AMD’s blow and surprise at NVIDIA has been manual and although the latter reacted in time, with each generation of GPUs they have more and more problems to tell the difference. AMD’s definitive move was intended to be an RDNA 3 architecture where Huang couldn’t explain the huge jump in performance, but it was all subject to TSMC’s ability to manufacture the necessary amount of chips in its new 5nm node and …
TSMC could be on the ropes: no production capacity of its 5nm?
This is one of those news that works like a loudspeaker of a rumor and so we have to be careful and take a little salt to flavor it, because at the moment we have only been able to find out by the source and the company has not made any statements about it. But if TSMC finally faces a wafer problem due to below-expectations production, well below what should be inclusive, AMD is in serious trouble and it would be confirmed that the jump from NVIDIA to Samsung was a success. .
The problem is that the industry is very quickly abandoning the 7 nm and the 7 nm + of the Taiwanese, Samsung has a limited chip capacity and most of the high performance goes to NVIDIA, Intel for its part although it has opened its doors. Fabs is unwilling to offer wafers with their 7 nm SF … So can AMD face any problems because of TSMC?
Yes and no at the same time. Yes, because if there are not enough wafers for RDNA 3, we are talking about that only Zen 4 would be at the level of its rival in CPU within the lithographic section, which will allow it to compete in efficiency, performance per watt and surely number of cores. But in GPU, the s tory is very different and the options come to the fore.
AMD could use TSMC’s 6nm node for RDNA 3
Most likely, AMD will have to do something rare in the industry with RDNA 3: launch an architecture with two different nodes for its models, or choose to launch the first models with a lower performing node adapting to the market and later Upgraded versions of these GPUs with the highest performing node.
There are rumors about the use of TSMC’s 6nm as an alternative to 5nm and its lack of platelets. We are talking about a node which is an improved version in EUV of the current 7 nm and which achieves an increase in the density of the 18%, a decrease in the energy of the 8% and you don’t get any performance improvement in terms of frequencies. Ergo, AMD would be far from being as efficient and to stand up to Samsung if it arrived with its 5 nm for next year, another unknown whose secrecy is absolute around them.
Can AMD improve the remaining% to achieve the above in efficiency and compete with NVIDIA in performance? Will you postpone the launch in search of these 5 nm? We’ll have to wait and see if that eventually comes to pass.