Array
(
    [content] => 
    [params] => Array
        (
            [0] => /forum/threads/microsofts-new-internally-designed-ai-and-cloud-server-cpu-chips.19146/page-2
        )

    [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
)

Microsoft's new internally designed AI and Cloud Server CPU chips

Simple answer... make shuttles, especially those of us who can make PDKs (models, stdcells, pcells), layout automation, DRC and LVS checkers, etc.

What IP takes a long time to port over?
I'm guessing the validation part would take longer than the actual time to port.
 
High speed SerDes... is NRZ and 500fs of jitter acceptable?

As far as SRAM, would the foundry supply or external design house?
 
I'm guessing the validation part would take longer than the actual time to port.
The validation boards, methods, etc are already established. Odds are, calibration was already added.

Provide the DRM and shuttles. IP will be developed quicker than you guys think. Naysayers ...

Whether you think you can or your can't, you're right. -- Ford
 
Back
Top