We have read actively and passively according to leakers that NVIDIA and AMD will compete with the same weapons in the new generation of graphics cards. That the fight will focus on other key aspects and that therefore the best architecture will win, but… It seems that this will not be the case, since NVIDIA and TSMC they have a secret agreement that we already saw in Hopper and that will naturally extend to the RTX 40 under the Ada Lovelace architecture: the node 4N.
The 5nm has several high-volume applicants and TSMC’s problems launching it on its high-performance node (Apple consumes the so-called Low Power N5 LP) do not seem to finish completely despite the rumors that everything is going well. In addition, to this fact that has AMD and Apple as protagonists, we must add a key fact from the past that will make us understand what has been revealed: payment in advance.
NVIDIA and TSMC have an agreement since last year
We are going to try to explain what is happening and not confuse anyone with it, because it is easy to fall into error. When NVIDIA and TSMC signed an exclusivity agreement for cutting-edge chips at the end of last year, it was believed that this was to reserve production of the lithographic process N5 as AMD or Apple had done.
The reservation was true, the node was wrong, and here the controversy begins. NVIDIA did not want to compete with AMD on the same node because its Ada Lovelace architecture was not MCM like its rival’s (we will come back to it later) and therefore asked TSMC for something better and above all more specific.
Notice I didn’t mention PCIe 5.0 in my Lovelace Slides: https://t.co/n7sdIL1Uku
Speaking of “4”, #NVIDIA Lovelace is indeed 4nm!
🤠🎉😋 More to say on the next Broken Silicon… https://t.co/jjJ1GSod0j
— Moore’s Law Is Dead (@mooreslawisdead) April 24, 2022
Out of that need was born a secret agreement whereby TSMC would manufacture in high volume an exclusive node for NVIDIA called 4N, but beware, as we say it is easy to make a mistake because this 4N node is not the N4 that will follow N5 that AMD uses. The NVIDIA 4N node is something specific and designed under CoWoS 2.5D with one thing in mind: the best energy efficiency without compromising performance and also having a small improvement in transistor density if we fairly compare this node with the N5 that AMD will use.
NVIDIA RTX 40 4N vs AMD RX 7000 5N + 6N: TSMC as the cornerstone
This is the ultimate battlefield that both companies will use to face each other. NVIDIA will take this 4N that was already presented in the Hopper graphics cards and that we thought would be exclusive to them and will implement it in any GPU of this new series.
Instead, AMD will opt for an MCM approach that will house two or more chips (depending on the GPU model) and that will have chips as its main attraction. GCD (Graphic Compute Die) and MCD (Memory Compute Die) in two different packages and substrates, where the first will be manufactured in the aforementioned 5nm while the seconds will come in 6nm.
Therefore, the war is centered between the best node available for a graphics card against an architecture that divides resources and chips to manage efficiency and power in a similar way to what Ryzen does against processors. Current Intel.
A secret agreement between TSMC and NVIDIA that will mark the future of the next generation of graphics cards for both gaming and data centers, AI and DL.
