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. This means they use a chiplet design, similar to the company’s Ryzen processors.
Both cards will launch on December 13, 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 over what the previous-gen cards currently sell for – the top-spec 6950 XT retails for $849, while the base 6900 XT is $679, although they launched for $1,099 and $1,000 respectively. However, Nvidia’s RTX 4080 starts at $1,199, while the 4090 is an eye-watering $1,599.
There’s been a lot of buzz around AMD’s next-gen card, with people waiting to see how it would respond to Nvidia’s latest RTX 4000 series GPUs, especially given that Intel’s newly released GPUs aren’t really a high -end challenger.
So, about those cards: The RX 7900 XTX is the company’s flagship, which it touts as its 4K gaming card that’s up to 1.7x 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 seems to be focusing largely on performance per watt here. With a card power of just 350 watts, compared to 450 watts on the RTX 4090, AMD may have an efficiency advantage here, even if it uses more power than Nvidia’s regular 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-bit, and a card power of 300W.
The company says it uses GDDR6 memory instead of GDDR6X for both cards, mainly because it uses less power. You don’t need to use any special power connectors or adapters, as both cards require two standard 8-pin connectors. Nvidia chose a new 12VHPWR connector for the 4090 and has had issues with them melting, an issue the company is still investigating.
The company promises 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 the RDNA 2’s 23 TFLOPs, although 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 promises 62 fps Cyberpunk 2077 with its 7900 XTX card with ray-tracing and AMD FidelityFX Super Resolution (FSR) enabled — the company says its new computing devices feature next-generation ray-tracing technology, providing up to a 50 percent performance boost over 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.
When it comes to traditional rasterized performance, the story looks a bit better – although obviously we’ll 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 2and Valorant, with 300, 600 and 833 fps respectively. That’s when it was paired with a pretty beefy Ryzen 9 7950X processor and 32GB of RAM on an AM5 motherboard.
At 4K (at seemingly unspecified settings), the company says the card can reach 295, 355 and 704 fps with these games.
In the meantime, it says games that Call of Duty Modern Warfare 2 can play around 306 fps as long as you use its FSR technology, which is similar to Nvidia’s DLSS technology 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.
AMD says it will improve FSR, with a new generation of the technology coming next year with “up to 2x more fps” than FSR 2. It will use “fluid motion frames technology”, aka frame generation, similar to Nvidia’s DLSS 3 technique. We’ll have to wait and see how it really compares though – Nvidia uses machine learning hardware on its cards to accelerate its technology, while AMD says the current iterations of FSR don’t because they’re meant to run on any graphics card, not only Radeon ones. The company wouldn’t say if the same was true for the FSR 3, but given its promise of better AI performance on the RDNA 3, it would be nice if it could give its next-gen scaling technology a bit of an edge when running on its latest cards.
Interestingly, AMD has opted for DisplayPort 2.1 support on both the RX 7900 XTX and RX 7900. This means higher refresh rate support at 4K and 8K compared to the old DisplayPort 1.4 port that Nvidia uses on its latest RTX 40 series cards. And like Nvidia, AMD has simultaneous encoding or decoding for AV1, something creators will be interested in for their streams.
According to AMD, RDNA 3 is the first time a chiplet architecture (where a chip is broken up into multiple parts and talks to each other via an ultra-fast interface) has been used in a gaming GPU, and it says it decided to go with the design so that it can use “the right process technology for the right job.” Basically, this means it can use cutting-edge 5nm technology for its graphics processing while relying on more “mature” 6nm chips for memory cache instead of having to use the fancy stuff for everything. AMD previously made waves with its chiplet-based Ryzen processors, and companies such as Intel, TSMC, Samsung, ARM and Qualcomm have all at least begun to look at the concept.
The chips can talk to each other extremely fast, around 5.3 TB/s. For reference, Apple’s M1 Ultra interprocessor connector that connects two processors and GPUs runs at what was widely believed to be a blistering 2.5 TB/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 they expect the cards to be good out of the gate, although they admit they’ll likely see some performance improvements over the next year or so as drivers and software improve.
Beyond the raw hardware speeds, AMD was keen to emphasize software improvements for its latest Radeon cards. AMD is introducing a new one-click feature called “Hypr-RX” in early 2023. It’s supposed to help you automatically get the best settings for various AMD technologies like FSR or anti-lag without having to play 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 work with Ryzen 7000 series processors. It essentially spreads the encoding and decoding workload across Ryzen CPUs and Radeon GPUs, so doing batch transcoding will greatly improve the time 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 Nov. 3, 9:49 p.m. ET: Added context on launch pricing for the 6950 XT and 6900 XT.
#AMDs #nextgen #XTX #GPUs #start #launch #December