Array
(
[content] =>
[params] => Array
(
[0] => /forum/whats-new/latest-activity?before_id=109221
)
[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] => 2030970
[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 .
K
The issue is rapid evolution and specialization of processor architectures. Two things happened about 2-3 years ago that radically...
Tuesday at 2:38 PM
K
This Groq 3 initiative by Nvidia is a curiosity to me. So all this time Nvidia knew inference processing was coming up fast (they...
Tuesday at 2:16 PM
K
It looks like Samsung is making the Groq 3 LPU (Language Processing Unit) inference chip for Nvidia. Certainly SRAM heavy but also...
Tuesday at 2:16 PM
K
Samsung shares rise after Nvidia's Huang flags tie-up on new AI chips
By Hyunjoo Jin
March 16, 20265:20 PM CDTUpdated 12 hours ago
A...
Tuesday at 2:16 PM
I wonder if Pat G ever tried to approach Musk for chip business. I feel like they both have some traits in common.. Hubris, for...
Tuesday at 1:41 PM
It looks like Samsung is making the Groq 3 LPU (Language Processing Unit) inference chip for Nvidia. Certainly SRAM heavy but also...
Tuesday at 11:05 AM
S
Memory Chips are also made in Foundry so the title is correct but i still confused it to a logic foundry deall
Tuesday at 10:45 AM
J
Tesla just finished their AI5 design two months ago. It will take at least a year before high volume production can start at either...
Tuesday at 9:35 AM
B
Strength in HBM4 memory chips corresponding to strength in Samsung Foundry.
Tuesday at 9:30 AM
B
Samsung shares rise after Nvidia's Huang flags tie-up on new AI chips
By Hyunjoo Jin
March 16, 20265:20 PM CDTUpdated 12 hours ago
A...
Tuesday at 9:27 AM
Key Takeaway:
Nvidia has projected that the revenue opportunity for its artificial intelligence chips could reach at least $1 trillion...
Tuesday at 8:34 AM
C
Let’s look at this logically. Let’s take into account all of Elons promises and how frequently they don’t come true? Let’s go through...
Tuesday at 8:18 AM
J
Elon kicked out all but two of xAI's founders and is now rebuilding it from scratch as he put it yesterday. So what will he be running...
Tuesday at 7:50 AM
SK Hynix presented a recent IEEE paper describing an architecture combining High-Bandwidth Memory (HBM) speed and High-Bandwidth Flash...
Tuesday at 7:22 AM
https://zdnet.co.kr/view/?no=20260317111538
SK Group Chairman Chey Tae-won predicted that the supply shortage in the global memory...
Tuesday at 5:47 AM
kvas reacted to Xebec's post in the thread Musk says Tesla's mega AI chip fab project to launch in seven days with
Haha.
I wonder if Pat G ever tried to approach Musk for chip business. I feel like they both have some traits in common.. Hubris, for...
Xebec replied to the thread Samsung Foundry nabs Nvidia.It looks like Samsung is making the Groq 3 LPU (Language Processing Unit) inference chip for Nvidia. Certainly SRAM heavy but also...
Daniel Nenni posted the thread Nvidia Says AI Chip Market Could Hit $1 Trillion by 2027 — and It’s Coming for All of It in SemiWiki Main Forum ( Ask the Experts! ).Key Takeaway: Nvidia has projected that the revenue opportunity for its artificial intelligence chips could reach at least $1 trillion...
Like.
Let’s look at this logically. Let’s take into account all of Elons promises and how frequently they don’t come true? Let’s go through...
user nl replied to the thread SK Hynix proposes HBM and HBF hybrid for LLM inference.https://zdnet.co.kr/view/?no=20260317111538 SK Group Chairman Chey Tae-won predicted that the supply shortage in the global memory...