AMD Planning September Launch for Radeon RX 7800 series and RX 7700 series

[AnotherReader]

30% clock speed increase doesn't mean 30% performance increase, there's more to it, at most it will be 20-25%. There are tests already "emulating" the 7800xt out there, we are seeing a moderate boost of 8-10% over the 6800xt, which also seems to be about 20% faster than the 6800. Thou that was emulated using a wx7800 (navi31).

You're right. A 30% increase in clocks wouldn't result in a 30% performance increase in most tests. It would be dependent upon the game as well. Still, a 30% faster clock would mean about 15% higher clocks over the current norm and that isn't insignificant.

 

[Chrispy_]

Average clock from reviews is already 300mhz over that? More unconfirmed bs about bad silicon.

Unconfirmed BS? The source is AMD themselves - both Frank Azor and Sam Naffziger.

Board manufacturers are happy to make gigantic cards with higher TDPs and higher clocks, but the original plan for Navi31 was 3GHz at 300-350W, and that never happened. That doesn't make Navi31 a bad product, or bad silicon, only that AMD didn't reach their original goals due to unforseen design issues. Sam talked about delaying Navi32 to apply the lessons they'd learned from Navi31. I'm simply wondering whether they actually took that path or not. Talking about it in an interview doesn't make it a reality and AMD have been pretty quiet about it publicly since then.

If Navi32 is respun silicon and it's more efficient and faster, you can guarantee they'll charge more for it.
If Navi32 is the original silicon design taped-out shortly after Navi31 launched, then it'll be a bit slower and hotter, but cheaper to buy.

I don't really see a downside with either outcome; Faster/more efficient silicon would be nice, but MCD is never going to be as power-efficient as monolithic so it's unlikely to match the Nvidia 40-series either way, rending it a moot point not worth discussion.

 

[rv8000]

Doesn't hit that frequency in almost all games. Just for reference, I know my 4090 hits 3045-3060 under extreme low loads but it usually stays at 2865-2910 in most games. It should be same for AMD afaik. If I increase the PL, I am pretty sure I can hit higher frequency as I am still at stock now. 7900xtx hitting 3ghz seems totally plausible, but I don't think it stays there for most games if u know what I mean.

It really doesn’t take much to get it to sit at 3ghz on average, and will definitely stay there for the majority of games. There are exceptions, but they’re the minority, most notably CP2077 with RT. There’s a user on OCN reporting 3000-3100 @411w with RT and FSR at 4K, simply takes juice and most games aren’t like that.

Id check personally but PC is in pieces until noctua offset mount comes in tonight; nitro typically hovers around low 2900s stock and I’ve got it FPS capped to 240.

Unconfirmed BS? The source is AMD themselves - both Frank Azor and Sam Naffziger.

Board manufacturers are happy to make gigantic cards with higher TDPs and higher clocks, but the original plan for Navi31 was 3GHz at 300-350W, and that never happened. That doesn't make Navi31 a bad product, or bad silicon, only that AMD didn't reach their original goals due to unforseen design issues. Sam talked about delaying Navi32 to apply the lessons they'd learned from Navi31. I'm simply wondering whether they actually took that path or not. Talking about it in an interview doesn't make it a reality and AMD have been pretty quiet about it publicly since then.

If Navi32 is respun silicon and it's more efficient and faster, you can guarantee they'll charge more for it.
If Navi32 is the original silicon design taped-out shortly after Navi31 launched, then it'll be a bit slower and hotter, but cheaper to buy.

I don't really see a downside with either outcome; Faster/more efficient silicon would be nice, but MCD is never going to be as power-efficient as monolithic so it's unlikely to match the Nvidia 40-series either way, rending it a moot point not worth discussion.

Where do they say the limit is “2500mhz”. I’ll wait.

 

[Chrispy_]

It really doesn’t take much to get it to sit at 3ghz on average, and will definitely stay there for the majority of games. There are exceptions, but they’re the minority, most notably CP2077 with RT. There’s a user on OCN reporting 3000-3100 @411w with RT and FSR at 4K, simply takes juice and most games aren’t like that.

Id check personally but PC is in pieces until noctua offset mount comes in tonight; nitro typically hovers around low 2900s stock and I’ve got it FPS capped to 240.



Where do they say the limit is “2500mhz”. I’ll wait.

That's the boost clock of the reference 7900XTX, as quoted by AMD themselves, Techpowerup's GPU database, and Wikipedia.

Other clock speeds and TDPs are available for any SKU, whether that's Nvidia, AMD or Intel. Whether that's a partner model with beefed-up cooling and power delivery, or someone pushing a manual overclock/undervolt on a reference card - but that's irrelevant.

When comparing GPUs - especially speculating against pre-launch models, the reference clocks are the defining standard. It's why most reviews (even those that test overclocked performance) always show reference clocked results too. That's what you're paying for, and that's what you're guaranteed to get.

If someone takes a 1001 horsepower Buggatti Veyron and tunes it to 1500 horsepower, that doesn't meant that all Veyrons now make 1500 horsepower. The original Veyrons are all still limited to 1001hp until they, too, are individually modified. Such is the way for "stock" GPUs; They run at stock until modified. The default TDP and clock limits in the driver and BIOS of the original 7900XTX doesn't allow it get anywhere near 3GHz, and whilst the 2500MHz reference clock is likely a lower estimate of what typical cards will opportunistically boost to, it cannot possibly be a shocking new revelation to you.

Take an AMD/Intel CPU for example. They are sold as "up to 5 GHz boost clock" and if you're lucky it might slightly exceed that by a few percent at stock settings based on silicon lottery, but it's not magically going to boost to 6GHz without some pretty extreme tinkering and modification to power limits, cooling, BIOS etc.

 

[rv8000]

Do we know if this coming Navi32 is the cited respin with hardware fixes to tackle the clocking artifacts, or is this just the original silicon run that's limited to ~2.5GHz?

That's the boost clock of the reference 7900XTX, as quoted by AMD themselves, Techpowerup's GPU database, and Wikipedia.

Other clockspeeds and TDPs are available for any SKU, whether that's Nvidia, AMD or Intel, but when comparing GPUs - especially launch models, the reference clocks are the defining standard for that model.

Default boost behavior of the reference card exceeds that on average and at max; that doesn’t even take into account the issues with the reference cooler and it’s limits.

Navi in any form is by no means limited to 2500mhz; if you want to hide behind marketing lingo that doesn’t match reality, be my guest. Clocking artifacts and bad silicon? 2.5ghz limits? They didn’t knock it outta the park and they definitely didn’t hit efficiency targets, but your claims have zero proof.

 

[Chrispy_]

I really hope so, if it is the original silicon design, then why the hell is it so late? Hopefully they've solved all the nagging issues as well, and it will have good drivers from day one. Well, maybe good launch drivers is asking too much, it would be a nice change. It's a bit tedious that it takes them a few months more to work out all the minor driver issues every single launch.

IIRC Navi32 was always supposed to be the last GPU in the 7000-series family. Even last year before Navi31 launched, Navi32 was 2H23 on AMD's roadmap

View attachment 305224

Default boost behavior of the reference card exceeds that on average and at max; that doesn’t even take into account the issues with the reference cooler and it’s limits.

Navi in any form is by no means limited to 2500mhz; if you want to hide behind marketing lingo that doesn’t match reality, be my guest. Clocking artifacts and bad silicon? 2.5ghz limits? They didn’t knock it outta the park and they definitely didn’t hit efficiency targets, but your claims have zero proof.

Average boost clock is 2612MHz, that's a long way off the 3GHz they were aiming for, and lot closer to the 2500MHz boost clock advertised.

I think you think I'm arguing something I'm not.
I don't know what you think I'm arguing but I thought I'd made it pretty clear that I'm just citing AMD themselves.
I don't need to defend my opinion because I've not provided one, other than being pleased Navi32 is on the way; If you have issues with what AMD have said in the past, take it up with them, not me.

 

[rv8000]

That's the boost clock of the reference 7900XTX, as quoted by AMD themselves, Techpowerup's GPU database, and Wikipedia.

Other clock speeds and TDPs are available for any SKU, whether that's Nvidia, AMD or Intel. Whether that's a partner model with beefed-up cooling and power delivery, or someone pushing a manual overclock/undervolt on a reference card - but that's irrelevant.

When comparing GPUs - especially speculating against pre-launch models, the reference clocks are the defining standard. It's why most reviews (even those that test overclocked performance) always show reference clocked results too. That's what you're paying for, and that's what you're guaranteed to get.

If someone takes a 1001 horsepower Buggatti Veyron and tunes it to 1500 horsepower, that doesn't meant that all Veyrons now make 1500 horsepower. The original Veyrons are all still limited to 1001hp until they, too, are individually modified. Such is the way for "stock" GPUs; They run at stock until modified. The default TDP and clock limits in the driver and BIOS of the original 7900XTX doesn't allow it get anywhere near 3GHz, and whilst the 2500MHz reference clock is likely a lower estimate of what typical cards will opportunistically boost to, it cannot possibly be a shocking new revelation to you.

Take an AMD/Intel CPU for example. They are sold as "up to 5 GHz boost clock" and if you're lucky it might slightly exceed that by a few percent at stock settings based on silicon lottery, but it's not magically going to boost to 6GHz without some pretty extreme tinkering and modification to power limits, cooling, BIOS etc.

Citing marketing material has nothing to do what you said. You flat out said there were silicon level issues causing artifacting and limiting Navi clock speeds to 2500.

Not only does the reference model exceed that on average by 100mhz and peak 500 mhz, every single AIB model with adequate cooling and does so significantly; not to mention when allowed to draw 450w+ Navi 31 will clock in excess of 3100-3200.

Where is this magical bad silicon limiting clock speeds to 2500 and causing artifacting? All I see is a missed efficieny target.

 

[Imouto]

Citing marketing material has nothing to do what you said. You flat out said there were silicon level issues causing artifacting and limiting Navi clock speeds to 2500.

You can't make him acknowledge that he said what he said. He will tire you out, make you waste your time until you die of old age and then slip through one of your nostrils to eat your carcass inside out.

 

[Macro Device]

7700+7700 PC will be possible

Are AMD A10-7700K, Intel Core i7-7700K, and AMD Radeon HD 7700 Series jokes for you?

Navi in any form is by no means limited to 2500mhz

But they still can limit either RX 7700 or 7800 (or even both) to 2500 MHz for whatever reason, be it competition with other their cards or target TGP, or whatnot. This limit would be implemented via BIOS/straps shenanigans and not by the architecture per se of course. //I don't see a reason for 2500 MHz limit in 7700 though as this will effectively make this card's superiority over RX 6700 series too negligible//

 

[kapone32]

I have a strange feeling that these will be OC monsters.

 

[wheresmycar]

So looks like 6000-series stock is finally entering its diminishing/concluding phase. About time - assuming its one of the triggers behind unleashing 7000-series mid-ranged cards. AMD's gotto get it spot on with pricing, none of that early extortionate scheming and slow burn reductions - its tiresome. A good start would be to drive the 7600's price down to $200 and then set the stage for the bigger brothers (in an ideal world)

 

[Ruru]

7800 XT could be interesting.

 

[Chrispy_]

But they still can limit either RX 7700 or 7800 (or even both) to 2500 MHz for whatever reason, be it competition with other their cards or target TGP, or whatnot. This limit would be implemented via BIOS/straps shenanigans and not by the architecture per se of course. //I don't see a reason for 2500 MHz limit in 7700 though as this will effectively make this card's superiority over RX 6700 series too negligible//

I doubt they'll limit The RX 7700 or 7800 though; They haven't done that for any of the previous few generations, and some of those cards have been in similar market conditions to what we have today. The mining crash that caused late 2018/early 2019 flood of Polaris and lower-end Pascal in the market mirrors all the unsold RDNA2 and Ampere stock we're seeing right now.

As I said earlier, AMD aren't competing with just the Nvidia 40-series, they're competing with every last gen card still sat on store shelves, despite their discounted price. Artificially limiting Navi32 for any reason doesn't make sense to me as AMD will charge us as much as they can for the silicon that they already paid TSMC a fixed price for, a year or more ago.

Whether Navi31 had issues or not, my question was whether AMD have had a chance to respin/tweak/fix/improve on it in the last 10 months. (please select whichever word doesn't trigger you as necessary). Navi 31 is out, it's successful, it's selling well, and it's competitive. How it's flawed or not isn't really the issue and more importantly, it's not going to change past, present, or future Navi31 cards. The only relevance Navi31's design success has is on the speculation of whether AMD found something they could fix in the last ten months or not. At worst, Navi31 is as good as RDNA3 gets, and we're going to get a lukewarm, unexciting (but welcome) Navi32. On the other hand, if there were flaws that AMD has managed to correct in the last 10 months, Navi32 could turn out to be an absolute belter of a GPU.

Since this is a discussion based on a MLID source, here's a 'wonderful' MLID take on Navi31:

Pretty fuzzy and citing anonymous sources at AMD/partners rather than named sources like Steve(GN), Wendel (L1T), or Gordon (PCW) but also laid out much more convincingly alongside the glaringly mismatched performance graphs of what AMD promised and what AMD delivered. Memories are obviously short around here, but Navi31 was disappointing only because it failed to match the performance of even AMD's own cherry-picked benchmarks. Reviewed without those overhyped expectations, the 7900XTX is great.

 

[Macro Device]

They haven't done that for any of the previous few generations

RX 7600 can't be clocked over 3 GHz despite the die being absolutely physically capable of that.
ALL RX cards can't be clocked over 2150/2400/whatever VRAM base speed just because AMD decided not to let you push it this hard.
RX 6700 XT can't be clocked to match RX 6750 XT just because the 6750 variant would lose its entire point.

I don't see any reason why they won't limit the cards. The only question is how. 2500 MHz on-die looks too silly to be true, I'd rather expect same clocks as in RX 7600, perhaps with slight differences (no more than 200 MHz).

AMD aren't competing with just the Nvidia 40-series

Even if their only competition was Ada their pricing is yet to be justified. RX 7600 is absolutely destroyed by RTX 4060 in RT performance, doesn't have DLSS and is obliterated in terms of power efficiency. And it's not faster than 4060 in pure raster, they're almost the same pace. So this 10 percent discount compared to 4060 is a little bit too much of a rip-off. How does RX 7700 make 4060 Ti a funny purchase, I don't really know. To REALLY compete, 7700 has to be as affordable as $270 but I guess Lisa has a 4 hunnit number in her mind. 7800, OTOH, is perfectly dead because aftermarket 3080s and BNIB 4070s sell really well compared to AMD cards of this calibre. Oh by the way, $300 6800 XT on the aftermarket. And its price is dropping.

I always hated nVidia but AMD is literally the king of the disappointment nowadays. If it's not for conspiracy I don't get it why they try SO EFFIN HARD to lose in every segment. Only the RX 7900 XTX makes sense as 7900 XT is priced virtually the same and is slower by too much to justify this pricing. RX 7600 is effectively a 6600 XT for the price of 6700 XT, thus utter garbage. Other RXes, I don't know... And not sure if I want to know.

whether AMD have had a chance to respin/tweak/fix/improve on it in the last 10 months

I'm entirely sure they had. The question is did they use this chance. And the answer is 95 percent negative.

 

[Chrispy_]

I'm entirely sure they had. The question is did they use this chance. And the answer is 95 percent negative.

Your guess is as good as mine!

Design changes > tape out > wafer lithography is a 3-4 month process at minimum, last time I read about process nodes - but that was back in the TSMC 7FF and Intel 10>7 rebranding days. I have no such info on TSMC 5nm so I'm making the assumption that it's as long or longer.

 

[AusWolf]

Sources: Moore's law is dead.... Deep sigh

I almost got excited until I got to this part. Since when can we call sensationalist youtube speculators a source?

 

[Deleted member 185088]

Sources: Moore's law is dead.... Deep sigh

To be fair to him he has been inviting interesting people, and was one of the few with reasonable take on the whole FSR exclusivity.
As for leakes, there are to be taken with a grain of salt.

 

[AnotherReader]

Design changes > tape out > wafer lithography is a 3-4 month process at minimum, last time I read about process nodes - but that was back in the TSMC 7FF and Intel 10>7 rebranding days. I have no such info on TSMC 5nm so I'm making the assumption that it's as long or longer.

The last time a GPU was redesigned to overcome unexpected performance shortfalls was the GTX 580: it was released just seven months after the GTX 480.

 

[Vader]

Your guess is as good as mine!

Design changes > tape out > wafer lithography is a 3-4 month process at minimum, last time I read about process nodes - but that was back in the TSMC 7FF and Intel 10>7 rebranding days. I have no such info on TSMC 5nm so I'm making the assumption that it's as long or longer.

I would be very surprised if amd didn't know about these issues before cards got into reviewers' hands. I think they're working on it even before the 7900s release

 

[rv8000]

IIRC Navi32 was always supposed to be the last GPU in the 7000-series family. Even last year before Navi31 launched, Navi32 was 2H23 on AMD's roadmap


Average boost clock is 2612MHz, that's a long way off the 3GHz they were aiming for, and lot closer to the 2500MHz boost clock advertised.

I think you think I'm arguing something I'm not.
I don't know what you think I'm arguing but I thought I'd made it pretty clear that I'm just citing AMD themselves.
I don't need to defend my opinion because I've not provided one, other than being pleased Navi32 is on the way; If you have issues with what AMD have said in the past, take it up with them, not me.

Finally, confirmation of Navi32
\o/

I was starting to worry that AMD had cold feet with GPU-based MCM, after the issues with Navi31 not clocking as intended - the unexpected artifacting that couldn't be fixed in software requiring them to dial it back by 10-15 from the originally-intended performance and clocks.

Do we know if this coming Navi32 is the cited respin with hardware fixes to tackle the clocking artifacts, or is this just the original silicon run that's limited to ~2.5GHz?

This is the absolute definition of an opinion highlighted in bold. Your mental gymnastics and goal post moving is quite astonishing.

Clearly you cannot back up what you said, because there is no way to confirm your opinion. All actual evidence points to the exact opposite of your opinion.

 

[Zareek]

IIRC Navi32 was always supposed to be the last GPU in the 7000-series family. Even last year before Navi31 launched, Navi32 was 2H23 on AMD's roadmap

Well, I guess they are going to hit 2H then. Let's hope it was worth the wait.

 

[KV2DERP]

looking forward to the 7800 XT, 7800 XTX, 7800 XTXT, 7800 XTXTX

I'm waiting for XFX RX 7800 XTXTX XXX Edition.

 

[wheresmycar]

I'm waiting for XFX RX 7800 XTXTX XXX Edition.

keep an on eye on aliexpress and you should have something along those lines sooner than you think. If you're lucky with a free XXX-rated 16K movie too.

 

[forman313]

I'm waiting for XFX RX 7800 XTXTX XXX Edition.

Its going to take more than 10 X's for me to get one if they are $550.
Only 9 should be $200 at most. Unless RGB is very good and makes me look kewl in the eyes of 25y old kids.

If they keep this up, a lot of casual gamers are going to move on to other things like programming, tinkering and outdoor activities. Who knows.. Maybe even get a girlfriend.

 

[Macro Device]

Maybe even get a girlfriend

What if some casual gamers are heterosexual women? Do they also have to get a GF? I mean, husband is a more appropriate thing here...