RDNA 3 this year, RDNA 4 lands in 2024

Among AMD’s many announcements today around its 2022 Financial Analyst Day, the company is offering an update to their client GPU (RDNA) roadmap. Much like the company’s Zen CPU architecture roadmap, AMD has held a 2-year horizon here, essentially showing what’s coming, what’s coming, and what’s coming out in a year or two. This means that today’s update gives us a first look at what will follow from RDNA 3, which itself was announced way back in 2020.

With AMD experiencing a wave of success with their current RDNA 2 architecture products (the Radeon RX 6000 family), the company is looking to maintain that momentum as they shift toward launching products based on their upcoming RDNA 3 architecture. And while AMD’s roadmap update today is top notch, it nevertheless gives us the most detailed look yet at what AMD has in store for their Radeon products later this year.

RDNA 3: 5nm with Next-Gen Infinity Cache & Chiplets

First and foremost, AMD is aiming for a performance-per-watt improvement of more than 50% over RDNA 2. This is a similar improvement to seeing them move from RDNA (1) to RDNA 2, and while such a claim from AMD might have seemed gaudy two years ago, RDNA 2 has given AMD’s GPU teams a significant amount of newfound credibility.

Fortunately for AMD, unlike the 1-to-2 transition, they don’t have to figure out a way to come up with a 50% increase based on architecture and DVFS optimizations alone. RDNA 3 will be built on a 5nm process (no doubt that of TSMC), which is a complete improvement of the node of the TSMC N7/N6 based Navi 2x GPU family. As a result, AMD alone will see significant efficiency gains.

But that said, nowadays a single node jump on its own cannot deliver a 50% improvement per watt (RIP Dennard scale). So there are several architecture improvements planned for RDNA 3. This includes the next generation of AMD’s on-die Infinity Cache, and what AMD calls an optimized graphics pipeline. According to the company, the GPU Computing Unit (CU) is also being redesigned, but to what extent remains to be seen.

But the biggest news in this area is that AMD, confirmed by a year of rumors and several patent applications, will be using chiplets with RDNA 3. The GPU layer (as we know it) moves from a monolithic GPU to a chiplet-like design, using multiple smaller chips.

Chiplets are in some ways the holy grail of GPU engineering, as they provide GPU designers with options for scaling GPUs beyond current die size (crosshairs) and yield limits. That said, it’s also a holy grail because the sheer amount of data that has to be passed between different parts of a GPU (on the order of terabytes per second) is very difficult to do – and very necessary to do if you a multi-chip GPU to present itself as a single device. We’ve seen Apple tackle the task of essentially merging two M1 SoCs together, but it’s never been done before with a powerful GPU.

AMD specifically calls this an “advanced” chiplet design. That name is often thrown around when a chip is packaged using some sort of advanced, high-density interconnect like EMIB, which sets it apart from simpler designs like Zen 2/3 chiplets, which just route their signals through the organic packaging without any advanced technology. So while we eagerly await further details of what AMD is doing here, it wouldn’t be at all surprising to find that AMD uses some form of Local Si Interconnect (LSI) technology (such as the Elevated Fanout Bridge used for the MI200- family of accelerators) to directly and tightly bridge two RDNA 3 chiplets.

RDNA 4: Improving AMD’s Performance and Efficiency in 2024

And as AMD prepares to bring RDNA 3 based GPUs to market, the company is already hard at work on its successor.

RDNA 4, as it’s aptly called, will be AMD’s next-generation GPU architecture for 2024. Unlike today’s Zen 5 reveal, we’re getting almost no detail here – although that was also the case for the RDNA 3 unveiling in 2020. As a result, there is not much to dissect about the architecture at this point other than the name.

All we do know is that RDNA 4 GPUs will be manufactured on what AMD calls an “advanced node”, which would take it beyond the 5nm node used for RDNA 3. AMD will have a similarly veiled 2020 revealed for RDNA 3 , and as was the case back then, AMD is seemingly keeping the door open to make a final decision later, when the state of play for the 2024 time frame is better established. One of TMSC’s 3nm nodes would be the most ideal outcome here, but a 4nm node is off the table, especially if AMD has to fight for capacity. (As cool as consumer GPUs are, other types of products tend to be more profitable on a mm2 basis)

Finally, like AMD’s Zen 5 architecture, RDNA 4 is expected to land in 2024. Given that AMD has established a pretty consistent two-year GPU cadence in recent years, a launch in the second half of 2024 is not an unreasonable bet. Although there is still a lot of time to go until we reach 2024.