Skip to main content

Update: Nvidia VP Says Next-Gen GPUs Will Be Made by TSMC and Samsung

(Image credit: Michael Vi/Shutterstock)

Updated, 7/5/19, 9:23am PT: Nvidia executive vice president of operations Debora Shoquist said in a statement that “Recent reports are incorrect – NVIDIA’s next-generation GPU will continue to be produced at TSMC. NVIDIA already uses both TSMC and Samsung for manufacturing, and we plan to use both foundries for our next-generation GPU products.”

Updated, 7/5/19, 7:25am PT: An Nvidia spokesperson responded to our request for comment on this story by saying that "We do not comment on rumors or speculation." We asked if that meant Nvidia was disputing The Korea Herald's report, or if Nvidia Korea's Yoo Eung-joon was mistaken about Samsung manufacturing Ampere GPUs using its 7nm EUVL process. The spokesperson said, "We already use both TSMC and Samsung, and qualify each of them for every process node. We can’t comment in any further detail on future plans, but both remain terrific partners."

Original article, 7/2/19, 8:08am PT:

Nvidia reportedly confirmed that it's partnered with Samsung to manufacture its Ampere GPU, which is expected to launch in 2020 using its 7nm extreme ultraviolet lithography (EUVL) process rather than continuing to source GPUs from longtime foundry partner TSMC.

The Korea Herald reported that Nvidia Korea leader Yoo Eung-joon confirmed the switch from TSMC to Samsung during a press conference. The companies don't appear to have formally announced the partnership on their websites--the most recent articles from Nvidia focus on the GeForce RTX 2060 and 2070 Super graphics cards that debuted today. We've emailed Nvidia for confirmation of their new deal.

Yoo didn't offer much information about the partnership. He called Samsung's production commitment for Ampere "substantial," according to the report, but declined to get into any specifics. Yoo was also said to have claimed that Nvidia's acquisition of Mellanox would close before the end of the year, pending regulatory approval from various countries and final approval from Mellanox's shareholders.

It's not clear why Nvidia decided to switch foundry partners for Ampere. EETimes reported in early June that Samsung "aggressively undercut" TSMC. We do know that TSMC's 7nm process has already become popular with Apple and AMD. 

There are few details available about Ampere so far. It's expected to launch in 2020 and will succeed Turing architecture introduced in September. But if Nvidia follows a similar cycle as it did with Turing, we could learn more about the Ampere architecture during the SIGGRAPH conference in August.

  • TCA_ChinChin
    Please give truly next gen price/performace. The Super refresh is a nice holdover to this, but Turing has been and still is slightly disappointing in the value arena. Maybe after the new AMD cards launch, Nvidia will finally give consumer friendly pricing (but I have my doubts).
    Reply
  • bit_user
    Oh man. I saw the words "Ampere" and "partnership" and, remembering their recently-announced software support for ARM-based hosts, immediately thought it was referring to this:

    ?rel=ugc]https://en.wikichip.org/wiki/ampere_computing/emag?rel=ugc]https://amperecomputing.com/wp-content/uploads/2018/02/ampere-product-brief.pdf
    Reply
  • jimmysmitty
    TCA_ChinChin said:
    Please give truly next gen price/performace. The Super refresh is a nice holdover to this, but Turing has been and still is slightly disappointing in the value arena. Maybe after the new AMD cards launch, Nvidia will finally give consumer friendly pricing (but I have my doubts).

    Considering the information we have I am also doubtful Navi will do anything to force nVidia to lower prices. Navi just doesn't seem to be what it needs to be, a new non-GCN based uArch that can perform equal to or better than their nVidia counterparts.
    Reply
  • TCA_ChinChin
    jimmysmitty said:
    Considering the information we have I am also doubtful Navi will do anything to force nVidia to lower prices. Navi just doesn't seem to be what it needs to be, a new non-GCN based uArch that can perform equal to or better than their nVidia counterparts.

    The Super stuff have finally pushed price/performance for Turing to what would be more palatable levels. Navi got price cuts in return. Everything this gen is finally at semi-reasonable levels in my opinion. Maybe another 50$ drop across the midrange market would really put things in the solidly worth it side for me. I'm thinking that Navi has at least pushed Nvidia to release the Super stuff, maybe at least the next Uarch from AMD could keep Nvidia from marking up Ampere even higher up than Turing.
    Reply
  • jimmysmitty
    TCA_ChinChin said:
    The Super stuff have finally pushed price/performance for Turing to what would be more palatable levels. Navi got price cuts in return. Everything this gen is finally at semi-reasonable levels in my opinion. Maybe another 50$ drop across the midrange market would really put things in the solidly worth it side for me. I'm thinking that Navi has at least pushed Nvidia to release the Super stuff, maybe at least the next Uarch from AMD could keep Nvidia from marking up Ampere even higher up than Turing.

    We will never know if Super is a response to Navi or just a logical refresh like they have done in the past, as has AMD done. I like to think this stuff is planned out a few years in advanced as it takes a lot of time to test and qualify these kinds of products, even CPUs.

    It is nice but I still miss the days of ATI where they pushed nVidia even harder and would win more often than AMD has done in the past few years. I think having a total lineup that really challenges the other ends up with better price/performance than just barely creeping on their tails.
    Reply
  • TCA_ChinChin
    jimmysmitty said:
    We will never know if Super is a response to Navi or just a logical refresh like they have done in the past, as has AMD done. I like to think this stuff is planned out a few years in advanced as it takes a lot of time to test and qualify these kinds of products, even CPUs.

    It is nice but I still miss the days of ATI where they pushed nVidia even harder and would win more often than AMD has done in the past few years. I think having a total lineup that really challenges the other ends up with better price/performance than just barely creeping on their tails.

    I wasn't around for the days of ATI, but I can agree with what you mean. More competition means better products and better prices.
    Reply
  • hannibal
    TCA_ChinChin said:
    Please give truly next gen price/performace. The Super refresh is a nice holdover to this, but Turing has been and still is slightly disappointing in the value arena. Maybe after the new AMD cards launch, Nvidia will finally give consumer friendly pricing (but I have my doubts).

    Well 3080 ti 1999$
    3080 999$
    3070 799$
    3060 499$
    2660 359$

    Easy to predict ;)
    Reply
  • kinggremlin
    hannibal said:
    Well 3080 ti 1999$
    3080 999$
    3070 799$
    3060 499$
    2660 359$

    Easy to predict ;)

    Nvidia's next gen will not be more expensive than turing. Nvidia flat out admitted in one of their quarterly reports that Turing sales were lower than expected with one of the primary reasons being that prices were higher than consumers expected. If you already know your prices are hurting sales volume, you don't raise prices further. Turning was so much more expensive than Pascal, because the dies were significantly larger and because Nvidia was trying to recoup R&D expenses for ray tracing and tensor cores. With the next gen moving to 7nm and no significant architectural changes the prices should remain static to the Super cards at worst.
    Reply