Skip to main content

Nvidia Will Use TSMC for Ampere 8nm Successor in 2021 (Rumor)

(Image credit: Shutterstock)

Nvidia's Ampere architecture is barely out of the gate, especially when you factor in continued shortages of the new GeForce RTX 3080 and GeForce RTX 3090 — the theoretically top picks for the best graphics cards and GPU benchmarks hierarchy. The latest rumor from Digitimes (also discussed at TechPowerUp), however, is that the follow-up for Ampere is already on the way and could arrive as early as 2021. #MuchSalt #Speculation

To be clear, we've already mused about this ourselves with the Ampere launch. There's no question that TSMC's N7 process is superior to Samsung's 8N in nearly every important metric — except price and available production capacity. Besides N7, TSMC also has N7P, N7+, N6, and N5 nodes all in active production. In other words, there are a lot of options available for Nvidia to consider, any one of which should be better than Samsung 8N, provided TSMC and Nvidia can come to some sort of agreement on price.

Considering Nvidia CEO Jensen has talked about Nvidia's desire to diversify and not be reliant on any single supplier for chips, plus the shortages of RTX 30-series GPUs, it makes sense for Nvidia to think about shifting some future production over to TSMC. And of course, with RTX 3090 and 3080 being the two highest power single-GPU solutions Nvidia has ever shipped to consumers, finding a way to reduce power requirements and potentially boost performance would be great. However, there are many other factors that also come into play.

First, Nvidia would have to have new designs (relative to the current RTX 30-series GPUS) for TSMC. Samsung 8N is different from all of the TSMC options, so some additional porting work would be required. It shouldn't be too complex, relatively speaking, since Nvidia already has its A100 GPU shipping on TSMC N7, but porting a design to a new manufacturing node is never 'simple.'

Second, we have to assume that any GPUs manufactured on one of TSMC's advanced nodes would perform better than the current GA102/GA104 designs. We would expect improved power characteristics, potentially higher performance, and smaller chips from N7, and additional improvements should Nvidia opt for N7P, N7+, N6, or N5 — though the last three would be even more complex ports, considering they use EUV.

That leads us to the logical conclusion that if Nvidia does end up porting Ampere over to TSMC, it won't be for additional sources of the current RTX 30-series GPUs. Instead, it will be for a mid-cycle refresh similar to last year's 20-Series Super models (i.e., RTX 2080 Super, RTX 2070 Super and RTX 2060 Super). Otherwise, selling two rather different variants of the same chip would lead to problems. Even if the TSMC versions were simply lower power, that's a big enough change that someone would inevitably file a class-action lawsuit. Releasing as RTX 30-series Super avoids that possibility.

There's another possibility, though. The rumor mill suggests Nvidia's post-Ampere architecture might be called Hopper, and this could all just be Nvidia prepping its next-generation GPUs. Hopper is anticipated to use TSMC N5, and normally we'd expect it to arrive 18-24 months after Ampere. Ampere was at least somewhat delayed thanks to COVID-19, however (we originally expected a spring or early summer 2020 launch), so a late 2021 launch isn't out of the question. Likely a big factor will be just how competitive AMD's Big Navi ends up being when it's revealed in a few weeks. Should AMD end up matching RTX 3080, maybe even RTX 3090, Nvidia will almost certainly fast-track a TSMC-based successor. 

  • hotaru.hino
    Something of note since I saw in the other comments that people think NVIDIA and TSMC have a rocky relationship due to NVIDIA chewing TSMC out.

    My cursory glance of the interwebs on the history of this points to two prominent instances where NVIDIA wanted to jump on a new process node, but had trouble with it. The first was the GeForce FX series, going on the then-new 130nm node and TSMC were having issues with that node ( ). The second was the GeForce 400 series at 40nm ( ). While you could argue that if TSMC had issues at 40nm, then AMD would've brought it up as well since the Radeon HD 5000 series was based on the same process, but apparently AMD only had to pay per chip, whereas NVIDIA had to pay per wafer.

    If anything, I think NVIDIA learned its lesson to not jump on the latest process node (hence why Turing was 12nm even though 7nm was around) or at least take a more cautious approach. This time around, since everyone and their mother wants TSMC 7nm, it was probably better from a production capacity standpoint to go with someone who wasn't as burdened. Though given the shortages we're seeing with Ampere...

    Either way, while sure, NVIDIA does have its hiccups with its architectures not being up to snuff, them yelling at their manufacturer isn't entirely unwarranted.
    Reply
  • JarredWaltonGPU
    hotaru.hino said:
    Something of note since I saw in the other comments that people think NVIDIA and TSMC have a rocky relationship due to NVIDIA chewing TSMC out.

    My cursory glance of the interwebs on the history of this points to two prominent instances where NVIDIA wanted to jump on a new process node, but had trouble with it. The first was the GeForce FX series, going on the then-new 130nm node and TSMC were having issues with that node ( ). The second was the GeForce 400 series at 40nm ( ). While you could argue that if TSMC had issues at 40nm, then AMD would've brought it up as well since the Radeon HD 5000 series was based on the same process, but apparently AMD only had to pay per chip, whereas NVIDIA had to pay per wafer.

    If anything, I think NVIDIA learned its lesson to not jump on the latest process node (hence why Turing was 12nm even though 7nm was around) or at least take a more cautious approach. This time around, since everyone and their mother wants TSMC 7nm, it was probably better from a production capacity standpoint to go with someone who wasn't as burdened. Though given the shortages we're seeing with Ampere...

    Either way, while sure, NVIDIA does have its hiccups with its architectures not being up to snuff, them yelling at their manufacturer isn't entirely unwarranted.
    The thing is, Nvidia went with TSMC N7 for Ampere A100, so it's mostly a question of price and capacity I think. Clearly, the A100 is the "price doesn't even matter" market segment. But AMD is doing Zen 2, Zen 3, Navi 10, Navi 12, and Navi 14 all on N7 -- and most likely Navi 21/22 as well. Apple has been doing A12 since 2018 and A13 (N7P) in 2019. Obviously a much smaller chip than Nvidia's GPUs, but even so, no one else is complaining about TSMC's 7nm nodes. Which is the problem, apparently: they're so good that TSMC can charge more, and demand has surpassed (wafer) supply.
    Reply
  • Kamen Rider Blade
    The question is, will Jensen Huang let his ego get in the way of good business decisions?

    Will Jensen Huang accept the higher prices per waffer and go crawling back to TSMC and beg them to manufacture their GPU's?

    Will Samsung try to sweeten the per Waffer price even more to keep nVIDIA as a partner?

    Time will tell.
    Reply
  • JarredWaltonGPU
    Kamen Rider Blade said:
    The question is, will Jensen Huang let his ego get in the way of good business decisions?

    Will Jensen Huang accept the higher prices per wafer and go crawling back to TSMC and beg them to manufacture their GPU's?

    Will Samsung try to sweeten the per Wafer price even more to keep Nvidia as a partner?

    Time will tell.
    Considering Nvidia has already partnered with TSMC, I strongly doubt that it was pure ego getting in the way. If Nvidia went to TSMC last year and said, basically, "We need about 200,000 wafers of GA102 by September, 400,000 wafers of GA104 by October ... oh, and we're still in need of more wafers for GA100," the answer might simply have been that TSMC couldn't do it on the timeframe Nvidia wanted.
    Reply
  • hotaru.hino
    JarredWaltonGPU said:
    The thing is, Nvidia went with TSMC N7 for Ampere A100, so it's mostly a question of price and capacity I think. Clearly, the A100 is the "price doesn't even matter" market segment. But AMD is doing Zen 2, Zen 3, Navi 10, Navi 12, and Navi 14 all on N7 -- and most likely Navi 21/22 as well. Apple has been doing A12 since 2018 and A13 (N7P) in 2019. Obviously a much smaller chip than Nvidia's GPUs, but even so, no one else is complaining about TSMC's 7nm nodes. Which is the problem, apparently: they're so good that TSMC can charge more, and demand has surpassed (wafer) supply.
    I would like to add since now that I look at it, that NVIDIA probably doesn't want to go on the latest and greatest thing the moment it comes out. 7nm now is fine, but 7nm a couple of years ago had teething problems and a lot of fabs that were looking into going 7nm simply dropped it because it was costing too much.

    EDIT: Actually I take back what I said about Turing, since it was likely just Volta with RT cores tacked onto it, Volta was a 12nm design to begin with, and it was likely designed before 7nm had its first "production grade" part manufactured.
    Reply
  • InvalidError
    Kamen Rider Blade said:
    The question is, will Jensen Huang let his ego get in the way of good business decisions?
    As pointed out by others, GA100 is on TSMC 7nm, so Nvidia clearly has no problems going to TSMC when cost is no object for ultra-high-margin parts. Also as already mentioned by others, I too believe Nvidia's decision to go with Samsung 8nm is mainly because of TSMC's 7nm backlog - TSMC being superior is pointless if you cannot book anywhere near enough wafers on the process you want to use.
    Reply
  • MasterMadBones
    Regardless of what Nvidia's relationship with TSMC is, there are also some noises that Nvidia is already pumping huge amounts of money into Samsung to assist them in developing their nodes. If this is true, it's probably part of a long term plan to be able to avoid potential issues with high demand from TSMC and the inflated pricing that would cause.

    hotaru.hino said:
    hence why Turing was 12nm even though 7nm was around
    Mostly because 7nm was a very, very young process at the time and not suitable for large dies at all. Even AMD had availability issues with Vega 20 GPUs more than 4 months later. It was not a matter of taking a "calculated risk", it would simply have been a terrible decision.
    Reply
  • NightHawkRMX
    Considering Samsung can't seem to make more than about a single GPU die per week, I would hope they would come back to a company that doesn't have AS MANY production issues.
    Reply
  • zodiacfml
    Looks like Samsung has pretty bad yield issues and Nvidia is not happy and so are the customers. The hype for the new cards is really good but users can't get their hands on the cards as quickly, wasting precious hype until AMD announces/releases their new cards.
    Congrats to TSMC for doing so well, so well that I'm predicting a future where Intel has fewer fabs until they let go of it like AMD did
    Reply
  • wr3zzz
    This really begs the question why UMC and GlobalFoundry chose not to invest in 7nm.
    Reply