Array
(
[content] =>
[params] => Array
(
[0] => /forum/index.php?members/tanj.16713/latest-activity&before_id=44518
)
[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
)
You are currently viewing SemiWiki as a guest which gives you limited access to the site. To view blog comments and experience other SemiWiki features you must be a registered member. Registration is fast, simple, and absolutely free so please,
join our community today !
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser .
T
Neither one of these documents is recent enough to be news, or close to the quoted length. Interesting nonetheless.
Mar 31, 2024
T
Figure around $30 per W for average of GPUs and other machines plus infrastructure and Capex to provide the power. So, around 3 to 4GW...
Mar 31, 2024
T
It depends on where, scale, and technical designs. It should have several data enterers across America. Certain areas in US might have...
Mar 31, 2024
T
This is the Oct 2023 release referred to in the Reuters presser:
https://www.bis.doc.gov/index.php/about-bis/newsroom/2082
It updates a...
Mar 31, 2024
T
I believe this report from the White House titled "Building Resilient Supply Chains, Revitalizing American Manufacturing, and Fostering...
Mar 31, 2024
T
Business Insider is quoting The Information, and that article reads like it was copied almost verbatim from the Reuters article you...
Mar 29, 2024
T
OneAPI, CUDA, and ROCM are intermediate levels. PyTorch and TensorFlow are modelling languages (though TF has its own modelling layer...
Mar 27, 2024
T
OneAPI is based on SYCL, which is a multi-vendor industry specification.
https://www.khronos.org/sycl/
OneAPI and CUDA are based on...
Mar 27, 2024
T
Tanj replied to the thread
Fusion needed for AI .
More efficient machines and more efficient algorithms.
Mar 27, 2024
T
Sam Altman has invested hundreds of millions of dollars in nuclear fusion? And it is likely decades away? Is this a ChatGPT generated...
Mar 27, 2024
T
4NP not necessarily the same as N4P but still customized for NVIDIA.
Mar 21, 2024
T
There are two situations, chiplet is at the end of a spoke, or chiplet is in the middle of a fabric. At the end of a spoke the...
Mar 21, 2024
T
Percentage was the wrong word. A better way to describe it was if you have I don't know let's call it 5-10% of the die is your die to...
Mar 21, 2024
T
Not very big. This paper from Nvidia probably describes the pre-production version of their chip to chip fabric Phy...
Mar 20, 2024
T
All of their DC products have been at or near the ret limit for the better part of a decade. To me this is hardly concerning. Also the...
Mar 20, 2024