TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Can We Break the 2nm Barrier in Silicon Fabrication?

28 pointsby sfmthover 4 years ago

8 comments

kemotepover 4 years ago
So we have options and this is all ten years out before we actually hit this wall.<p>However, according to this, our current solutions to the issues faced at sub-20nm lithography were developed by IBM in the 90&#x27;s. So that is the question.<p>What technique exists today that will be used for the next 30 years?<p>I am envisioning a true death of &quot;Moore&#x27;s Law&quot; but we will have time before we encounter the limits of Amdahl&#x27;s law[0] in the use of chiplets and other dedicated hardware. Apple has their T2 and security enclaves, NVIDIA has tensor cores and other fixed function silicon, AMD is proving chiplets with seperate compute dies and I&#x2F;O dies works well, Intel is now working on the same but for GPU&#x27;s[1] ontop of compute and I&#x2F;O, and the new Playstation 5 has a dedicated ARM CPU for the SSD.<p>Having dedicated silicon for specific tasks (such as encryption, ray-tracing, storage, networking, and so on), or even an FPGA of some sort will likely be the future.<p>It will be like the 90&#x27;s again with northbridge and southbridge chips and 5 or 6 expansion cards.<p>But I am excited to see the solutions that will drive computers for the next 30 years.<p>[0]:<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Amdahl%27s_law?wprov=sfla1" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Amdahl%27s_law?wprov=sfla1</a><p>[1]:<a href="https:&#x2F;&#x2F;www.anandtech.com&#x2F;show&#x2F;16021&#x2F;intel-moving-to-chiplets-client-20-for-7nm" rel="nofollow">https:&#x2F;&#x2F;www.anandtech.com&#x2F;show&#x2F;16021&#x2F;intel-moving-to-chiplet...</a>
评论 #26205686 未加载
评论 #26205844 未加载
rrssover 4 years ago
original: <a href="https:&#x2F;&#x2F;semiengineering.com&#x2F;breaking-the-2nm-barrier&#x2F;" rel="nofollow">https:&#x2F;&#x2F;semiengineering.com&#x2F;breaking-the-2nm-barrier&#x2F;</a>
payambover 4 years ago
&gt; Seyed Farhad Modaresi &gt; Editor-in-Chief and the Owner<p>&gt; High school diploma<p>Sounds like a credible scientific journal
评论 #26205739 未加载
评论 #26205820 未加载
评论 #26205904 未加载
评论 #26205508 未加载
评论 #26205729 未加载
Lind5over 4 years ago
Copyright violation of Semiconductor Engineering <a href="https:&#x2F;&#x2F;semiengineering.com&#x2F;breaking-the-2nm-barrier&#x2F;" rel="nofollow">https:&#x2F;&#x2F;semiengineering.com&#x2F;breaking-the-2nm-barrier&#x2F;</a>
评论 #26206210 未加载
baybal2over 4 years ago
Best to ask is it doable in practice?<p>E-beam lithography can get to real 1nm in practice quite easily, but you can spend a week on a CPU sized IC for a single exposure.
abdullahkhalidsover 4 years ago
I would rather we figure out how to manufacture 30nm at 1&#x2F;100 the capital cost that it does now.<p>You can&#x27;t really democratize compute, if there is a global oligopoly on manufacturing processor chips.
评论 #26206004 未加载
AcerbicZeroover 4 years ago
I wonder if any of those higher temperature (relatively) super conductors that were at the top of the page recently will be of value here?
评论 #26205932 未加载
hackopackoover 4 years ago
atomically precise manufacturing with diamondoid mechanosynthesis or something maybe? xprize elon or bill gates fund this plz <a href="https:&#x2F;&#x2F;www.researchgate.net&#x2F;publication&#x2F;266583736_A_Minimal_Toolset_for_Positional_Diamond_Mechanosynthesis" rel="nofollow">https:&#x2F;&#x2F;www.researchgate.net&#x2F;publication&#x2F;266583736_A_Minimal...</a>