RX 5950 XT, RX 5950, and RX 5800 XT: New AMD Radeon SKUs Reach Regulators

[Minus Infinity]

Unless these are released soon, why wait until the same year you are releasing Navi+ cards. Already 5700XT is competitive with 2070 Super, so 5800XT should be between 2070 Super and 2080 Super, 5900XT should be similar to 2080 Super and 5950XT should be 2080 Ti competitor. If they priced the 5800XT right, say $50 more than current 5700XT and pushed that down a bit, I’d be tempted especially if next gen cards are really only coming late in the year.

I still think their are too many variants at the high end, this segment is not price sensitive, people won’t quibble about $50 on a $500+ card. I’d just release 5800XT and 5900XT and have one sit just under 2080 super performance at $100 less, and 5900XT sit just under 2080 TI at $100-150 less and release them by next month. They need to be priced well since Ampere is due out before Navi+, so these new cards will lose appeal if too late and dear. Get them out early and keenly priced and give yourself plenty of breathing space before Ampere arrives. Still if Amepre is released by mid year I’ll go with that for sure.

 

[Midiamp]

Well, seeing how Navi scales up... The power draw from the supposed 5950XT will be interesting to say the least. Thank goodness I don't have superfluous monitors that needs a high end GPU.

I really wonder how AMD going in with Ray Tracing. The wording on Xbox Series X launch has a weird framing, something along the line that the Ray Tracing is done externally... I forgot where I read or the exact sentence, but it's around there.

 

[my_name_is_earl]

Don't hold your breath. AMD is 2 card behind NVDIA. Or an entire generation if you put ray traced tech in.

 

[HenrySomeone]

Wow so 5700xt at 2070 level, 5800 2070 super, 5950 2080 and 5950xt possibly at or above 2080ti... Let's hope so, now there should be competition at every level can we get back the pricing where it should be?

They'll be lucky if 5950XT can get anywhere near 2080super at less than 350watts! Of course, if these supposed cards materialize at all, there are a lot of indications, they won't.

If this is existing RDNA and not RDNA2 it will be dead on arrival. Assuming the navi architecture scales, 5950xt might be a 2080ti competitor without RT, or if its RDNA2 with RTRT.

The problem is, Turing is more than a year old and Ampere is soon, reportedly pushed into first half of 2020. Considering Nvidia is already performance and efficiency leader using 12nm, and with first gen RTRT taking die space and power budget, 7nm+ Nvidia will be 50%+ performance gains with slight efficiency gains as well.

Think 2080ti performance at $450 or less, using the power draw of a 2060S.

AMD needed big navi 6 months ago, if it releases it now and its just RDNA1 scaled up it's a waste of time, and the only ones who will buy it are AMD fan boys, of which, admittedly there's a lot of.

Even with RDNA2, they'll be dead the moment Ampere launches and regarding AMD fanboys, yes, the internets are crawling with them, however when it comes time to dish out big bucks for a high-end card, most are nowhere to be found... They wait for a discount RX 570 at like 99$ and then praise AMD for their perf/$

5500, 5600, 5700, 5800, 5900, 5950.. Why this reminds me so much of GeForce FX lineup, only 5200 is missing?

There are other similarities; late to the party, hot and loud (at least with stock coolers), not to mention inferior performance . Although, with the fx line, 5800 was the worst, while 5900 and 5950 were OK(ish) at least, but with Navi, I'm expecting the opposite - 5800 might be somewhat passable (akin to 5700 non-xt), while the other two will be intolerable "gas-guzzlers" setting new records for a single-chip card power draw and possibly even rival the likes of 295x2 when pushed to the max

 

[Midiamp]

regarding AMD fanboys, yes, the internets are crawling with them, however when it comes time to dish out big bucks for a high-end card, most are nowhere to be found... They wait for a discount RX 570 at like 99$ and then praise AMD for their perf/$

Hey, I'm an AMD fan, and your statement is wrong, I bought my 570 at $110, and yes it offers good perf/$.

 

[Deleted member 193706]

They'll be lucky if 5950XT can get anywhere near 2080super at less than 350watts! Of course, if these supposed cards materialize at all, there are a lot of indications, they won't.

Even with RDNA2, they'll be dead the moment Ampere launches and regarding AMD fanboys, yes, the internets are crawling with them, however when it comes time to dish out big bucks for a high-end card, most are nowhere to be found... They wait for a discount RX 570 at like 99$ and then praise AMD for their perf/$

There are other similarities; late to the party, hot and loud (at least with stock coolers), not to mention inferior performance . Although, with the fx line, 5800 was the worst, while 5900 and 5950 were OK(ish) at least, but with Navi, I'm expecting the opposite - 5800 might be somewhat passable (akin to 5700 non-xt), while the other two will be intolerable "gas-guzzlers" setting new records for a single-chip card power draw and possibly even rival the likes of 295x2 when pushed to the max

Talks about amd fan boys then proceeds to say how an unreleased gpu will set a new single card record for power consumption whilst in the same breath saying how ampere, also unreleased will blow rdna2 out of the water, please do tell me more about these fan boy people

 

[springs113]

I for one, is waiting for big navi... I'd be surprised if the performance is less than "amperes" highend. I don't think it should surprise anyone that AMD will compete. I'm almost certain that they chose not to release something faster than the 5700xt, even they have the resources to do so... also that they limited the 5700xt performance on purpose. Although this is pure speculation on my part, I believe we're all in for the same Zen treatment on the gpu front, only this will be much quicker than the time it took zen to truly compete.

 

[kings]

I don't know why some people insist on comparing CPUs with GPUs, they are completely different situations.

On CPUs, AMD caught an Intel sleeping for almost a decade, with marginal performance increases every year. As if that were not enough, they were too optimistic for their 10nm density and the shot backfired. And to make things even worse, at a time when AMD had access to a better manufacturing process. That is, without taking AMD's merit, but basically everything aligned to AMD almost perfectly, probably not even they expected everything to go that well.

In the GPU front, the story is very different. Not only has Nvidia significantly increased performance every year, introducing new features and always improving the efficiency of its products, unlike CPUs, the 7nm advantage does not apply. Nvidia is still better with the old 12nm and they will change to 7nm in a few months.

These are very different market situations, and unless all the stars line up for AMD and Nvidia starts to fail, I don't see how anything similar to CPUs could happen. I don't doubt that AMD could have something competitive, but doing just like what Ryzen have done on CPUs is pretty much a daydream.

 

[Vya Domus]

Nvidia is still better with the old 12nm and they will change to 7nm in a few months.

How so ? If you mean they're better because they have chips that are an astonishing 3X times bigger you're absolutely right.

 

[kings]

Performance/watt.

Look at Nvidia cards and AMD equivalents, in most of them AMD not only has less performance, but is less efficient, despite already using 7nm.

Perhaps the only exception is the RX5700 non-XT.

 

[Vya Domus]

Perhaps the only exception is the RX5700 non-XT.

It's not "an exception", it's the same architecture. And if you think Nvidia's next gen will have much better efficiency, your in for a big surprise.

less efficient, despite already using 7nm.

That's exactly because their chips are huge, the bigger the chip the more power efficient it gets.

 

[Vayra86]

If this is existing RDNA and not RDNA2 it will be dead on arrival. Assuming the navi architecture scales, 5950xt might be a 2080ti competitor without RT, or if its RDNA2 with RTRT.

The problem is, Turing is more than a year old and Ampere is soon, reportedly pushed into first half of 2020. Considering Nvidia is already performance and efficiency leader using 12nm, and with first gen RTRT taking die space and power budget, 7nm+ Nvidia will be 50%+ performance gains with slight efficiency gains as well.

Think 2080ti performance at $450 or less, using the power draw of a 2060S.

AMD needed big navi 6 months ago, if it releases it now and its just RDNA1 scaled up it's a waste of time, and the only ones who will buy it are AMD fan boys, of which, admittedly there's a lot of.

I don't know, you're saying here they will straight up do another Pascal. Its possible. Not extremely plausible. What are they fighting? As you say, last year's Turing... they're not fighting AMD at all. Also... the 980ti is an entirely differently positioned card as the 2080ti. The latter is a fantasy product really given its price. The 980ti actually was used competitively, and priced as such. They won't jump from their 2080ti fantasy card straight to an upper-midranger. Never.

I'm more of a believer we get +30% in the stack compared to the Supers and then a mild price bump too. That will still leave AMD gasping for air. Nvidia is going to want to keep their first 7nm iteration as small as possible, so they can follow up on it within the same architecture. AMD is approaching it the other way around now, with process before arch. Also, Nv needs die space for RT, so that's going to limit their raw perf die space too.

It's not "an exception", it's the same architecture. And if you think Nvidia's next gen will have much better efficiency, your in for a big surprise.



That's exactly because their chips are huge, the bigger the chip the more power efficient it gets.

You miss the point where Nvidia was still on an old, easy node and AMD is using valuable 7nm capacity. Nvidia can make that huge chip a tad more easily, and they can still scale down to repeat the trick again once 7nm is matured. This is how architecture efficiency translates into economics.

I do get what you're saying about the 5700 and same architecture, but in practice, we see every time AMD is 'forced' to clock the snot out of its line up to keep it competitive within the same SKU. And that kills efficiency and shows the flaws of GCN/RDNA. Bigger dies won't suffer that so much, but then... what's next? Its not like they have 5nm on the shelf so its going to have to come from RDNA2.

 

[TheoneandonlyMrK]

I don't know why some people insist on comparing CPUs with GPUs, they are completely different situations.

On CPUs, AMD caught an Intel sleeping for almost a decade, with marginal performance increases every year. As if that were not enough, they were too optimistic for their 10nm density and the shot backfired. And to make things even worse, at a time when AMD had access to a better manufacturing process. That is, without taking AMD's merit, but basically everything aligned to AMD almost perfectly, probably not even they expected everything to go that well.

In the GPU front, the story is very different. Not only has Nvidia significantly increased performance every year, introducing new features and always improving the efficiency of its products, unlike CPUs, the 7nm advantage does not apply. Nvidia is still better with the old 12nm and they will change to 7nm in a few months.

These are very different market situations, and unless all the stars line up for AMD and Nvidia starts to fail, I don't see how anything similar to CPUs could happen. I don't doubt that AMD could have something competitive, but doing just like what Ryzen have done on CPUs is pretty much a daydream.

I could find many posts saying amd couldn't pull a win in CPU space , plus discounting the effect intel will have on discrete sales is foolish, Amd won't have to beat Nvidia alone though obviously they won't actually work with intel they will benefit kn kind from intel pushing their discrete gpu into laptops for example, lots of Nvidia laptop gpu sales are at risk when DG2 hits shelves.

 

[ratirt]

So maybe the stronger NAVI cards will be released after all. This info's been going back and forward for quite a while. I hope it will be released eventually and it will be good. I'd like to see something with more juice than 5700XT

 

[Vya Domus]

I do get what you're saying about the 5700 and same architecture, but in practice, we see every time AMD is 'forced' to clock the snot out of its line up to keep it competitive within the same SKU. And that kills efficiency and shows the flaws of GCN/RDNA.

No but that's the thing, they clock them higher because the chips are small, as I said, the bigger the chip the more power efficient it gets. An 2080ti is almost 90% faster than a 2060 but it doesn't use anywhere near 90% more power. RDNA is power efficient and if the time comes and make a bigger one it will scale very well not worse like the lot of you suggest.

You miss the point where Nvidia was still on an old, easy node and AMD is using valuable 7nm capacity.

No I'm not missing that, what happens is that I know what these nodes can do. The only advantage 7nm has is transistor count, that's it, it's neither more performant or power efficient than 16nm (not in a remarkable way).

 

[Vayra86]

No but that's the thing, they clock them higher because the chips are small, as I said, the bigger the chip the more power efficient it gets. An 2080ti is almost 90% faster than a 2060 but it doesn't use anywhere near 90% more power. RDNA is power efficient and if the time comes and make a bigger one it will scale very well not worse like the lot of you suggest.

I'm not suggesting it scales worse in efficiency. What I do say is it scales worse in profit margins for AMD, and its going to be a repeat of the good old exercise where Nvidia just runs over AMD with a mildly faster chip every time, at an almost similar price. And note: also better efficiency at that price point. You know what will happen with that 'efficient' big chip. We get another XT version of it that will run straight to boiling point.

You're also taking for granted that Ampere will not improve upon Turing efficiency wise.... I beg to differ. Look at what Pascal did... that wasn't just a shrink, they used that shrink to push 25% higher clocks and maintain efficiency, due to much finer grained power control.

 

[Vya Domus]

What I do say is it scales worse in profit margins for AMD

Why is that ? Are we just going on the same old rhetoric that AMD must always undercut their competition ? They can charge 1500$ for a GPU that's slightly faster than 2080ti for all I know or care. This domain is not Nvidia exclusive.

 

[Vayra86]

Why is that ? Are we just going on the same old rhetoric that AMD must always undercut their competition ? They can charge 1500$ for a GPU that's slightly faster than 2080ti for all I know or care. This domain is not Nvidia exclusive.

They can charge it. But they won't sell it. That is why; and the backdrop of that idea is the advantages Nvidia still brings to us, a much better driver regime, software suite, featureset, and first to market.

Also, 1500 for all you care; its not like the 2080ti's present a major market share... even Nvidia has trouble selling at that price; and they don't even want or need to, its still a hard chip to make. You don't just poop out big chips with good quality like that. Take special note of the bad batches of 2080ti we have seen.

You are not blind, are you. Nvidia has been pushing smaller dies for a looong time, their efficiency push has always translated into profit there. Smaller memory bus, smaller chip. They departed from that with Turing, but the timing is fantastic, because now they can time their 7nm more comfortably and get comfy with RT. They used Turing to buy time. AMD used the node to buy time to work on architecture... so again, RDNA2 had better deliver, and they had better have something after that too.

 

[Vya Domus]

Look at what Pascal did

As I said above 7nm isn't the free lunch that 16nm was, they'll be faced with the exact same problems AMD had. I really don't understand why you all believe Nvidia has some sort of magic dust that allows them to squeeze more stuff out of existing technologies.

But they won't sell it.

And Nvidia can because ... they're not AMD ? Come on, this is some weird ass goal post slalom. As soon as it becomes feasible that AMD will have a competitor suddenly their software suite is not good enough or they're late or any other excuse pops up.

AMD can and will price their products above Nvidia's if the opportunity arises, just like they did with Ryzen.

 

[Vayra86]

As I said above 7nm isn't the free lunch that 16nm was, they'll be faced with the exact same problems AMD had. I really don't understand why you all believe Nvidia has some sort of magic dust that allows them to squeeze more stuff out of existing technologies.



And Nvidia can because ... they're not AMD ? Come on, this is some weird ass goal post slalom. As soon as it becomes feasible that AMD will have a competitor suddenly their software suite is not good enough or they're late or any other excuse pops up.

So far we've seen a lot of Nvidia magic dust the past years, you may say in hindsight it was all logical and just another step forward... but seriously? You want a list? And note, some crucial things on that list, AMD has not managed to copy, or is still working at and even when implemented don't quite work as well. Clocking being the major, major one here. How do those Navi's run at 2100mhz by now and how efficient are they doing that? So apparently there really is some unicorn out there.

And first to market... it matters. It mattered with Gsync; it matters because it enforces mindshare and the idea of leader not follower. It also reinforces the idea that as a customer you're not missing out. And that is a BIG one, despite what you may think. It translates into Nvidia being able to charge premium. Even something as silly as RT in Turing, while it has very little to show to us, what it did show was that with Nvidia you are again on the first row in tech progress.

So yes, Nvidia can, because they are not AMD. You may not agree with the rationale but that doesn't make it less of a reality.

An example to drive this home. Pascal was released in 2016. Here is Nvidia doing 2000 mhz clocked GPUs

Here is AMD in 2019 doing 2000 mhz clocked GPUs.

 

[HenrySomeone]

I don't know why some people insist on comparing CPUs with GPUs, they are completely different situations.

On CPUs, AMD caught an Intel sleeping for almost a decade, with marginal performance increases every year. As if that were not enough, they were too optimistic for their 10nm density and the shot backfired. And to make things even worse, at a time when AMD had access to a better manufacturing process. That is, without taking AMD's merit, but basically everything aligned to AMD almost perfectly, probably not even they expected everything to go that well.

In the GPU front, the story is very different. Not only has Nvidia significantly increased performance every year, introducing new features and always improving the efficiency of its products, unlike CPUs, the 7nm advantage does not apply. Nvidia is still better with the old 12nm and they will change to 7nm in a few months.

These are very different market situations, and unless all the stars line up for AMD and Nvidia starts to fail, I don't see how anything similar to CPUs could happen. I don't doubt that AMD could have something competitive, but doing just like what Ryzen have done on CPUs is pretty much a daydream.

Precisely! In the cpu space, the heavens alinged in AMDs favor and they still only matched Intel at thread parity in the so called productivity tasks, while the latter is still considerably better at gaming. In the gpu space, sth like that isn't going to happen anytime soon, barring an asteroid wiping out Nvidia headquarters and main research center and even then, it would take a couple years

 

[Vya Domus]

So far we've seen a lot of Nvidia magic dust the past years, you may say in hindsight it was all logical and just another step forward... but seriously? You want a list? And note, some crucial things on that list, AMD has not managed to copy, or is still working at and even when implemented don't quite work as well. Clocking being the major, major one here. How do those Navi's run at 2100mhz by now and how efficient are they doing that? So apparently there really is some unicorn out there.

Irrelevant, Nvidia and AMD have not been on the same equal ground in terms of nodes for a very long time, what they have done cannot and should not be compared like that. It simply doesn't make sense to say one implemented something better because they had different technologies to work with at their disposable and inevitably one of those technologies was simply better. But now they are and it's not going to be smooth sailing anymore. You known, kinda how as soon as Zen got on 7nm, suddenly the situation got a lot worse for Intel.

They wouldn't have been able to copy them in the past even if Nvidia would have handed them over all their IP, it wasn't possible.

So yes, Nvidia can, because they are not AMD.

OK, enjoy being ripped off by one company in particular because they were first or something along those lines. AMD should go home and stop trying to do anything because there is no point.

 

[EarthDog]

Haters going to hate. Studies show.

 

[ValenOne]

Wow so 5700xt at 2070 level, 5800 2070 super, 5950 2080 and 5950xt possibly at or above 2080ti... Let's hope so, now there should be competition at every level can we get back the pricing where it should be?

FYI, both RTX 2070 Super and RTX 2080 uses the same TU104 chip.

RX 5800 series could have RX 5800 and RX 5800 XT.

 

[Vayra86]

Irrelevant, Nvidia and AMD have not been on the same equal ground in terms of nodes for a very long time, what they have done cannot and should not be compared like that. It simply doesn't make sense to say one implemented something better because they had different technologies to work with at their disposable and inevitably one of those technologies was simply better. But now they are and it's not going to be smooth sailing anymore. You known, kinda how as soon as Zen got on 7nm, suddenly the situation got a lot worse for Intel.

They wouldn't have been able to copy them in the past even if Nvidia would have handed them over all their IP, it wasn't possible.



OK, enjoy being ripped off by one company in particular because they were first or something along those lines. AMD should go home and stop trying to do anything because there is no point.

So the fact remains, AMD's choices in the past years are still biting them in the ass. The fact they can't copy it and or cannot match it, is still a fact, no matter if you think it makes sense or not. Nobody cares what you think. I just look at the cold hard data of releases, pricing, and how it was followed up, and what's still in the tank for the future. You try to sell the idea that RDNA(2) is somehow going to be just as great as Nvidia's Ampere when in fact, even good old Pascal is already more efficient than it at every turn. EVEN when RDNA uses lower clocks, it can only get equal efficiency at lower absolute performance.

And then you top it off by saying 7nm is not going to be an efficiency jump when AMD showed that it was all by itself with the Radeon VII. Dafuq?!

Start connecting the dots, mate.

OK, enjoy being ripped off by one company in particular because they were first or something along those lines. AMD should go home and stop trying to do anything because there is no point.

Also this really says it all. I can separate my personal buying decisions from the analysis of how companies perform and how its products work.

You apparently seem to have trouble doing that.