Array
(
    [content] => 
    [params] => Array
        (
            [0] => /forum/index.php?search/247846/&c[users]=semiman&o=date
        )

    [addOns] => Array
        (
            [DL6/MLTP] => 13
            [Hampel/TimeZoneDebug] => 1000070
            [SV/ChangePostDate] => 2010200
            [SemiWiki/Newsletter] => 1000010
            [SemiWiki/WPMenu] => 1000010
            [SemiWiki/XPressExtend] => 1000010
            [ThemeHouse/XLink] => 1000970
            [ThemeHouse/XPress] => 1010570
            [XF] => 2021370
            [XFI] => 1050270
        )

    [wordpress] => /var/www/html
)

Search results

  1. S

    Will Samsung take business from TSM in AI

    When major AI chip companies are printing money, foundry discount is practically nothing. For example, NVIDIA is making twice more profit than TSMC right now, so for NVIDIA, risk of not getting good dies outwieghs benefits of cheaper foundries. So, there's TSMC, as usual. Samsung will get...
  2. S

    Interesting Samsung 14nm vs. tsmc 4nm function comparison from Gorq in SFF2024

    I remember some material saying that Groq's benchmark has 3 concurrent users(full rack of servers). In many cases, DRAM + GPU combination supports more than 100 concurrent users(Single 4U rack). Groq might have some oppurtunities if there are applications who wants blazing fast language model...
  3. S

    Interesting Samsung 14nm vs. tsmc 4nm function comparison from Gorq in SFF2024

    AFAIK, they decided to use Samsung Taylor fab. Since they're designing DRAM-less(SRAM only) inference chip, no wonder it's faster than their competitions. So basically they're emphasizing their design superiority, not comparing foundries.
  4. S

    Is this software advance significant?

    The problem of non-conventional approaches are 'software'. If we have super great compiler and runtime which are capable of break large operations into smaller OPs which perfectly fits to each accelerator(whatever accelerators are), removing all possible bubbles then it'll work. But can we? This...
  5. S

    TSMC Q1 2024 Discussion

    Hm..it seems that Intel Arrow Lake and Lunar Lake are not in HVM yet. Maybe we're going to see N3 revenue boost in 2024 2H.
  6. S

    Will Intel Foundry Break-Even Before 2028?

    We can see this in another way. In 2023, Samsung electronics reported that about 6B dollars were spent to buy Application Processors(from Qualcomm...etc). This means that Intel foundry will still lose money even if they get 20%(Samsung's smartphone share) of AP foundry share. In other words...
  7. S

    Will Intel Foundry Break-Even Before 2028?

    IFS was losing 4B in 2022(using their new financial model), even if they have in-house customer(Intel products). It's quite surprising because Intel products teams are the single largest leading edge silicon users in the world. Intel products revenue was almost 60B per year. Their modelled...
  8. S

    Intel's Foundry Business discloses a $7B operating loss

    Still Intel expects 18A be a big and profitable node. It should be REALLY great then...I kinda see why they needed to introduce PowerVIA(BSPDN) earlier than competitors...
  9. S

    When Will IFS Losses Peak, Since Admittedly, The Peak is Yet to Come

    Intel's new disclose says followings. (million dollars) (2,100) Lower product profit driven by lower internal revenue (411) Higher period charges related to excess capacity when their products lost revenue 9,371 (from 57,038 to 47,667), foundry lost 2511. So without any further cost...
  10. S

    Alternatives to Shrink for Performance?

    As long as there's value added, we can use everything. For example, in HBM(memory) manufacturing, stacking is used a lot even if price per bit goes up. They can use that because, AI companies are willing to pay A LOT. In logic side, I think there will be a 'in-house design' era where large IT...
  11. S

    GAA Process Video from Applied Materials

    Now we're making 35-atom thick materials then implant it to make PMOS and NMOS...what an amazing technology..
  12. S

    Nvidia introduces Blackwell (800mm2 reticle limit N4P dies)

    BTW, what's going to happen if we start using High NA EUVs later? Can we still get 800mm2~ish single chip? Since AI wants BF-chips, it's little concerning I guess..
  13. S

    Samsung Foundry MPW schedule for 2024

    I think Samsung runs one MPW for each full-node changes. 14nm, 8nm(10nm family), 5nm(7nm family), 4nm(Full node from 7nm. it was announced as 5nm half node at first, but updated later)
  14. S

    The new Cerebras CS-3

    Cerebras uses BF wafer sized single chip(single big chip with spams of cores) and Groq and Tenstorrent uses high density racks(servers with spams of blades, cards...etc). It's quite ok for Groq and Tenstorrent to use Samsung anyway.
  15. S

    Intel Will Have 1 Critical Advantage Over TSMC and Samsung in 2025

    One of the problem Intel has is that there's more mobile customers than HPC customers. CPU and GPUs are high-volume HPC chips but Intel is unlikely to get orders from AMD who is in rear-view mirrors.
  16. S

    Most upcoming Arrow Lake CPUs will leverage TSMC nodes for compute, Intel 20A only for Core i5 and lower: Leak

    I think it's rentable units(RUs) patent. For me it doesn't seem that obvious how it removes SMT
  17. S

    Most upcoming Arrow Lake CPUs will leverage TSMC nodes for compute, Intel 20A only for Core i5 and lower: Leak

    Intel was in chaos for a 6~7 years. So it's not really easy what's really happening there. If the leaker is correct then it's just same as what they did to Meteor lake(2023 Dec. launch, mobile only Intel 4). Maybe they're doing this because they have reserved so much N3B capacity to hedge their...
  18. S

    Intel plots 1nm silicon for 2027 but are the wheels coming off its existing roadmap? 2N6Y?

    This graph tells us a lot(Assuming that it's accurate). Look at the wafer capacity of Intel 4/3 which already got mass production chips(Meteor lake). Comparing its sheer volume to Intel 7(Which also has mass production chips), we can say that their manufacturing is not really recoverd. Maybe...
  19. S

    Samsung’s Foundry Hit with 0% Yield Rate for 3nm GAA Process

    News seems busted. Actually the news doesn't look true to me. Samsung have been maunfacturing mining ASICs for a year, so It's hard to believe that their Galaxy Watch(Exynos W940, small chip) is running 0% yield. Maybe some insider saw failed experiement in certain lot?
  20. S

    SAMSUNG’S 2ND-GEN 3NM PROCESS, SF3, HAS BEGUN TRIAL PRODUCTION

    It could still make sense, if they somehow mass produce GAA-powered Samsung LSI chips(Exynos?) and sell them to market. The real problem Samsung foundry had was not in press release(it's also problem though...), but in broken promises to their customers, even to their LSI counterpart. If foundry...
Back
Top