Array
(
[content] =>
[params] => Array
(
[0] => /forum/whats-new/latest-activity?before_id=97248
)
[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] => 2030770
[XFI] => 1060170
)
[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
exactly it's poorly worded by the article
Friday at 10:22 PM
T
They must have had test chips or something going on for more than few months you can't just validate something in just 6 Months
Friday at 10:22 PM
T
On the Datacenter side, It looks like Intel will fab the Custom Xeons at IFS with support for NVLink and sell it to Nvidia. Nvidia buys...
Friday at 10:22 PM
T
Jensen said that architecture teams have been working on this partnership, close to a year now in the conference call.
Friday at 10:22 PM
T
Agree with all of what you say. But the A100 is also ancient. And that’s before NVIDIA began their extreme co-optimization of systems...
Friday at 10:20 PM
T
Ain't happening there are fundamental difference between what a CPU/GPU is optimized for you can't magically expect everything to work...
Friday at 10:20 PM
T
This is comparing a very old CPUs remember Intel was stuck on 14nm at that time and also never trust first party benchmark
Friday at 10:19 PM
S
yes not to mention as BruceA said the infrastructure is not there and Goverment does a poor job of planning many stuff.
Friday at 9:56 PM
S
Microsoft, brought to you by Huawei...
Friday at 9:54 PM
S
Agree with all of what you say. But the A100 is also ancient. And that’s before NVIDIA began their extreme co-optimization of systems...
Friday at 9:54 PM
I think you nailed it. Microsoft in-house workloads are historic CPU-centric workloads, not AI, which requires entire rethinks of what a...
Friday at 8:06 PM
I think there are two very fundamental problems with their thinking per his statement in the article:
Later, he told CNBC, "It's about...
Friday at 8:06 PM
Azure is the #2 cloud computing company in the world. Their proprietary cloud-native applications include six database management...
Friday at 8:06 PM
Microsoft, brought to you by Huawei...
Friday at 8:05 PM
K
I think you nailed it. Microsoft in-house workloads are historic CPU-centric workloads, not AI, which requires entire rethinks of what a...
Friday at 7:23 PM
Like.
exactly it's poorly worded by the article
Haha.
Microsoft, brought to you by Huawei...
Daniel Nenni reacted to KevinK's post in the thread Microsoft CTO says he wants to swap most AMD and Nvidia GPUs for homemade chips with