were to incorporate HBM2E which isn't cheap.

Who said I was OK with the 2080TI price? NVIDIA is out of control

[Maticks]

42 minutes ago, Bananasplit_00 said:

Who said I was OK with the 2080TI price? NVIDIA is out of control

I don't think anyone is ok with the price they literally started selling the Ti cards at Titan pricing.

Being unchallenged in a market set of tiers though allows you to set whatever price you want.

 

Let's hope Navi delivers so we can get a reality check back to Nvidia and these prices can come down.

[Bananasplit_00]

27 minutes ago, Maticks said:

I don't think anyone is ok with the price they literally started selling the Ti cards at Titan pricing.

Being unchallenged in a market set of tiers though allows you to set whatever price you want.

 

Let's hope Navi delivers so we can get a reality check back to Nvidia and these prices can come down.

Im hoping for Intel to make a splash too, we really need high end competition now

[Trixanity]

4 hours ago, Energycore said:

I just hope these GPUs aren't massive low yield chips that leave AMD selling at a loss. Wasn't Navi supposed to bring "scalability"? If these guys are multiple chip solutions then I'm on board.

I think it's less than a year ago that AMD said chiplet GPUs weren't ready for gaming. Of course it could all be misdirection but the problem is obfuscating the chiplets from software developers to avoid scaling nightmares as well hiding latencies and scheduling work properly. If these can be solved then it should be ready for primetime but it could take years. I think we'll see chiplets in enterprise/HPC first before anything else. It should be much easier to implement assuming the workloads are insensitive to latency.

 

AMD won't be selling at a loss if they can deliver on performance and efficiency. They could just up the price to offset higher unit costs. The reason AMD's HBM offerings have been selling without profits is because they were expensive products to make but the performance wasn't there so they couldn't sell them for the price necessary to make a decent profit.

[Mihle]

4 hours ago, Energycore said:

I just hope these GPUs aren't massive low yield chips that leave AMD selling at a loss. Wasn't Navi supposed to bring "scalability"? If these guys are multiple chip solutions then I'm on board.

The main point that removed the profitability Vega 7 was the HBM from what I know. Navi wont have HBM in the consumer cards at least.

Navi wont be multiple chip in consumer cards. If I remember right, in some interviews with someone at AMD (cant quite remember) they specifically said that multiple chip GPU in gaming is not coming soon, tho it probably will for non gaming task, like servers or whatever. dont quote me tho.

 

[cj09beira]

4 hours ago, Energycore said:

I just hope these GPUs aren't massive low yield chips that leave AMD selling at a loss. Wasn't Navi supposed to bring "scalability"? If these guys are multiple chip solutions then I'm on board.

just by looking at navi gpus it shows us that what they meant by scaling, navi's shader engines and compute engines are double the width of gcn, meaning they can get 2 times the performance with the same number of shader engines, most gcn gpus have 4 shader engines navi 10 only has 2 but its still almost as fast as the maxxed out gcn architecture,

bigger navi chips should go to 4 shader engines to allow for even more performance hopefully with good scalability

18 minutes ago, Mihle said:

The main point that removed the profitability Vega 7 was the HBM from what I know. Navi wont have HBM in the consumer cards at least.

Navi wont be multiple chip in consumer cards. If I remember right, in some interviews with someone at AMD (cant quite remember) they specifically said that multiple chip GPU in gaming is not coming soon, tho it probably will for non gaming task, like servers or whatever. dont quote me tho.

 

pretty sure high end navi will have hbm, hbm's main disadvantage is cost, a good way to resolve it is to increase volume so that its not just expensive fpgas using it

[S w a t s o n]

Unless the price advantage is true AMD tier (Not likely given Ryzen 3000 pricing, but they arent ahead of Nvidia so maybe I'm wrong) I'll be buying RTX for Cyberpunk 2077, Atomic Heart, and others.

[Results45]

18 hours ago, System32.exe said:

When is the last time you've looked at benchmarks? The RTX cards are already doing 60+ FPS with ray tracing on..

Only with DLSS turned ON (or dropping the resolution scale by 20-30%):

.

[mr moose]

19 hours ago, System32.exe said:

When is the last time you've looked at benchmarks? The RTX cards are already doing 60+ FPS with ray tracing on..

How these discussions go:

 

 

Ahh, but 60FPS isn't 100FPS so I am still going to have to post shit about it.  Then when it gets to 150FPS I am still going to point out that my 240Hz monitor is not being fully utilized so it is still a shit technology.  Then when it finally can do 240FPS,  AMD will have something out so I will pontificate how it only became a usable feature when AMD pushed the market.   

 

Everything can be twisted to suit an ideal if people aren't willing to be rational.

[illegalwater]

1 hour ago, Results45 said:

Only with DLSS turned ON (or dropping the resolution scale by 20-30%):

.

Wrong.

https://www.techpowerup.com/review/metro-exodus-benchmark-performance-test/6.html

https://www.techpowerup.com/review/battlefield-v-tides-of-war-rtx-dxr-raytracing/3.html

https://www.techpowerup.com/review/shadow-of-the-tomb-raider-rtx-dlss/4.html

[Results45]

26 minutes ago, System32.exe said:

Wrong.

https://www.techpowerup.com/review/metro-exodus-benchmark-performance-test/6.html

https://www.techpowerup.com/review/battlefield-v-tides-of-war-rtx-dxr-raytracing/3.html

https://www.techpowerup.com/review/shadow-of-the-tomb-raider-rtx-dlss/4.html

 

Wasn't JayZtwocents testing it at 4K and doesn't those links verify that? But yes, if you want to get 60-100+ FPS at 1440p with only RTX on, you can (albeit 2060 only at 1080p and the 2080ti/Titan RTX at 4K).

[Maticks]

5 hours ago, mr moose said:

How these discussions go:

 

 

Ahh, but 60FPS isn't 100FPS so I am still going to have to post shit about it.  Then when it gets to 150FPS I am still going to point out that my 240Hz monitor is not being fully utilized so it is still a shit technology.  Then when it finally can do 240FPS,  AMD will have something out so I will pontificate how it only became a usable feature when AMD pushed the market.   

 

Everything can be twisted to suit an ideal if people aren't willing to be rational.

I get what you are saying here, but... there is a big difference between an 60FPS experience to 100FPS, aside from fast motion movements in competitive gaming i dont think 150-240FPS is really going to be as highly noticeable, vs 100FPS being brought down to 60FPS.

 

RTX from users experience seems to be very expensive to adopt and take a top end card and ram it into the 60FPS area, for anyone running at 150FPS on average or even 100FPS is going to see a massive difference in game experience.

Gsync only really softens the jumping FPS but when you start going under 60FPS there is nothing Gsync is going to do to make it feel not garbage.

 

[thorhammerz]

36 minutes ago, Maticks said:

RTX from users experience seems to be very expensive to adopt

Such is the price of first-gen tech: pay-to-play!

[mr moose]

37 minutes ago, Maticks said:

I get what you are saying here, but... there is a big difference between an 60FPS experience to 100FPS, aside from fast motion movements in competitive gaming i dont think 150-240FPS is really going to be as highly noticeable, vs 100FPS being brought down to 60FPS.

 

There is also a big difference in person opinion on what counts.  I am happy at 60FPS, always have been.  For some games stunning visuals trump FPS everyday for me.

 

37 minutes ago, Maticks said:

RTX from users experience seems to be very expensive to adopt and take a top end card and ram it into the 60FPS area, for anyone running at 150FPS on average or even 100FPS is going to see a massive difference in game experience.

Gsync only really softens the jumping FPS but when you start going under 60FPS there is nothing Gsync is going to do to make it feel not garbage.

 

But that is up to the each user.  Many people are more than happy to spend that much money just to be bleeding edge, some pay that much to be bleeding edge and are happy with performance. Not everyone is hellbent on 150FPS+ or nothing.

 

[Humbug]

On 8/24/2019 at 6:31 AM, Franck said:

Can they fix their driver and OpenGL issues first. I am dealing with this daily since 2012 and still nothing viable.

What applications are you using?

On 8/24/2019 at 7:05 AM, DrMacintosh said:

OpenGL is an architecture limitation. Navi is the best it’s ever been. 

On windows AMD has neglected the openGL drivers and focused on directX and Vulkan. On Mac Apple's regressive attitude does not allow AMD to provide good openGL support. So Linux is the only place where AMD has properly invested in openGL and provides good performant drivers.

 

On 8/24/2019 at 2:05 PM, MeatFeastMan said:

92CU's, GOOD LORD. That has to be water-cooled, doesn't it? And surely they're gonna have to lower clocks...even at 7nm+. If that is true though, GOODNIGHT Nvidia. The 92CU is pretty much guaranteed to destroy the 2080ti, provided Navi scales perfectly. And I'd imagine the gap between it and the 7nm 3080ti won't be too much.

Ya these GPUs will have to compete with next gen Nvidia. The target is not merely the 2080ti.

 

On 8/24/2019 at 5:51 PM, Maticks said:

I seriously doubt Navi will be able to hit RTX 2080ti speeds, but if they do it will be what 1000 Watts?

When AMD hit the numbers they usually also hit the PSU as well.

They will easily hit 2080ti performance, it's not even a question. The RDNA architecture with only 40 compute units is almost as fast as GCN based Radeon 7 which has 50% more compute units. And this is only the first iteration of RDNA which is a hybrid with GCN stuff. Even if the efficiency gains are small in the upcoming second gen RDNA parts they can lower clock speeds to keep power down since they are going wide for more performance. The real question is how it will compete with next gen Nvidia GPUs, that's the target. Nvidia will have gains too over the 2080ti.

[Humbug]

57 minutes ago, mr moose said:

There is also a big difference in person opinion on what counts.  I am happy at 60FPS, always have been.  For some games stunning visuals trump FPS everyday for me.

I always picked IPS panels over the faster TN panels for this reason. I prefer that my games look beautiful with good colours. Now that IPS and VA panels have got faster though I am ready to switch to 120/144Hz and get that fluidity without sacrificing good colours.

[Rune]

On 8/23/2019 at 8:45 PM, Results45 said:

• RX 5900XT @ 20.7 TFLOPS vs. 2 x RTX 2080ti @ 16.81-24.88 TFLOPS (FPS gains of 25%-85%)

Lel.
I'll make a wager. If this is true and Nvidia doesn't have something better by launch, I'll buy one regardless of the price.

[Humbug]

On 8/25/2019 at 11:26 AM, Energycore said:

I just hope these GPUs aren't massive low yield chips that leave AMD selling at a loss.

AMD no longer has to worry about selling at loss. Remember as shown in the below chart what has happened in the last few generations is that Nvidia has continuously escalated GPU pricing to ridiculous levels. In this environment it is much easier for AMD to also raise prices and sell at a good profit.

 

For example the Navi GPUs that have been launched are little more than Polaris replacements when you look at the number of compute units and the die size. However they are priced way higher because AMD can now choose to increase their margins too enjoying the fact that there is no price pressure from Nvidia. So they just price about USD 50-100 lower than the equivalent performance Geforce part and still enjoy the big margins. If Nvidia cuts pricing AMD too has lots of room to cut further.

 

 

With the 2080ti at more than a thousand US dollars AMD knows that the market is moving up. It would be stupid of AMD to lower prices drastically and force Nvidia down, they would rather make big margins than try to grab market share.

[AkatsukiKun]

A possible Navi 56 and Navi 48 would be good to see.

[RejZoR]

1 hour ago, Humbug said:

AMD no longer has to worry about selling at loss. Remember as shown in the below chart what has happened in the last few generations is that Nvidia has continuously escalated GPU pricing to ridiculous levels. In this environment it is much easier for AMD to also raise prices and sell at a good profit.

 

For example the Navi GPUs that have been launched are little more than Polaris replacements when you look at the number of compute units and the die size. However they are priced way higher because AMD can now choose to increase their margins too enjoying the fact that there is no price pressure from Nvidia. So they just price about USD 50-100 lower than the equivalent performance Geforce part and still enjoy the big margins. If Nvidia cuts pricing AMD too has lots of room to cut further.

 

 

With the 2080ti at more than a thousand US dollars AMD knows that the market is moving up. It would be stupid of AMD to lower prices drastically and force Nvidia down, they would rather make big margins than try to grab market share.

They'll make them cheaper. Just look at Ryzen vs Intel. But there, they are doing the price magic with chiplets. So, price drop will be smaller, but you can expect it, because even AMD knows people sort of expect that from AMD.

[LeSheen]

On 8/24/2019 at 3:58 AM, Beskamir said:

I'll believe it when I see it but so far AMD doesn't seem to have a RT or Tensor core equivalent and I doubt they'll have one when these cards come out.

I'll gladly sell my rtx2070 if amd's performance on my 3440x1440 beats nvidea.

I just want higher framerates on it without selling a kidney. Bonuspoints if there will be one in white to match my setup. RTX is not that big of an improvement visually. Let a non-gamer play a game with and without and ask if the noticed something. Chances are pretty big they only noticed some stuttering with it turned on. Especially with this first generation, nice party trick sure. Right now it wouldn't be a dealbreaker for me if a card came out without it.

[Franck]

7 hours ago, Humbug said:

What applications are you using?

I'm a developper, I deal everyday with custom CAD and non CAD 3D application's running DX and OpenGL. One example is a major issues with mouse cursor location on OpenGL with AMD cards since Radeon 7000 series and up (6000 series works #1) and all Pro card up as crap as well up to the WX series. We even shipped cards on the other side of the world to inspect them by specialist and we all add to get in contact with AMD to fix the issue and they kept refusing to answer.

 

When just swapping the video card on the system fix the issue it's very lame. There is many issues but the only fix there is are :

 

- Disable Hardware Acceleration (don't use the card but the CPU).

- Run in DirectX.

- Throw to garbage your card and buy nvidia.

 

Oh i know one app that hate AMD and that's Solidworks. If you ever have to create and work with an addin for that software you will regret getting a cheaper AMD card over a entry level Quadro

[leadeater]

3 minutes ago, Franck said:

Throw to garbage your card and buy nvidia.

Sadly, at least competition wise, this is the go to solution for anything professional and graphics. To go with AMD you either really know what your doing and know it'll work or you're unaware of what you are getting in to and will regret the purchase.

 

The only way this will ever change is getting prompt support on the issues like you had and active efforts to fix it, even if you have to wait for the next generation of cards you at least know they acknowledge the issue and are willing to work on it. Without that as a minimum why would you buy hardware you know you couldn't rely on to work or get support for.