@thomasfuchs 1000x shorter and 1000x narrower : 1,000,000x less 2-dimensional area.
A *million* 3nm transistors would fit in the same wafer area as one of those old 3-micron transistors.
@thomasfuchs 1000x shorter and 1000x narrower : 1,000,000x less 2-dimensional area.
A *million* 3nm transistors would fit in the same wafer area as one of those old 3-micron transistors.
@thomasfuchs my 20 year old self still can't fathom that a breath of wind could whiff 512GB from the table for the doggo to gulp it without serious side effects
@thomasfuchs The more I've learned about processor manufacturing, the more I'm convinced it is likely our biggest accomplishment. Such insane precision at SCALE is just incredible. Really dealing with manufacturing at “near” atom level.
@thomasfuchs an ARM cortex m0 fits into two transistors of the 6502. And that was almost ten years ago.
@thomasfuchs sorry to tell you, but the modern naming convention of processes is no longer a technical term to do with length, and is only a marketing term. See 3rd paragraph of wiki page: https://en.wikipedia.org/wiki/3_nm_process?wprov=sfla1 . However, it's still several orders of magnitude smaller, so your point isn't undermined much!
@thomasfuchs I dont think that 3m *technology node* uses transistor whose dimensions are 3nm. They are still significantly smaller than 3um.
@thomasfuchs I wire-wrapped two additional banks of eight 4116 chips to give my first machine a full 48kb of RAM. It took a shoebox sized enclosure. Obviously, the density could have been increased somewhat, but …
GNU social JP is a social network, courtesy of GNU social JP管理人. It runs on GNU social, version 2.0.2-dev, available under the GNU Affero General Public License.
All GNU social JP content and data are available under the Creative Commons Attribution 3.0 license.