The AMD RDNA4 architecture and the upcoming Navi 41, Navi 42, and Navi 43 GPUs have been extensively covered by RedGamingTech. This is one of the first leaks from a known leaker, and while RGT has a track record of reliability, this post is still being treated as a rumour at this time because information this early is always in flux and subject to change. So, salt shakers at the ready, let’s dive into this absolute treat of a leak from RGT.
The AMD Navi 41, Navi 42, and Navi 43 GPUs have been given preliminary specifications for the upcoming Radeon RX 8000 series.
The first order of business is that RGT confirms that the ALU count for RDNA4 CUs will remain exactly the same as RDNA 3 – that is, 128 ALUs per CU. GDDR7 memory is definitely in play but has yet to be confirmed, and PCIE 5.0 is very likely to be the standard of choice over PCIE 6.0 because the latter will most likely not be ready in time. Interestingly, the RDNA4 architecture will target a boosted 3.5 GHz clock frequency, which when combined with the other architectural changes means a net performance per watt gain of around 50-60%.
One of the shortcomings of AMD’s RDNA3 architecture was the lack of ray tracing and AI/ML performance, which AMD hopes to address with RDNA4. Caches will be significantly upgraded, with the introduction of the 3rd Generation Infinity Cache and a new data prefetch system. WMMA (Wave Matrix Multiply-Accumulate) V2 will also allow for two times the performance per CU for (presumably) matrix instructions, allowing for full SIMD lane usage. Despite the fact that the total increase in CUs is around 50%, the performance increase generation to generation is 100%, which is fantastic to hear. The individual dies are listed below:
AMD Navi 41 – 144 CUs
Here’s where things get even crazier: the Navi 41 is said to have up to 32 GB of vRAM, most likely of the GDDR7 variety. A second configuration with 24 or 48 GB of GDDR7 and 6 MCDs is also available (the 32 GB variant has 4 MCDs). The Navi 41 will have 144 CUs, which when clocked at 3.5 GHz and divided by 128 ALU per CU should result in a whopping 129 TFLOPs of FP32 performance. That is, without a doubt, a Godzilla level of performance.
AMD Navi 42 – 96 CUs
Navi 42 will be slightly muted, with a total of 12,288 CUs clocked at 3.5 GHz, yielding around 86 TFLOPs of FP32 performance. 96 CU is also the exact count of the RDNA3 flagship, the Radeon 7900 XTX, so this SKU will represent the generation over generation comparison between RDNA3 and RDNA4 (or more accurately, as apples to apples its ever going to get). Specifications like these *can* and do change before the final revision, as RGT notes in their slides.
AMD Navi 43 – 48 CUs
Finally, there is Navi 43, which will have 48 CUs. This will produce around 43 TFLOPs of FP32 performance when clocked at around 3.5 GHz. This is most likely the lower end of AMD’s RDNA4 lineup, and it just goes to show how much performance is packed into this upcoming RDNA4 architecture, where the “lower end” easily exceeds 40 TFLOPs. The memory standard will remain GDDR7, and it will include two MCDs. This is also the only SKU where RGT mentions that the GPU may not be of an MCM design, despite being told that it is.
Source: wccftech
