Another week, another new GPU rumor! Traveling the halls of the web is a claim that AMD’s upcoming RDNA 4 graphics chip could be running at clock-level much higher than we’ve seen before from Team Red. Specifically, the claims suggest that the higher end version of the next generation GPUs can clock up to 3.3GHz, a full 20% more than any RDNA 3 chip on the market.
Who is making this claim? Moore’s Law is dead, of course, and since the whistleblower doesn’t have a flawless record of making accurate predictions (or ‘leaks’, if you prefer), it’s important not to read. too much into any of this. On the other hand, it still makes a good discussion point about what AMD can do with its next series of Radeon graphics cards to make them stand out even more from the crowd.
Let’s examine the claim in question, which is that RDNA 4 discrete GPU engineering samples are clocking between 3.0 and 3.3GHz. That’s a big jump up from the likes of the Radeon RX 7600 XT, which has a boost clock of just 2.755GHz. One of the notable reasons for this increase is the much-touted claim that AMD will be using TSMC’s N4P process node for all of its GPU manufacturing duties.
That is already being used to make chips such as the Ryzen 7 8700G, a monolithic (single die) processor. It has a Radeon 780M GPU inside and at least one overclocker managed to squeeze 3.1GHz out of that design, 200MHz more than the stock value of 2.9GHz. However, that also required increasing the amount of power consumed by the GPU, from the standard 50W up to 83W, and even as high as 153W to get the best graphics performance.
The Radeon 780M is a tiny GPU, however, with just 12 Compute Units or 768 Shaders. The Radeon RX 7600 XT sports 2048 shaders and is one of the smallest GPUs AMD currently makes.
So while it’s possible to get a small RNDA 3 graphics chip, built on a 4nm process node, to run over 3GHz, it’s another thing entirely to get a larger processor to do the same. And it is the chip that MLID is referring to much larger, with an estimated die area of 300 to 350 square millimeters. That’s at least 47% more than the GPU in the RX 7600 XT.
Those of you who remember the launch of the RDNA 3 architecture will probably remember one particular presentation slide that clearly stated that it was ‘architectured to go beyond 3GHz’ and yet no commercial release of that design ever took place it. And no, GPU overclocking is not the same thing as masses of extra power.
One counterargument to this is that MLID is talking about RDNA 4 and there is a good chance that a new design will achieve this. After all, TSMC has plenty of GPU experience with its 4nm process nodes, as Nvidia is using it for all its Ada Lovelace chips. However, none of those are boosting past 3GHz, even the small ones.
For the sake of simplicity, let’s assume that the claim is correct, and the next series of Radeon graphics cards from AMD will boost north of 3GHz in some models. A better process node will help keep the power consumption and heat under control, especially if these GPUs have the same number of shaders as the current range.
Your next upgrade
Best CPU for games: The top chips from Intel and AMD.
The best gaming motherboard: The right boards.
Best graphics card: Your perfect pixel crusher is waiting.
Best SSD for gaming: Get into the game ahead of the rest.
Without any other improvements, we’d be looking at up to 20% more performance than, say, a Radeon RX 7900 XT (assuming the number of shaders are identical). That’s already a pretty decent graphics card and if I’m being honest, it’s not necessity more performance: It’s more than fast enough as it is. What it needs is a better feature set, especially in ray tracing and upscaling technology.
If RDNA 4 is just going to be RDNA 3 at process scale (ie essentially the same technology, just overclocked) then there won’t be much to entice PC gamers to upgrade. On the other hand, if the new architecture sports hardware dedicated to matrix calculations, which could be used for AI-based upscaling like DLSS Super Resolution, and specialized units for BVH diagonals in ray tracing, then we might have a really good graphics card. waiting just around the corner.
Of course, Intel and Nvidia are hardly sitting back and doing nothing. The first Battlemage architecture is expected to be released at some point this year, and we could see Blackwell launch as a countermeasure to RDNA 4.
The GPU market needs intense competition, from both AMD and Intel, to help combat the rising cost of desktop graphics cards. I’m not sure we’ll see a 3.3GHz Radeon anytime soon but if we’re given something that’s just a more capable GPU, I’ll be a happy person.