Intel to Make 3nm Technology More Accessible to IFS Customers

US chip industry labor
(Image credit: SIA)

Intel and Synopsys this week extended their EDA and IP partnership to the company's Intel 3 and Intel 18A manufacturing technologies. In line with the agreement, Synopsys is set to develop its standardized interface IP for Intel's 3nm and 1.8nm-class production nodes, which will be beneficial for Intel Foundry Services (IFS) customers adopting these fabrication processes. Meanwhile, a standout aspect of this announcement is Intel's intention to extend its 3nm-class node to a wider array of external clients.

While chip designers tend to invest a lot into differentiating their IP, most of them tend to license IP-like interfaces and memory controllers. To that end, the availability of an industry-standard IP portfolio of interfaces from Synopsys is crucial for the success of new process technologies, such as the upcoming Intel 3 and Intel 18A, as it enables chip developers to streamline their work and shrink the time-to-market. Unfortunately, it is unclear when exactly Synopsys is set to be ready with its IP for Intel 3, even though that is set to be ready for manufacturing this year. Intel 18A has a bit more time, as it's set to be ready for production in 2H 2024.

The intriguing part is that Intel is now extending its IFS offerings to the Intel 3 fabrication process, which is a major refinement of its Intel 4 node and does not use any of the company's ambitious innovations like gate-all-around RibbonFET transistors or the backside power rail called PowerVia. Compared to its predecessor, Intel 3 promises a 18% higher performance per watt, a denser high-performance library, reduced via resistance, and increased intrinsic drive current, which is beneficial primarily for datacenter system-on-chips. Indeed, Intel has announced zero Intel 3-based client products so far, but three datacenter SoCs: Xeon-branded Granite Rapids and Sierra Forest processors, as well as a custom SoC for a major cloud datacenter provider.

The extension of the IP partnership with Synopsys will enable Intel to make its Intel 3 node — a fabrication technology that Intel barely advertised as an offering for IFS customers — more accessible to a wider range of interested parties. That also implies that there are potentially such interested parties.

As for the Intel 18A node, this is a superior version of the company's Intel 20A process technology that promises up to a 10% improvement in performance per watt, a refined RibbonFET architecture, and line width reduction, which implies a higher transistor density. It will be crucial for Intel 18A to have industry-standard interface IP readily available as soon as possible, as developing things like memory or PCIe controllers and PHY on a 1.8nm node is both expensive and time consuming.

TOPICS
Anton Shilov
Contributing Writer

Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.

  • ikjadoon
    Surely with all these press releases, nearly 15 months after Gelsinger launched IFS "2.0", can't IFS share one major fabrication win?

    Intel's upcoming CPUs still use TSMC, even as Intel has comparable nodes & capacity. I'm still waiting for "Apple or Sony" to take up Intel's offer 12 years ago.

    Reply
  • thisisaname
    Apple is happy with TSMC why would it want to go with Intel when they have removed all Intel's chips from their gear?
    Reply
  • JamesJones44
    ikjadoon said:
    Intel's upcoming CPUs still use TSMC
    Only for the iGPU tile. I don't read much into that other than potential capacity offload at this stage. If that is the case in 3 generations then it's a different story
    Reply
  • ikjadoon
    JamesJones44 said:
    Only for the iGPU tile. I don't read much into that other than potential capacity offload at this stage. If that is the case in 3 generations then it's a different story

    If IFS is worried about its CPUs exceeding IFS capacity, then external customers probably should be worried, too, though, right? That is, vendors might not be willing to trust Intel's capacity claims until Intel has a few generations of its nodes delivering capacity for Intel's own products.

    Does anyone want to be "second", if Intel isn't ready to be first?

    It took Apple more than a few generations to end its dual-sourcing from Samsung & TSMC, and commit to TSMC. I don't forget that Intel's entire GPU line-up is fabbed at TSMC, including all mobile, workstation, and desktop Arc dGPUs:

    Intel Arc A310: TSMC N6
    Intel Arc A380: TSMC N6
    Intel Arc A750: TSMC N6
    Intel Arc A770: TSMC N6
    etc.

    These GPUs are likely extremely low volume. Of course, maybe future Arc generations use Intel nodes? But, rumors indicate Intel will again use TSMC nodes for Intel's flagship-to-low-end Arc GPU products.

    https://www.tomshardware.com/news/intel-battlemage-celestial-gpus-tsmc-report
    That would mean even in 2026, Intel backing TSMC for its GPU foundry needs. Of course, these are rumors. These are future generations, but I imagine Intel wants to promote any foundry wins, just as frequently as it promotes these ancillary updates (like the OP).
    Reply
  • TerryLaze
    thisisaname said:
    Apple is happy with TSMC why would it want to go with Intel when they have removed all Intel's chips from their gear?
    Apple wants to pay as little as possible which is why they don't want to pay the overhead for a full intel CPU, but they do have to manufacture their M1 cpus somewhere anyway, so unless you can come up with a reason why Apple actively hates intel I don't see a reason why Apple would care whom they pay the money to manufacture their M1.
    Reply
  • TerryLaze
    ikjadoon said:
    If IFS is worried about its CPUs exceeding IFS capacity, then external customers probably should be worried, too, though, right? That is, vendors might not be willing to trust Intel's capacity claims until Intel has a few generations of its nodes delivering capacity for Intel's own products.

    Does anyone want to be "second", if Intel isn't ready to be first?
    TSMC might be more efficient in making GPU tiles until intel makes a FAB that is special made for it.
    As far as I understand it intel has only FABs that are 100% specialized towards CPUs now and it might be more expensive for them to make gpu tiles on a CPU FAB then to pay TSMC to make them.
    Just a guess.
    Reply
  • thisisaname
    TerryLaze said:
    Apple wants to pay as little as possible which is why they don't want to pay the overhead for a full intel CPU, but they do have to manufacture their M1 cpus somewhere anyway, so unless you can come up with a reason why Apple actively hates intel I don't see a reason why Apple would care whom they pay the money to manufacture their M1.
    I have no proof they hate Intel.

    As for why they would not swap the cost of changing design to work with Intel would be substantial.
    Also having worked quite closely with TSMC I would be surprised if they have tailored their designs to be efficiently manufactured by them.
    Reply
  • thestryker
    TerryLaze said:
    TSMC might be more efficient in making GPU tiles until intel makes a FAB that is special made for it.
    As far as I understand it intel has only FABs that are 100% specialized towards CPUs now and it might be more expensive for them to make gpu tiles on a CPU FAB then to pay TSMC to make them.
    Just a guess.
    Anything they produced in house would have to take away from CPU production which undoubtedly is more profitable. I don't think they'll move GPUs in house until they have the majority of fabs producing 20a/18a or beyond.
    Reply
  • TerryLaze
    thisisaname said:
    I have no proof they hate Intel.

    As for why they would not swap the cost of changing design to work with Intel would be substantial.
    Also having worked quite closely with TSMC I would be surprised if they have tailored their designs to be efficiently manufactured by them.
    Intel works hard with ARM to make ARM designs easily fabbable on intel FABs, it won't do anything for current designs probably but it will definitely make it easy for future products. The Apple CPUs are just ARM CPUs with Apple design.
    Also in general intel might just pay the expense for any design changes themselves to get IFS going.
    https://www.intel.com/content/www/us/en/newsroom/news/intel-foundry-arm-announce-multigeneration-collaboration-leading-edge-soc-design.html
    Reply