China's Defense/Military Breaking News Thread

Status
Not open for further replies.
Xizor

Xizor

Captain
Registered Member
Keeping an eye on the competition -

Please, Log in or Register to view URLs content!




Screenshot_20211030-000137.jpg

The US military-Intel duo's 5nm+ technology uses the RibbonFET transistor design ( departing from the FinFET).

Also, a technology called Powervia is also packed into. A video -
 
G

gelgoog

Lieutenant General
Registered Member
Xsizor said:
Not Samsung but I have read that US uses Nvidea chips to drive AI in many systems. Nvidea semiconductors are manufactured by TSMC.

Whether the contract is high value is not known. But the Intel contract fab reorganization may be there exactly to push out this kind of reliance on TSMC.
Click to expand...

Actually the latest Nvidia generation of chips (Ampere) is being fabbed at Samsung at 8nm instead of TSMC like it used to.
Good luck convincing Nvidia to use Intel fabs. Even if their process was good enough they are competitors and both companies hate each other's guts. At one point Nvidia had a plan to make a X86 compatible processor codenamed Project Denver but because of license and technical issues it was cancelled.

That RibbonFET just looks like a commercial name for GAAFET.
 
Xizor

Xizor

Captain
Registered Member
gelgoog said:
Actually the latest Nvidia generation of chips (Ampere) is being fabbed at Samsung at 8nm instead of TSMC like it used to.
Good luck convincing Nvidia to use Intel fabs. Even if their process was good enough they are competitors and both companies hate each other's guts. At one point Nvidia had a plan to make a X86 compatible processor codenamed Project Denver but because of license and technical issues it was cancelled.

That RibbonFET just looks like a commercial name for GAAFET.
Click to expand...
I missed this. Interesting that Samsung has started to manufacture the Ampere series.

From a website -
General-purpose graphics processing (GPGPU) is becoming the cornerstone of digital signal processing in aerospace and defense applications like radar and sonar signal processing, image processing, hyperspectral sensor imaging, signals intelligence, electronic warfare, and persistent surveillance.

The primary designers of GPGPU chips in the U.S. today are NVIDIA Corp. in Santa Clara, Calif., and Advanced Micro Devices Inc. (AMD) in Sunnyvale, Calif.

So Intel Xeon and Nvidia Tesla series are being used by US MIC.
 
  • Like
Reactions: crx
Status
Not open for further replies.
Top