NVIDIA is reportedly coughing up big money to TSMC (Taiwan Semiconductor Manufacturing Company) to ensure that it secures plenty of next-gen 5nm wafers for its upcoming Ada Lovelace GPUs that will power the next-gen GeForce RTX 40 series graphics cards.
But in new rumors from MyDrivers, NVIDIA is paying much more than usual to get 5nm wafer from TSMC with the company reportedly paying TSMC a large $1.64 billion in Q3 2021... but that increases to $1.79 billion in Q1 2022 as they ramp up to the Ada Lovelace GPU being made and printed onto next-gen GeForce RTX 40 series GPUs.
A larger long-term deal has also reportedly been struck, which would see NVIDIA coughing up $6.9 billion to TSMC in order to secure next-gen 5nm wafers for Ada Lovelace. We've heard before that NVIDIA's next-gen GeForce RTX 40 series GPUs would be made by TSMC -- and not Samsung -- and its upcoming 5nm node.
- Read more: NVIDIA GeForce RTX 4090: 5nm GPU, 24GB GDDR6X, 3x faster than RTX 3090
- Read more: GeForce RTX 4090 rumor: 2x RTX 3090 perf, power: 'can you accept it?'
- Read more: GeForce RTX 3090 Ti: single-sided GDDR6X, new power plug, 450W TDP
- Read more: PCIe 5.0 power connector allows up to 600W of power, for next-gen GPUs
- Read more: NVIDIA's next-gen GeForce RTX 4090 predicted to cost $2999
MyDrivers reports: "According to industry sources, TSMC's requirements for Apple, MediaTek, AMD and other three major customers are relatively low. They do not need to pay too much deposit in advance to stabilize production capacity. Customers like NVIDIA need to pay huge advance payments in advance if they want to obtain 5nm production orders".
Samsung has been making Ampere GPUs for NVIDIA and its GeForce RTX 30 series, but we all know they aren't the most power-efficient GPUs when you get to the high-end. AMD has hit its stride with its RDNA 2 GPU architecture, with TSMC baking their Radeon RX 6000 series chips on the 7nm node -- the same node used to make the semi-custom chips inside of the PlayStation 5 and Xbox Series X consoles -- and they're fantastic with power.
NVIDIA is making a move that it needs to in order to... well, frankly survive. The company makes its bread and butter from GPUs and if it can't sell enough -- especially of the very best, which TSMC will be capable of providing with its new N5 node -- then well, that's not going to be good at all. NVIDIA can't have another misfire as things will be radically different for Team Green in 2022, 2023, and beyond.
AMD will have its next-gen RDNA 3 architecture here with an MCM-based design -- MCM being a multi-chip module, so multiple GPU chiplets on the same card, similar to how the Zen CPU chiplets are on the Ryzen CPUs -- and will offer some truly monster performance on the next-gen Navi 31-based Radeon RX 7900 XT.
- Read more: AMD's next-gen Navi 31 GPU taped out, flagship RDNA 3 silicon is close
- Read more: NVIDIA GeForce RTX 4090 leaks: beast GPU, 100%+ faster than RTX 3090
- Read more: NVIDIA's next-gen AD102 GPU: RTX 4090 twice as fast as the RTX 3090?!
- Read more: AMD's next-gen Radeon RX 7900 XT: new Navi 31 GPU, battles RTX 4090
Not only that, but the GPU market is going to be completely different this time next year with CPU giant Intel joining the GPU market with its Xe-based Arc Alchemist. Later in the year we'll see how Intel has gone, and what comes next with Intel's Arc GPUs, and then in 2023 we've been hearing that is when things will really ramp for Xe and Arc... and NVIDIA knows that.
It gets worse, as the ongoing pandemic has been wreaking havoc on every single industry -- and the tech industry hasn't been shy from being slammed into the ground. The entire supply chain is f***ed right now, and Taiwan is in the middle of a shit-flinging fight with China + Japan, with the threat of nuclear strikes from China on Taiwan if Japan intervenes in any form.
NVIDIA's next-gen Ada Lovelace GPU and the flagship GeForce RTX 4090 or GeForce RTX 4090 Ti should be capable of 4K 120FPS gaming without a problem, but I think next-gen 8K 60FPS and better yet, 8K 120FPS gaming to be in the sights of NVIDIA. Maybe not raw, but with a next-gen DLSS 3.0 up its sleeve... it's entirely possible, and that is very, very exciting.
AMD's next-gen Navi 31 GPU has recently taped out, the very first MCM-based GPU that should form into a new flagship Radeon RX 7000 series graphics card in the second half of 2022. NVIDIA will be fighting back with the GeForce RTX 40 series and new flagship GeForce RTX 4090, which should offer 2x the performance and power consumption of the GeForce RTX 3090.
In previous rumors, NVIDIA is expected to launch a new GeForce RTX 3090 Ti or GeForce RTX 3090 SUPER graphics card in January 2022 with the same 24GB of GDDR6X memory but single-sided Micron gear. Not only that, but it is rumored to rock the new PCIe 5.0 high power connection, and a higher 450W TDP.
If that's true, NVIDIA is slowly leading up from 300W to 450W with the new RTX 3090 Ti or RTX 3090 SUPER, into the realms of 600W (double the performance, double the power...) with the new Ada Lovelace-based GeForce RTX 4090 graphics card.