AMD’s next-gen RX 7900 XTX and XT GPUs start at $899, launch December 13th
- PC Gaming
RDNA 3 is here, and it brings AMD’s chiplet architecture to gaming GPUs. The company’s promising big improvements to 4K performance.
By Mitchell Clark and Tom Warren
Share this story
AMD has announced its next generation of graphics cards, the RX 7900 XTX and RX 7900 XT, which are the first cards powered by its new architecture, RDNA 3. That means they use a chiplet design, similar to the company’s Ryzen processors.
Both cards will launch on December 13th, with both AMD’s reference cards and board partner models set to ship on that date. The 7900 XTX will cost $999, and the XT is $100 cheaper at $899. That represents a significant price jump compared to what the previous gen cards are currently selling for — the top-spec 6950 XT retails for $849, while the base 6900 XT is $679, though they launched at $1,099 and $1,000 respectively. Nvidia’s RTX 4080, however, starts at $1,199, while the 4090 is an eye-watering $1,599.
There’s been a lot of buzz around AMD’s next generation of cards, with people waiting to see how it would answer Nvidia’s latest RTX 4000 series GPUs, especially considering that Intel’s newly released GPUs aren’t really a high-end contender.
AMD’s performance claims for the RX 7900 XTX.Image: AMD
So, about those cards: the RX 7900 XTX is the company’s flagship, which it’s pitching as its card for 4K gaming that’s up to 1.7 times faster than its existing RX 6950 XT card at that resolution. It has 96 compute units clocked at 2.3Ghz and 24GB of GDDR6 memory with an up-to-384-bit bus. AMD appears to be focusing largely on performance per watt here. With a board power of just 350 watts, compared to the 450 watts on the RTX 4090, AMD might have an efficiency advantage here, though it does use more power than Nvidia’s stock RTX 4080.
The RX 7900 XT is a less powerful option — it has 84 compute units running at 2Ghz, 20GB of GDDR6 memory running at a slightly slower 320 bits, and a board power of 300W.
The company says it’s using GDDR6 memory instead of GDDR6X for both cards, mainly because it uses less power. You won’t need to use any special power connectors or adapters, as both cards will require two regular 8-pin connectors. Nvidia opted for a new 12VHPWR connector for the 4090 and has had problems with those melting, an issue that the company is still investigating.
The company’s promising a lot with RDNA 3: up to a 54 percent jump in performance-per-watt compared to RDNA 2, which used a more traditional GPU design. AMD says it’s capable of producing up to 61 TFLOPs, compared to RDNA 2’s 23 TFLOPs, though it’s worth noting that these numbers aren’t always comparable when you’re talking about different architectures. That means we probably won’t be able to use just the numbers to directly compare consoles like the PS5, Xbox Series, and Steam Deck, which use RDNA 2, to the company’s new PC GPUs.
At 4K, AMD is promising 62fps in Cyberpunk 2077 with its 7900 XTX card with ray tracing and AMD FidelityFX Super Resolution (FSR) enabled — the company says its new compute units have next-generation ray-tracing tech, which provide an up-to-50 percent bump in performance compared to its last-gen cards. Still, that’s less than what we’ve seen with the RTX 4090 at 4K with DLSS 2 or DLSS 3, so it looks like the 7900 XTX is positioned more to compete with Nvidia’s RTX 4080 instead.
AMD performance promises for Cyberpunk 2077 and more.Image: AMD
When it comes to traditional rasterized performance, the story looks a bit better — though we’ll obviously have to wait and see how it performs when we get our hands on it ourselves. At “esports” (aka medium-to-low) settings and 1440p resolution, AMD says the 7900 XTX can max out the frame rate limits of Apex Legends, Overwatch 2, and Valorant, with 300, 600, and 833 fps, respectively. That’s when it was paired with a pretty beefy system Ryzen 9 7950X processor and 32GB of RAM on an AM5 motherboard.
At 4K (with seemingly unspecified settings), the company says the card can hit 295, 355, and 704 fps with those games.
Meanwhile, it says games like Call of Duty: Modern Warfare 2 can play around 306 fps as long as you’re using its FSR technology, which is similar to Nvidia’s DLSS tech in that it renders games at a lower resolution and then upscales them. Move up to 8K, and FSR does even more heavy lifting for 96 fps in Assassin’s Creed Valhalla.
In games that support it, FSR does do a lot of heavy lifting.Image: AMD
AMD does say it’ll be improving FSR, with a new generation of the tech coming next year with “up to 2 times more fps” than FSR 2. It’ll use “fluid motion frames technology,” aka frame generation, similar to Nvidia’s DLSS 3 tech. We’ll have to wait and see how it really compares, though — Nvidia uses machine learning hardware on its cards to accelerate its tech, while AMD says the current iterations of FSR don’t because they’re meant to run on any graphics card, not just Radeon ones. The company wouldn’t say if the same was true for FSR 3, but given its promise of better AI performance on RDNA 3, it would be nice if it could give its next-gen scaling tech a bit of an advantage when it’s running on its latest cards.
Interestingly, AMD has opted for DisplayPort 2.1 support on both the RX 7900 XTX and RX 7900. That means higher refresh rate support at 4K and 8K compared to the old DisplayPort 1.4 port that Nvidia is using on its latest RTX 40-series cards. And just like Nvidia, AMD has simultaneous encode or decode for AV1, something that creators will be interested in for their streams.
AMD seems very proud of RDNA 3, but it is slightly difficult to compare it to RDNA 2 just based on specs alone.Image: AMD
According to AMD, RDNA 3 is the first time a chiplet architecture (where a chip’s multiple parts are broken up and talk to each other via an ultrafast interface) has been used in a gaming GPU, and it says it decided to go with the design so it can use “the right process technology for the right job.” Basically, it means it can use cutting-edge 5nm tech for its graphics processing while relying on more “mature” 6nm chips for memory caching instead of having to use the fancy stuff for everything. AMD previously made waves with its chiplet-based Ryzen processors, and companies like Intel, TSMC, Samsung, ARM, and Qualcomm have all at least started looking into the concept.
The chips can talk to each other extremely fast, at around 5.3TB/s. For reference, Apple’s M1 Ultra inter-processor connection that connects two CPUs and GPUs runs at what was widely considered a blazing-fast 2.5TB/s.
When AMD first introduced Ryzen, it’s fair to say there were some growing pains as developers and hardware manufacturers figured out how to really take advantage of its design. During a Q&A session, AMD said it expects the cards to be good right out of the gate, though it does admit that they’ll likely see some performance improvements over the next year or so as the drivers and software improve.
AMD Hypr-RX one-click optimization.Image: AMD
Outside of raw hardware speeds, AMD was keen to stress software improvements for its latest Radeon cards. AMD is introducing a new one-click feature called “Hypr-RX” in early 2023. It’s meant to help you automatically have the best settings for various AMD technology like FSR or anti-lag without having to play around with them yourself to see what offers the best frame rates and responsiveness.
AMD is also launching SmartAccess video with its Radeon 7000 series GPUs, which works paired with Ryzen 7000 series CPUs. It essentially spreads the encoding and decoding workloads across Ryzen CPUs and Radeon GPUs, so if you’re doing batch transcoding, it will greatly improve how long it takes to complete a video. AMD says this will be supported in apps like OBS, Adobe Premiere Pro, and others starting in December.
Update November 3rd, 9:49PM ET: Added context about the 6950 XT and 6900 XT’s launch prices.
Rivian CEO: ‘There’s far too much greenwashing in the system’
The excellent Arc browser is now available for anyone to download
Elon Musk just changed Twitter’s logo again — sort of
ChatGPT for Android is now available
Google’s CFO just got a promotion
AMD RDNA 3 — PC Guide
Last Updated on
AMD RDNA 3 graphics cards are nearly here. Continue reading to find out all you need to know about Radeon RX 7000 GPUs ahead of release.
With Black Friday closing in, it’s also the perfect time to upgrade your AMD CPU – you can shop the latest AMD Ryzen Black Friday deals right here.
RDNA 3 RX 7000 release date
The new microarchitecture was officially unleashed upon the public as planned on November 3. In the reveal event, we learned that the first two graphics cards of the generation, RX 7900 XT and RX 7900 XTX are coming on December 13.
Pre-orders and landing pages are not yet live, but we suspect you won’t be waiting long. We go into far more detail on their respective pages.
NOW READ: Here are the best Black Friday deals we could find for the RTX 4080
RDNA 3 RX 7000 price
The two current RDNA 3 RX 7000 graphics cards announced carry respective MSRPs of $899 and $999 for the RX 7900 XT and RX 7900 XTX. This is in line with the rumors and speculation which proceeded the event.
The company was smart to keep the same price point as with its previous flagship model for the new frontrunner, undercutting Nvidia by $600, with the rival’s RTX 4090.
NOW READ: Here’s where you can buy the Nvidia 4080
Nothing from the entry-level or mid-range field has been announced yet, but we’re expecting that this could change in early 2023. This is usually the case with new hardware launches from AMD. It leads with the best and then offers cheaper alternatives into the new year. Still, a top-performing card under $1,000 is a sure-fire win when Nvidia’s cheapest current-gen is $200 more.
RDNA 3 RX 7000 specs
Although the company hasn’t quite detailed every tech spec of its latest GPU line, we’ve compared the key specs against each other in an easy-to-read table to give you an insight into which card could be right for you in December:
|RX 7900 XTX||RX 7900 XT|
|96 RDNA CU cores||84 RDNA CU cores|
|24GB GDDR6 VRAM||20GB GDDR6 VRAM|
|384-bit memory bus||320-bit memory bus|
|2. 3 GHz Game Clock||2 GHz Game Clock|
|355W TDP||300W TDP|
In order to fully evaluate the specs of what’s possible with AMD’s latest microarchitecture, we must look closer at the highest end of the spectrum right now, the RX 7900 XTX. This card features 24GB GDDR6 memory with a 384-bit memory bus and a game clock speed of 2.3 GHz. The real highlight of these cards is the fact that they have support for DisplayPort 2.1, though.
This means you can expect resolution and frame rate support of up to 8K165, which is the world’s first in the world of consumer-grade graphics cards. It isn’t just marketing talk either, as the company showed a real-world example of Assassin’s Creed: Valhalla running at 8K60. That’s not something we’ve seen from Team Green, and especially not under the $1,000 mark.
NOW READ: Black Friday Ryzen deals have gone live – here’s what you could save
Also of note is the fact that the two RDNA 3 graphics cards utilize standard 2x 8-pin PCIe power cables without the need for an adapter. Equally impressive is the fact that these GPUs are near-identical in dimensions to the previous frontrunners, the RX 6900 XT. This means that there’s no need to upgrade your PC case or PSU. which is a good consumer-friendly choice on its part.
RDNA 3 RX 7000 performance
While we’re going to have to wait until we’ve tested and benched the graphics cards in-house, what AMD has presented is incredibly encouraging. A real focus appears to be on utilizing the new FSR 3, FidelityFX Super Resolution 3, A.I. supersampling, to push the highest frame rates in higher resolutions than what’s currently possible with the current generation.
The latest flagship from AMD appears to be incredibly comfortable at 4K (Source: AMD)
While the statistics demonstrated for 4K ray tracing are all well above 60 FPS at Ultra settings, the most impressive feat is just how high games can be pushed in the demanding resolution. As you can see, games such as the recently released Call of Duty: Modern Warfare II can achieve over 300 FPS in 2160p with the use of FSR. Natively, the same is said of Overwatch 2.
This means that high-performance 4K gaming is entirely possible for AMD’s newest cards, something that only the RTX 4090 can do reliably at two-thirds the price point. It remains to be seen just how capable this card (and wider RDNA 3 generation will be) but we’ll be bringing you all the latest as soon as they’re hot off the presses.
Do AMD GPUs have ray tracing?
Although not exactly billed for it as with Nvidia cards, AMD graphics cards do in fact utilize ray tracing. They don’t generally tend to perform as efficiently as with what Team Green offers on this front, but that could very well be changing soon. At the time of writing, current-generation GPUs from the red corner feature first-generation Ray Accelerators. We’ll likely see second-gen next.
What does RDNA stand for?
RDNA stands for Radeon DNA and is the name AMD has given its various generations of recent GPU architecture. The title was first used with the Navi 1 line back in 2019, which we know as the Radeon RX 5000 series. As well as being used in graphics cards, modified RDNA 2 microarchitecture is also used inside the PS5, Xbox Series X, and Steam Deck.
AMD and Nvidia are reported to suffer big losses in Q3 2022, GPU shipments fell by 25% not seen since the economic downturn of 2009.
Jon Reddie Research published its latest PC market report for the third quarter of 2022. The analysis shows that the figures for the third quarter, in which the PC market is traditionally gaining momentum, did not live up to expectations. For example, processor shipments are reported to have dropped by 19% compared to the third quarter of 2021.
However, the current downturn in the PC market has not affected the CPU market the most, but the video card market.
GPU market in Q3 2022
According to Jon Peddie Research, total PC GPU shipments totaled 75.5M in Q3 2022 and is expected to grow by 2.8% in to 3,138 million units by 2026, while overall GPU sales are down 25. 1% year-over-year. The slowdown in shipments hit the laptop segment the hardest, down 30%, while desktop graphics sales fell 15.43%. Jon Peddie notes that this is “the biggest drop since the 2009 recession.”years».
quarterly deliveries and the share of the market in percent, as well as the annual results of
We are moving further, it is worth noting that both NVIDI and the AMD have lost the pynka in the same time as a 2022 g, but 8.5% and 1.87% respectively. Intel, on the other hand, increased its market share for the quarter by 10.3%. Thus, Intel leads the PC GPU segment in Q3 2022 with a market share of 72%, while Nvidia and AMD take the 2nd and 3rd places with 16% and 12% respectively.
Finally, both AMD and Nvidia shipped fewer GPUs in the third quarter of 2022 compared to the second quarter of 2022, as the companies saw significant shipment cuts of 47.6% and 19.7%, respectively. Intel again managed to stay in the black with a 4.7% increase in this regard.
Processor market in Q3 2022
Similar to the graphics market, processor shipments also decreased by 5.7% quarter-on-quarter. Total CPU shipments, including desktop and laptop CPU sales, were 66 million in Q3 22, down 4 million units from Q2 22 and 15 million less than Q3 21.
Platform share and unit of shipment CPU
In particular, shipments of desktop processors increased by 10%, while sales of notebook processors decreased by 10%.
John Peddy, President of JPR, argues that according to PC vendors, the collapse of cryptocurrency mining, China’s COVID policy, US sanctions against China, soaring inflation leading to price hikes by AIB, and future uncertainty may be possible causes. PC market sluggishness in Q3 2022.
Finally, Peddy thinks that “there is a feeling that shipments in the 4th quarter will decrease, but ASP sales will increase and everyone will have a happy vacation.”
This material was written by a site visitor and has been rewarded.
Media: Intel, AMD, NVIDIA will raise prices for video cards and processors up to 20% in 2022
2022 started off with some pretty bad news for users looking to upgrade their PCs. According to DigiTimes , the Big Three, which includes the AMD , Intel and NVIDIA , plans to increase their product prices by up to 20% due to a number of external factors such as continued high supply and production costs.
Report says TSMC has already raised prices on existing 7nm and 5nm processes to be used in several next generation GPUs and CPUs such as AMD Ryzen 7000, AMD Ryzen 6000H/U, NVIDIA GeForce RTX 40 and Intel’s ARC Alchemist GPU. In the latter case, Intel is relying on the 6nm process technology, which is a continuation of the N7 process node, but the price increase will be similar.
AMD will increase the cost of all 7nm and 5nm chips manufactured by TSMC, as TSMC has increased its prices for old and modern technology nodes by 10-20% since this year.
Earlier this year, NVIDIA also reportedly paid TSMC advance payments for long-term orders for its 5nm RTX 40 series of GPUs and may pass on some of the increased manufacturing costs to customers.
The increase in end-user prices should compensate for the variables and external factors that have affected the existing chip manufacturing process. And while there is a chance that the availability of some products will improve by the end of this year, in the case of prices, there are no prerequisites for this, and this is what remains the main problem for many now.
AMD has already raised prices for Zen 3 processors based on TSMC’s 7nm process, but the Ryzen 7000, which uses TSMC’s 5nm process, may go up even more.
Intel’s ARC graphics and AMD’s new RDNA 2 graphics cards are the only GPUs currently known to use TSMC’s 6nm process node, so they may have a better supply situation, but pricing is a big question mark. Judging by retailer pricing for the Radeon RX 6500 XT, it appears that chip supply issues will also affect the 6nm process, despite AMD promising to improve supply and pricing for the upcoming card.
Read also : New leaderboard and improved game stability: DICE Studio talked about the upcoming improvements to Battlefield 2042 .