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.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."
396 Comments on Top AMD RDNA4 Part Could Offer RX 7900 XTX Performance at Half its Price and Lower Power
If you drop them you can use a 3080 or a 6800XT at 4k.
End of the day people make a big deal of RT because their hardware can't handle it and they cannot afford a suitable upgrade.
Because the best looking thing we could do for screenshot is a very high quality baked lighting that wouldn't be dynamic at all. Doesn't matter, screenshot don't move. This is also why so many old game still look good and seem to have good lighting on screenshot. Because it's just static.
When you get to Dynamic lighting, then the non RT stuff have many flaws. It can look somehow good but it's easy to fell apart. RT do a much better job for those kind of scenario. It just make the lighting to be much more realistic, witch at the same time, make it less obvious. That is a strange thing but that is the case. Like said previously that is a style you go for.
Right now, the main problem i think with Path Tracing and RT in general is not really the performance impact, it's the quality of the denoiser. Movie just brute force that issue with many more rays and heavy offline denoising algorithm.
DLSS 3.5 is a bit better on that front but it still have many flaws. Having a quality denoiser will be key to make RT look like what we see in movies.
As for the performance impact, this is just a current impact. Most of the shaders we use would destroys the few first generations of GPU that supported it. In 2-3 generation, even mid range should have plenty of power to run RT at 1080P
The only thing that matters now is to release something (anything) new, no matter if it's good or bad, then adjust the pricings accordingly, so that at least some stock moves off the warehouses shelves..
Nothing in the current AMD 7000-series lineup is 2 years old yet, most of it isn't even 1 year old yet - and the AMD 7000-series is younger than the RTX 40-series and the Intel Arc series.
4K cards dont exist and never have nor will. There is only a game and its performance. GPUs move along doing what they can, and especially now with dynamic 'anything' in graphics... if you put up with high latency, lower IQ you can have 4K on many cards...
So, a 2018 thing. :D
As for the design process being 2018, what does that have to do with anything? Every CPU and GPU in the last 30 years has been in development for multiple years before launch. Once again, you're spouting nonsense - please stop, or at least do a basic sanity check on whether what you type is sane, relevant, or worthwhile.
You in a wrong way count the period between a product going in the wild and the present moment, when the right way to count how old a product is to count the time between its set-in-stone, tape-out, or set-in-stone decision / feature set. Because between that moment in time, and the physical release to the wild, there can be multiple other milestones happening, feature set updates, etc. Wrong. AMD's market share is close to non-existent in the OEMs market, which means that while the products do indeed physically work, they are market failures.
88% of all GPU shipments are nvidia, the rest is AMD and intel.
www.jonpeddie.com/news/shipments-of-graphics-add-in-boards-decline-in-q1-of-24-as-the-market-experiences-a-return-to-seasonality/
Tape-out and product launch are at a bare minimum, 6 months apart and have been 2+ years on several notable occasions where redesigns were required after the initial tape-out. Tape-out is one of the product development phases, but there's no way to know if any tape-out will be final until the silicon is received back and tested months later. Saying that a tape-out is the time at which a product is set-in-stone proves that you have absolutely no idea what you're talking about.
By your metrics, Nvidia Blackwell GPUs, slated to launch in early 2025 are already 18 months old!
Here's another shovel if you want to keep digging...
Also, what's this big deal about market share imparity with Nvidia? Why do you think that a much smaller company should equal out a much bigger one in market share? :kookoo: