Array
(
    [content] => 
    [params] => Array
        (
            [0] => /forum/threads/intel-announces-its-18a-node-is-ahead-of-schedule-so-who-is-going-to-design-to-20a.15895/
        )

    [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] => 2021770
            [XFI] => 1050270
        )

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

Intel announces its 18A node is ahead of schedule so who is going to design to 20A?

Daniel Nenni

Admin
Staff member
Scott Jones did a nice writeup of this last week:

2024 – in the first half Intel 20A (20 angstrom = 2nm) process is due with a 15% performance improvement. This will be Intel’s first HNS (they call it RibbonFET) and they will also introduce back side power delivery (they call this PowerVia). The backside power delivery addresses IR power drops while making front side interconnect easier. We are estimating a 1.6X density improvement. In the second half of 2024 Intel’s 18A process is due with a 10% performance improvement. We are estimating a 1.06X density improvement making this another half node. This process has been pulled in from 2025 and Intel says they have delivered test devices to customers.

Intel will launch an 18A half node 6 months after 20A? So who is going to design to 20A? As with other half nodes like N7, N7+, and N6, they use the same fab and I expect Intel will do the same. Generally the first node is the biggest N7 versus N6 and N5 versus N4 but I expect the opposite from 20A and 18A. TSMC however spaces their half nodes one year apart versus 6 months. Thoughts?
 
Intel has talked about 20A being primarily for internal use as a kind of test case and then 18A as the improved process that gets adopted by foundries. 4nm and 3nm are similar, 4nm more for internal use and then 3nm for foundry.
 
Back
Top