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.
292 Comments on Top AMD RDNA4 Part Could Offer RX 7900 XTX Performance at Half its Price and Lower Power
I would assume that unless nGreedia is going to separate their AI and Consumer GPU designs, then we should expect at least another 40-60% perf from Blackwell. But at what cost, well, that's only limited by Jensen's greed and arrogance.
Anyway, the performance of the XTX @ $400 is a great offer. If we had an effective MCM solution it could be 2x the performance of the XTX at US$800-1000.
I assume a simpler, easier to manufacturer part (read higher volume yields) is because AMD is prioritizing higher end silicon to CDNA.
There is also a good chance that AMD is betting on Nvidia abandoning the mid-range to budget discrete desktop GPU space. This would leave AMD (RDNA4) and Intel (Battlemage) to compete in the sub $500 price bracket.
AMD is several years behind with their RDNA architecture. They need something new and something soon in order to stay relevant.That's not exactly right. AMD offers worse performance per money as is. Look at the benchmarks.
RTX 4090 is 71% faster than RX 7900 XTX for approximately 95% more money (1850 euros vs 950 euros).
Given Nvidia's far superior brand recognition, AMD is the big underdog and loser here.
Second tier manufacturer.
There is nothing to compete with the 4090, and even if there was, people would still buy the 4090 over anything, so what's the point in trying to compete where you can't?71% more performance for 95% more money? How is that better? :kookoo:
There is no advantage for Nvidia to compete against APUs, Battlemage and RDNA4 just to sell a low margin SKU. Its too crowded at the low end and the margins aren’t worth it. Something similar also happened with Nvidia discontinuing mobile MX processors in the laptop space as mobile APUs and SoCs became faster. I predict Nvidia will drop the RTX 5060 parts and only sell 5070/5080/5090 parts in its next GPU series.
Edit: If anything gets sent to the fabs from Nvidia at the low end, it will probably be Switch 2 SoCs.
If by "abandonment", you mean not spending money to carve a smaller chip out of the new architecture, then I agree.
But given that Moore's Law Is Dead deleted that video, I assume he's not that confident in his "predictions" either. While the dude is mostly competent, he's just like other youtubers - may guess few things right now and then, but he isn't a tech-Nostradamus.
1. RDNA5 is shaping to be promising enough that they have to prioritize more resources to finalize it ASAP.
2. RDNA4 Multi Chiplet design is still inefficient compared to RDNA5, going RDNA4 high-end means a lot of work for diminishing results.
So they could either continue with high-end RDNA4 thus delaying RDNA5 more and gaining little results from the high-end RDNA4 (not competitive enough or even worse than RDNA3 competitive position), or scrap high-end RDNA4 to accelerate RDNA5 development and release.
Before replying consider 2 things:
AMD's profit margins around 40-50%. Nvidia's profit margins at 65-75%.
Nvidia can have more wafers from TSMC and uses them only for GPUs. AMD needs to also use the majority of wafers it gets from TSMC for EPYC and Ryzen CPUs and APUs.