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
The move to chiplet design is not easy and it does not guarantee that the next generation dies would be always better in each segment.
No company is obliged to have a top product in each segment they operate in and in each generation. That is completely unreasonable expectation.
AMD is very successful in multiple CPU/APU segments, from desktop to server, in console gaming and they ship MI300 to clients and to build the biggest and most powerful supercomputer in the world - El Capitan. If they skip one top product in one segment, such as discrete GPUs, it's not a big deal. They continue to work on such product until it's ready. You need to acknowledge that there is a wide portfolio of products, and halo gamers is just one tiny little segment of the market.
7800XT is very popular in midrange. 4070 Super also looks good. Everyone needs to look into their needs and wants.This design is probably delayed for another year, until they get it to work properly. They invested most brain power and money in designing MI300. Now that this is out of the way, there is more time and space to perfect top chiplet-based GPU for consumer market. It will take time.I feel brain dead when I read such comments.Even more brain dead after such cherry-picking.
4090 si literally 25% faster in 4K gaming and 100% more expensive. It has the worst possible cost per frame, making it the worst value card for gaming.
You will not be able to ride a gaming rodeo with 4090 narrative for gaming. Nonsense. This card at current price is valuable for creators, engineers, AI folks and graphic designers. Halo gamers are just a tiny little cathegory of market.They will never do that if they want to keep mindshare. At the end of the day, majority of global DIY gamers own 3060 and similar cards.
The world is not that rich.It doesn't, really. If a top product is not ready for prime time, it's simply not ready and people need to wait for it, or buy alternative products, if they can't wait.That is ever more expensive with smaller nodes. Do you want to pay $1,500-2000 for 4K card? I don't.This is changing, little by little.
It's more like: "Nvidia = gaming, AMD = gaming too."Brain dead comparison of tech websites desperate for clicks.
Those two cards are not comparable in thed first place, designed for two different market segments, one of which is very sensitive to small prices fluctuations. People buying 70 class cards usually don't mind paying $30-40 more, but low end often waits until card gets some discount.
Besides, there is no "storm" or "GPU hunger" for Super cards. I can see them everywhere and no online retailer has sold them out.
There's no replacement for the 5-year-old 16-series because you're going to pay for raytracing even if it's an unusable slideshow, damnit!
There was nothing lower than a 2060 at $300 (RTX 2050 Mobile is a super-lame 64-bit bus 30-series Ampere die that Nvidia were so ashamed of, the couldn't even call it a 30-series part).
The 3050 was expected at $200, would have been competitive at $175 but had an insulting and pointless MSRP of $250. Presumably it existed solely as the reason to upsell the 3060 instead.
4050 is AWOL, and the 4060 isn't really appealing with it's high price, lame 8GB VRAM, PCIe x8 limitations, and barely enough bandwidth for 2022 games, let alone 2024 games.
At least AMD have the 6400, 6500, 6600 - all still in production I believe, and whilst the 6400 is awful, the 6500XT has its place, the 6600-series is genuinely great for the money. The 7600-series is a disappointment solely because there were minimal IPC and clock gains moving to RDNA3. You might as well just buy the RDNA2 equivalent until stocks dry up....
I think what people like you mess up is in AMD foundry business (now GlobalFoundries) was spin off in a Private company where stock aren't publicly traded and one of the big private investor was Abu Dhabi. They later sold most if not all of their stakes.
The reports that i sent to you is the real information, not made up information. AMD is a publicly traded company so it's quite easy to know who own it. That report is the truth. End of the story. You can debate all you want. But it's how public stock work. Ownership are reported and consultable. It would be different if AMD was a private corporation not traded in stock exchange. Then they could keep that information private and it would be impossible to know.
Basically they own everything and we are just sheep on computer forum fighting which GPU is better :D
What’s really funny is that most people here don’t want to believe this story only because they want AMD to help keep nVidia prices low. They would never ever buy an AMD video card but don’t want to pay unconstrained nVidia prices. Its funny how products become overpriced when no one buys from the competition.
It'd be like going to check the insides of manchester united via a guided tour. You'll be met by the first team laughing, ten hag kicking about and just a grand jolly time, then you leave and in the ride home discover that one of the stands in old trafford has fallen down due to built up rust.
Extreme (and not real) example of course, but one should mostly care for the product in such instances (and corporations defintely care for only the products). I don't think that AMD would've allowed anything to go wrong during the Level One visit. Much like (and this is an extreme example) when the press went to Qatar to discuss the working conditions of the migrant workers, they discovered what looked like very nice conditions and supposedly happy workers. We all know that is defintely not what went down.
Chiplet design is new generationally speaking, as was the Ryzen 1000 series. Good step forward for AMD but not great at the time compared to their competitor, now a few generations along they're crushing it in the cpu side of the industry.
No reason to think they wont be able to do that with gpu's, and potentially with less iterations due to lessons learnt from Rzyen.
2. Yes. They've discontinued less than 5 year old GPUs recently (such as the Radeon VII) and heavily prioritize features for latest-generation cards. Most of these features may eventually reach older cards, but they certainly were never a priority. Reminder that le ebil nGreedia still supports the GTX 900 series from 2014.
3. Yes, this has happened in the past with the X370 chipset, the elaborate lie surrounding BIOS ROM capacity, and the TRX40 chipset that was aborted mid-way and never received a Zen 3 Threadripper upgrade, leaving people with expensive workstations that never received a CPU upgrade and on a previous-generation architecture.
4. Yes, the 6500 XT launched in an unfortunate market situation and it commanded a relatively high price, and it was one of the most pathetic GPU launches in history (perhaps just not as bad as the GTX 1630). It also has several limitations that not even the 1630 has, such as the complete absence of a hardware encoder and a hard limit of two display outputs (hardware limitation, you will never see any Navi 24 design with more than two display outs).
5. AMD has historically released several China-specific SKUs and has openly licensed its processor IP to Chinese technology companies, going as far as investing itself in joint ventures in order to keep it "by the books" (see: Hygon Dhyana). Not exactly a clean sheet if you want to bring that conversation up.
6. No, AMD does not listen to the community.
www.techspot.com/news/96945-amd-radeon-rx-7900-av1-encoder-almost-par.html
Also, it's CoWoS packaging that is also used to package MI300, way more profitable product. AMD competes with Nvidia and others for access to CoWoS volume production, which is currently limited at TSMC and very saturated by orders for AI chips. TSMC will double CoWoS capacity this year for AI chips, so consumer GPU products will never get as much access to it.
2. Radeon 7, really. How many months was that on the market. I should tell you my story where Nvidia disabled features on my card.
3. I love this one. X370 was said by AMD that most of the BIOS files were too small. You should be glad that community pressure made them get a fix for that. They did not stop giving us Threadripper. Do you enjoy the modern media, well that was a real market for Threadripper and AMD made AM4 faster than Threadripper anyway. Don't worry I still have my X399 board.
4. Relatively high price because reviewers that make their money making videos complained about it. I know I paid $219 for mine and at that time 6600 was $650, much less a 6800XT for $1400 and 6900XT for $1500. What was crazy was all of the media reviews were the exact opposite for users who bought the card.Though in a world where you have a 120hz TV Freesync. You can enable it with a 6500XT. Yes the full 45-120 HZ that TV support. That translates to smooth Gaming vs 60Hz
5. All of that was before the US banned them but you can go on. Most Governments were for Chinese 5G until they were not.
6. AMD did not have to release Vcache to their 12 and 16 core CPUs. The community lamented, chastised and demanded that. AMD tried to give us 2 Vcache but it was not a tangible benefit. I guess when your Game crashes and that message comes up that AMD does nothing with that. I guess when people complained about boot times for AM5 AMD did nothing. I bet AMD gave us Hyper RX to help make Gaming worse. I guess the 8700G is not what we have been asking for but anyhow, you are entitled to your opinion.