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.

Nvidia Speeds Key Chipmaking Computation by 40x

123 pointsby afrcncabout 2 years ago

6 comments

iandanforthabout 2 years ago
Aside: Nvidia named this cuLitho, which I learned from my Spanish speaking mother-in-law basically looks like they named it 'butt'. So if you see a bunch of rear-end related memes about this software you know why!
评论 #35313392 未加载
ChuckNorris89about 2 years ago
It&#x27;s just sad how absent AMD is from such innovative uses of GPUs. It wouldn&#x27;t bother me too much if at least their GPUs were much more affordable than Nvidia&#x27;s, but they&#x27;re not. They&#x27;re at best playing catch-up months or years later with slight price discounts (the Steam HW survey still reflects this market discrepancy)<p>And I&#x27;m not talking about gimmicks like RTX, I&#x27;m talking about all these cool use cases around ML and DL like background noise cancelling, video upscaling, camera eye contact real-time deepfakes and now this. And that&#x27;s if you ignore all the mind-blowing research papers put out by Nvidia which aren&#x27;t featured in consumer apps yet.<p>This is Nvidia&#x27;s biggest moat and AMD isn&#x27;t even in the race here and for some reason Lisa Su seems to not give enough of a shit to compete.<p>I hate Nvidia for their price gouging and anti-consumer practices, but at least they haven&#x27;t gotten complacent and are innovating on all fronts to keep pushing the envelope. Massive respect for the tech leadership at Nvidia.
评论 #35314186 未加载
评论 #35314968 未加载
评论 #35313611 未加载
评论 #35313801 未加载
评论 #35314645 未加载
bottlepalmabout 2 years ago
That&#x27;s pretty cool they&#x27;re using GPUs to design GPUs.
评论 #35313835 未加载
评论 #35312207 未加载
评论 #35312907 未加载
评论 #35312925 未加载
评论 #35312520 未加载
jmartricanabout 2 years ago
I noticed TSMC and ASML were mentioned but not Intel. I wonder if this will set Intel further behind TSMC.
ameliusabout 2 years ago
How much does that mean in practice, considering:<p>- the computation output depends only on local features (my guess)<p>- most transistors look the same, so you can cache these results heavily<p>- the same holds for the interconnect layers
评论 #35314733 未加载
评论 #35314197 未加载
ftxbroabout 2 years ago
The chipmaking computation is inverse lithography, and the Nvidia system that is speeding it up is cuLitho on DGX H100.<p>I like how inverse lithography and neural network backpropagation were both techniques introduced in the 1980s and now we are finally seeing them both come to life, so to speak, with our sufficiently advanced GPUs.