Array
(
    [content] => 
    [params] => Array
        (
            [0] => /forum/whats-new/latest-activity?before_id=107292
        )

    [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
)

Latest activity

What's new Featured content New posts Latest activity

N

NY_Sam2 replied to the thread Applied Materials Unveils Transistor and Wiring Innovations for Faster AI Chips.

Logic Contact from W to Mo, could be a key innovation for GAA from 1st generations to 2nd generations, "traditional tungsten contacts...

Feb 11, 2026
C

C-4 replied to the thread SpaceX wants to put 1 million solar-powered data centers into orbit.

Is radiation hardening a problem?

Feb 11, 2026
Daniel Nenni reacted to Fred Chen's post in the thread CXMT Plans to Allocate a “Large Chunk” of Its DRAM Production to HBM3, Hoping to Compete in the AI Race with Like.

Feb 10, 2026 at 11:18am EST China's CXMT is expanding its presence in the HBM market, aiming to capitalize on the AI frenzy, as the...

Feb 11, 2026
F

Fred Chen posted the thread CXMT Plans to Allocate a “Large Chunk” of Its DRAM Production to HBM3, Hoping to Compete in the AI Race in SemiWiki Main Forum ( Ask the Experts! ).

Feb 10, 2026 at 11:18am EST China's CXMT is expanding its presence in the HBM market, aiming to capitalize on the AI frenzy, as the...

Feb 11, 2026
F

Fred Chen replied to the thread "ASML has a messy software stack" thread from LaurieWired.

So that's like ~100 MB of code storage?

Feb 11, 2026
S

swka replied to the thread Cisco launched its Silicon One G300 AI networking chip in a move that aims to compete with Nvidia and Broadcom..

do they have system that actually goes to the PB connection for training? SRAM along, while seems to be big, is far from enough. Perhaps...

Feb 11, 2026
Daniel Nenni posted the thread Applied Materials Unveils Transistor and Wiring Innovations for Faster AI Chips in SemiWiki Main Forum ( Ask the Experts! ).

New chipmaking systems boost the energy-efficient performance of Gate-All-Around transistors and wiring at 2nm and beyond Viva™ pure...
Feb 11, 2026
D

daniellahill replied to the thread Synopsys and ReversingLabs Sign Agreement to Enhance Software Supply Chain Risk Management.

It’s encouraging to see discussions around making Intel Foundry’s supply chain more resilient, sustainable, and secure. With all the...

Feb 11, 2026
Daniel Nenni replied to the thread Automation key to avoiding economic, social and environmental collapse, the SemiWiki community key.

6 US states want to halt data centers. Here's what could happen. https://www.yahoo.com/finance/video/6-us-states-want-halt-213125286.html

Feb 11, 2026
S

swka replied to the thread Cisco launched its Silicon One G300 AI networking chip in a move that aims to compete with Nvidia and Broadcom..

curious how Cerebras handles large memory access. No matter how much SRAM they have on chips, it's no where near what HBM provides

Feb 11, 2026
S

swka reacted to KevinK's post in the thread Cisco launched its Silicon One G300 AI networking chip in a move that aims to compete with Nvidia and Broadcom. with Like.

And then there is Cerebras, where scale‑up is essentially “inside one wafer” (one CS system), and scale‑out is multiple wafers connected...

Feb 11, 2026
Daniel Nenni posted the thread Taiwan’s tech giants accelerate US expansion in SemiWiki Main Forum ( Ask the Experts! ).

TSMC and Foxconn expand overseas operations as AI server demand surges TAIPEI (Taiwan News) — Taiwanese tech companies are...
Feb 11, 2026
K

KevinK replied to the thread Cisco launched its Silicon One G300 AI networking chip in a move that aims to compete with Nvidia and Broadcom..

And then there is Cerebras, where scale‑up is essentially “inside one wafer” (one CS system), and scale‑out is multiple wafers connected...

Feb 11, 2026
AmandaK posted the thread Ainekko Merges with Veevx, Expands Open Silicon Platform with Breakthrough Memory and Embedded AI Capabilities in Silicon Catalyst.

Brings together Raspberry Pi DNA, MRAM-powered AI memory, and open source hardware to redefine the future of edge silicon SAN...

Feb 11, 2026
AmandaK posted the thread Arteris Technology Deployed More Broadly by NXP to Accelerate Edge AI Leadership in Arteris.

CAMPBELL, Calif. – February 11, 2026 – Arteris, Inc. (Nasdaq: AIP), a leading provider of semiconductor technology for accelerating...

Feb 11, 2026

Show older items