Radeon 7900 XTX and XT in tests: faster, faster and cheaper than RTX 4080

NVIDIA RTX 4080 And 4090 The GPU is an amazing achievement. It’s surprisingly expensive, starting at $1,200 and going up to $1,500 and up road Also for cards from partners like MSI, Gigabyte and Asus. The 4080 costs nearly double the original RTX 3080 MSRP of $699.

These price increases are partly due to pandemic-era concerns such as supply chain crises and inflation, and partly to a cryptocurrency-driven boom (which has thankfully ended) that encouraged a network of speculators to snap up every high-end GPU. There was also a lack of competition in the game Increased cost and complexity Massive monolithic wafer construction with the most modern manufacturing processes. Today AMD tries to solve the last two problems by releasing the Radeon RX 7900 series of GPUs.

At $899 and $999 respectively, the RX 7900 XT and RX 7900 XTX are still objectively expensive – but since they’re not a step above the RX 6900 XT’s starting price, both cards are a good deal in your passport GPU market. Today. If you’re looking for cards that can handle 4K games consistently at 60fps or higher, these GPUs do it in less time than Nvidia’s latest cards, and they’re good enough and fast enough that they should hopefully start to undercut Nvidia’s prices a bit. . Also to do less.

But Nvidia still retains some key advantages that complicate a simple David-and-Goliath narrative. These GPUs don’t appear to be a Ryzen moment for AMD’s graphics division — a tipping point where an inconsistent AMD could severely erode the market share of an established, content competitor. But if you can find it at its starting price, it’s the first sign we’ve had in a while that some relief is on the way for high-end but budget-conscious PC gamers.

Akbar Nabi

The RX 7000 series is the third iteration of the RDNA GPU architecture, sometimes referred to as “Navi” after the codename of the GPU chips. RDNA 3 doesn’t add anything as significant as ray tracing support to RDNA 2, but AMD has added a ton of additional hardware and major under-the-hood changes.

Most important is a new chip-based approach, similar in concept which AMD uses for its Ryzen CPUs. Instead of making the entire GPU die in a single manufacturing process – increasing the size and therefore likely to have some or all of it defective – AMD builds the main Navi 3 GPU die on a 5nm manufacturing process with TSMC and a few smaller memory controller dies (MCDs) on the 6.nm process. All of these chips are connected to a high-speed internal interconnect that AMD says can transfer data at speeds of up to 5.3 terabytes per second.

The graphics compute master block (GCD) contains most of the hardware you think of when you think of a GPU—compute units, shaders, ray tracing devices, a media encoder and decoder block, and output rendering. Both the 7900 XTX and XT use the same Navi 31 GCD, but the XTX runs at a higher clock speed and has more CUs and stream processors. XTX has 96 CUs and 6144 stream processors while XT has 84 CUs and 5376 stream processors. Both cards represent a jump over the Navi 21-Die used in the RX 6900 series, maxed out at 80 CU and 5120 stream processors (and that’s before considering other performance-enhancing improvements).

All MCDs feature a single 64-bit memory controller and 16MB of Infinity cache from AMD, demonstrating the advantages of a chiplet-based approach. The 7900 XTX has a 384-bit memory bus and 96MB of infinity cache, while the 7900 XT has a 320-bit bus and 80MB of cache; All AMD has to do is remove MCD. The same MCDs can be reused up and down the stack with all the different RDNA 3 GCDs AMD chooses to launch, from low-end products to mid-range GPUs using between two and four with one MCD. Defects on MCD chips do not require scrapping or discarding larger and more complex GCDs, and vice versa.

RDNA 3’s brand new feature world has three notable ones. First, the GPU has new AI accelerators that could be useful for all the AI-assisted content creation released last year, and AI-assisted scaling (if AMD decides to include their FSR implementation in a future version of the upgrade algorithm). Both DLSS and XeSS use AI for upscaling, but FSR 2.0 does not.

Second, the video encoding and decoding block supports hardware-accelerated encoding of AV1 video codecs such as the RTX 4000 series and Intel Arc GPUs. This should be useful for content creators as well as streamers who want to stream HD video or video at the same resolution using less bandwidth.

And third, the Radiance Display Engine adds DisplayPort 2.1 support for GPUs. Monitors that take full advantage of the extra bandwidth provided by DisplayPort 2.1 don’t really exist as of this writing, but if they did, RDNA 3 GPUs could drive 4K displays up to 480Hz and 8K displays up to 165Hz.