Monday, January 29th 2024
Top AMD RDNA4 Part Could Offer RX 7900 XTX Performance at Half its Price and Lower Power
We've known since way back in August 2023, that AMD is rumored to be retreating from the enthusiast graphics segment with its next-generation RDNA 4 graphics architecture, which means that we likely won't see successors to the RX 7900 series squaring off against the upper end of NVIDIA's fastest GeForce RTX "Blackwell" series. What we'll get instead is a product stack closely resembling that of the RX 5000 series RDNA, with its top part providing a highly competitive price-performance mix around the $400-mark. A more recent report by Moore's Law is Dead sheds more light on this part.
Apparently, the top Radeon RX SKU based on the next-gen RDNA4 graphics architecture will offer performance comparable to that of the current RX 7900 XTX, but at less than half its price (around the $400 mark). It is also expected to achieve this performance target using a smaller, simpler silicon, with significantly lower board cost, leading up to its price. What's more, there could be energy efficiency gains made from the switch to a newer 4 nm-class foundry node and the RDNA4 architecture itself; which could achieve its performance target using fewer numbers of compute units than the RX 7900 XTX with its 96.
When it came out, the RX 5700 XT offered an interesting performance proposition, beating the RTX 2070, and forcing NVIDIA to refresh its product stack with the RTX 20-series SUPER, and the resulting RTX 2070 SUPER. Things could go down slightly differently with RDNA4. Back in 2019, ray tracing was a novelty, and AMD could surprise NVIDIA in the performance segment even without it. There is no such advantage now, ray tracing is relevant; and so AMD could count on timing its launch before the Q4-2024 debut of the RTX 50-series "Blackwell."
Sources:
Moore's Law is Dead (YouTube), Tweaktown
Apparently, the top Radeon RX SKU based on the next-gen RDNA4 graphics architecture will offer performance comparable to that of the current RX 7900 XTX, but at less than half its price (around the $400 mark). It is also expected to achieve this performance target using a smaller, simpler silicon, with significantly lower board cost, leading up to its price. What's more, there could be energy efficiency gains made from the switch to a newer 4 nm-class foundry node and the RDNA4 architecture itself; which could achieve its performance target using fewer numbers of compute units than the RX 7900 XTX with its 96.
517 Comments on Top AMD RDNA4 Part Could Offer RX 7900 XTX Performance at Half its Price and Lower Power
But if you are wanting to use it for rendering... They are working on desktop app support for windows directly through hip.
rocm.docs.amd.com/projects/install-on-windows/en/latest/ YMMV
I ... don't use windows for work... so...
Knows = in possession of definite information.
Facts = definite information coming straight from AMD.
Better?
Edit: typoSo by your logic, if there are people throwing "Ngreedia" around, then you may as well join the fight and throw in a line about some "crappy drivers" with zero detail or explanation? How does that make you better than the "Ngreedia" people? How does that help anybody on the forum make an informed judgement? It doesn't.
But I am not as conceited as thinking I am above reproach or that my word is law. I too make mistakes (many of them, in fact) and like any other human being, highly prone to talking smack. Thus, I am still waiting: Why should I give AMD my hard earned cash and faithfully opt for their product instead?
;)
2. The release schedule doesn't affect the product, let alone drivers.
3. It wasn't anti-lag, but anti-lag plus, and it got fixed, as far as I know.
4. What incomplete API support?
+1. No one said you should buy AMD. But just because you have your reasons not to, it doesn't mean that those reasons aren't highly subjective.
2. Yes, it does affect the product. GPUs without drivers are as good as expensive paperweights. You should demand of them the very highest standards in support software releases.
3. Semantics, and yes, of course it got fixed. But the fact remains that should have never shipped. It's one of the most unsanitary, unsafe, utterly stupid ideas I have ever seen. I've once heard a rather stupid joke about the AMD driver being developed by 4 Indian guys in a basement, paid with a goat and a crate of cheap beer. Of course, to even entertain such a notion that this individual was actually being serious is completely absurd, but stunts like the VAC issue truly do place them in that exact light to anyone who has an actual sense of the do's and don'ts of how the Windows DLL architecture works.
4. There was a reason as to why I made the inquiry as to if they actually offer comprehensive support to all API extensions from a wildly popular, 16 year old graphics API. Just as there was a reason I did not get an answer.
I take it no one will try to make a good faith answer to a good faith question, then. I genuinely want to understand what drives this passion, and why are their products worth it.
Edit: I also crunch with WCG, but it doesn't have any GPU work for my Nvidia cards, either.What HDR issues? I might have missed the news on that one. I've never had problems with HDR on my system.
I can take things in sport and learn from experiences, so I was hoping that someone could shed light on why am I wrong, without resorting to anecdotal "evidence". The simple truth is, there is not one department where AMD's software ecosystem measures up, but like I said, I am not conceited as to considering myself to be above reproach.
The one thing I won't accept is the regarding the whole Anti-Lag VAC issue. That was beyond unacceptable, it's not just an "error", it's going below even the lowest software quality standards that anyone could have. I just won't look the other way for something like that. I'm generally lenient with blunders as long as things are made right and made right fast, but this one was easily the most egregious of all.
Sure, my evidence on current issues with Nvidia (one) and current issues with AMD (none) are anecdotal, but even that's better than just talking out of thin air, don't you think?
Personally, I always take stuff on the internet with a grain of salt. Even reviews. That's why I go out of my way and buy stuff that I'm interested in. I even bought a 6500 XT only because everyone on the online world was outrageous about it, I wanted to see what the fuss was about. That's the kind of person I am. I've had lots of disappointment in generally loved products, and I've grown to love ones that are generally hated by the public.
So I'm sorry, but no first-hand evidence = no evidence in my eyes. It's only fan-talk or shittalk.Control panel? Linux support? Overclocking / tuning? Just to name a few.Okay. Please let us know how AMD could fix it beyond it being fixed.
Edit: I'm also curious why you think that compute is essential for gaming.
www.nvidia.com/en-us/software/nvidia-app/
While speaking of nice control panels, shame this isn't available on gaming drivers. Quite useful
And are we even talking about the same thing at this point? You kinda brought up the fancy control panel. idk, I need sleep. will make sure to count the leather jackets :sleep:
You're fine not to like what AMD has, and prefer Nvidia instead. Just don't try to sell it as objective fact because it's not.
But this is not my point. My point is that we shouldn't argue about the past, especially in an RDNA 4 thread. It's totally not relevant to anything here.
Get a grip dude.
Go on, then. I see you want to talk about it.