semicon_wiz's profile picture.

Paradinight

@semicon_wiz

Paradinight 已轉發

China Eyes Chip-Stacking Path to Narrow the Gap with NVIDIA tpu.me/78ad

TechPowerUp's tweet image. China Eyes Chip-Stacking Path to Narrow the Gap with NVIDIA tpu.me/78ad

Paradinight 已轉發

TSMC、次世代半導体「CFET」の基本回路が動作 30年代量産へ前進 xtech.nikkei.com/atcl/nxt/colum… 2033年かぁ… まあここでGAAとまとめられている中でも結構構造は変わるはず。 どうやって開発費の元を取るのか、AI特需はその原資になるのか、判んないですねぇ。

R3000C's tweet image. TSMC、次世代半導体「CFET」の基本回路が動作 30年代量産へ前進
xtech.nikkei.com/atcl/nxt/colum…

2033年かぁ…
まあここでGAAとまとめられている中でも結構構造は変わるはず。
どうやって開発費の元を取るのか、AI特需はその原資になるのか、判んないですねぇ。

Paradinight 已轉發

Thanks for sharing this. Just started watching his lectures on number theory. Awesome stuff as it should be from a Fields Medallist.

Today is Richard Borcherds’ birthday, not only a great mathematician and Fields Medal winner, but also a great teacher with probably the best YouTube channels on advanced mathematics: youtube.com/channel/UCIyDq…

Saman_Habibi_E's tweet image. Today is Richard Borcherds’ birthday, not only a great mathematician and Fields Medal winner, but also a great teacher with probably the best YouTube channels on advanced mathematics: youtube.com/channel/UCIyDq…
Saman_Habibi_E's tweet image. Today is Richard Borcherds’ birthday, not only a great mathematician and Fields Medal winner, but also a great teacher with probably the best YouTube channels on advanced mathematics: youtube.com/channel/UCIyDq…


Paradinight 已轉發

Paradinight 已轉發

Huawei's patent for 2nm-class patterning without EUV has been published. patents.google.com/patent/CN11930…

DrFrederickChen's tweet image. Huawei's patent for 2nm-class patterning without EUV has been published.
patents.google.com/patent/CN11930…

Paradinight 已轉發

Texas Elektronikgruppe, Inc. FLX-5024, 256 × 8 SRAM Silicon-on-Sapphire 28nm 2MRad/s Radiation Hardnening

usgraphics's tweet image. Texas Elektronikgruppe, Inc.
FLX-5024, 256 × 8 SRAM
Silicon-on-Sapphire 28nm
2MRad/s Radiation Hardnening

Paradinight 已轉發

Taiwan is a merchant state, and it’s interesting to draw the historical comparison to medieval Venice - perhaps the most successful merchant state in history. A little post-turkey history lesson: For about 300 years (from 1300 to 1600), Venice (more specifically Murano) had an…

Citrini7's tweet image. Taiwan is a merchant state, and it’s interesting to draw the historical comparison to medieval Venice - perhaps the most successful merchant state in history. A little post-turkey history lesson:

For about 300 years (from 1300 to 1600), Venice (more specifically Murano) had an…

Next level sad… this is a semiconductor researcher not a fucking cartel member. TSMC knows they are going to be losing process leadership and are desperate to do anything to stop it. Completely crosses all lines of normality, people change jobs all the time what are you going…



Paradinight 已轉發

In its latest Value Up Corporate Report released today, SK Hynix indicated plans to adopt hybrid bonding technology for HBM products exceeding 20 layers by 2029.

rwang07's tweet image. In its latest Value Up Corporate Report released today, SK Hynix indicated plans to adopt hybrid bonding technology for HBM products exceeding 20 layers by 2029.

Paradinight 已轉發

Intel Sees 5,000 W GPUs Possible with Integrated Voltage Regulators tpu.me/jdbb

TechPowerUp's tweet image. Intel Sees 5,000 W GPUs Possible with Integrated Voltage Regulators tpu.me/jdbb

Paradinight 已轉發

The internal bandwidth of monolithic 3D DRAM is much higher than HBM because TSVs occupy substantial area on both the logic base die and DRAM dies, limiting how many vertical connections can be provisioned and thereby capping internal bandwidth. dl.acm.org/doi/10.1145/37…


Interesting talk by Dong Hyuk Woo from Samsung at IBM think lab November 2025. Spoke about the inefficiencies of HBM and CoWoS for AI applications, and the need to customize the memory and 3D stack.

semicon_wiz's tweet image. Interesting talk by Dong Hyuk Woo from Samsung at IBM think lab November 2025. Spoke about the inefficiencies of HBM and CoWoS for AI applications, and the need to customize the memory and 3D stack.
semicon_wiz's tweet image. Interesting talk by Dong Hyuk Woo from Samsung at IBM think lab November 2025. Spoke about the inefficiencies of HBM and CoWoS for AI applications, and the need to customize the memory and 3D stack.

Paradinight 已轉發

Jensen is monitoring the TPUs almost in real time…

jukan05's tweet image. Jensen is monitoring the TPUs almost in real time…

United States 趨勢

Loading...

Something went wrong.


Something went wrong.