Skip to main content

AMD’s multi-chiplet GPU design might finally come true

RX 7900 XTX installed in a test bench.
Jacob Roach / Digital Trends

An interesting AMD patent has just surfaced, and although it was filed a while back, finding it now is all the more exciting because this tech might be closer to appearing in future graphics cards. The patent describes a multi-chiplet GPU with three separate dies, which is something that could both improve performance and cut back on production costs.

In the patent, AMD refers to a GPU that’s partitioned into multiple dies, which it refers to as GPU chiplets. These chiplets, or dies, can either function together as a single GPU or work as multiple GPUs in what AMD refers to as “second mode.” The GPU has three modes in total, the first of which makes all the chiplets work together as a single, unified GPU. This enables it to share resources and, as Tom’s Hardware says, allows the front-end die to deal with command scheduling for all the shader engine dies. This is similar to what a regular, non-chiplet GPU would do.

The second mode is where it gets interesting. In this mode, every chiplet counts as an independent GPU. Each GPU handles its own task scheduling within its shader engines and doesn’t interfere with the other chiplets. Finally, the third mode is a mix of the two, where some GPUs function as their own entity while others combine the chiplets to function together.

The design of an AMD multi-chiplet GPU.
AMD

As mentioned, this patent is not new. It was filed on December 8, 2022, just after AMD released the RX 7900 XTX and the RX 7900 XT. Although leakers have predicted that AMD might go down the multi-chiplet route for at least a generation or two now, this architecture is currently only really used in AMD’s data center GPUs. AMD has already dipped its toes in similar tech in RDNA 3, though, with a design that used a graphics compute die (GCD) and multiple memory cache dies (MCMs) for the memory interface.

Get your weekly teardown of the tech behind PC gaming
Check your inbox!

There are tangible benefits to switching to this type of architecture, as per the patent: “By dividing the GPU into multiple GPU chiplets, the processing system flexibly and cost-effectively configures an amount of active GPU physical resources based on an operating mode.” If it could turn out to be cheaper to produce these types of GPUs rather than using increasingly larger monolithic dies, we might start seeing this design outside of the data center and in the GPUs we all use in our own computers.

Early leaks about RDNA 4 graphics cards teased AMD going with a full multi-chiplet design, and it’s easy to imagine that the final result could have resembled what we see in the patent. However, with the news that AMD is sticking to midrange graphics cards in this next generation, any hope of a multi-chiplet GPU seems lost for now. Perhaps we’ll see this design come to life in RDNA 5.

Monica J. White
Monica is a UK-based freelance writer and self-proclaimed geek. A firm believer in the "PC building is just like expensive…
AMD’s graphics card sales just took a nosedive
RX 7900 XTX installed in a test bench.

AMD may make some of the best graphics cards you can buy, but they aren't selling well. In its financial results for the first quarter of 2024,  AMD shared that gaming revenue was down 33% compared to the previous quarter, and down 48% compared to the same point last year.

In total, AMD brought in $922 million in its gaming segment in the first quarter. For reference, in Nvidia's previous revenue report, it reported $2.9 billion for its gaming segment. AMD attributes the drop in revenue to "a decrease in semi-custom revenue and lower AMD Radeon GPU sales."

Read more
AMD’s canceled GPU could have crushed Nvidia
The AMD Radeon RX 7900 XTX graphics card.

For months now, we've been hearing rumors that AMD gave up on its best graphics card from the upcoming RDNA 4 lineup, and instead opted to target the midrange segment. However, that doesn't mean that such a GPU was never in the works. Data mining revealed that the card may indeed have been planned, and if it was ever released, it would've given Nvidia's RTX 4090 a run for its money.

The top GPU in question, commonly referred to as Navi 4C or Navi 4X, was spotted in some patch information for AMD's GFX12 lineup -- which appears to be a code name for RDNA 4. The data was then posted by Kepler_L2, a well-known hardware leaker, on Anandtech forums. What at first glance seems to be many lines of code actually reveals the specs of the reportedly canceled graphics card.

Read more
AMD’s upcoming APUs might destroy your GPU
AMD CEO Lisa Su holding an APU chip.

The spec sheets for AMD's upcoming APU lineups, dubbed Strix Point and Strix Halo, have just been leaked, and it's safe to say that they're looking pretty impressive. Equipped with Zen 5 cores, the new APUs will find their way to laptops that are meant to be on the thinner side, but their performance might rival that of some of the best budget graphics cards -- and that's without having a discrete GPU.

While AMD hasn't unveiled Strix Point (STX) and Strix Halo (STX Halo) specs just yet, they were leaked by HKEPC and then shared by VideoCardz. The sheet goes over the maximum specs for each APU lineup, the first of which, Strix Point, is rumored to launch this year. Strix Halo, said to be significantly more powerful, is currently slated for a 2025 release.

Read more