TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

IBM says it has made working versions of 7nm chips

239 点作者 mattee将近 10 年前

16 条评论

awalton将近 10 年前
Let&#x27;s all realize that all of these research branches have been playing around with 10nm and 7nm chips for years now - the fact IBM cobbled together some working chip isn&#x27;t surprising. Getting it to production is really the vastly more important part.<p>This press release is equivalent to &quot;Scientists Cures Diabetes in Mice&quot; - a breakthrough that happens about a half dozen times a year but has still yet to make it from the lab to the FDA.<p>The timing of this press release is entirely to boost investor confidence in IBM and GlobalFoundries given Intel&#x27;s recent announcement of delays at the 10nm process node.<p>edit:<p>The Ars article is vastly better than the above link: <a href="http:&#x2F;&#x2F;arstechnica.co.uk&#x2F;gadgets&#x2F;2015&#x2F;07&#x2F;ibm-unveils-industrys-first-7nm-chip-moving-beyond-silicon&#x2F;" rel="nofollow">http:&#x2F;&#x2F;arstechnica.co.uk&#x2F;gadgets&#x2F;2015&#x2F;07&#x2F;ibm-unveils-industr...</a>
评论 #9857087 未加载
评论 #9857020 未加载
评论 #9857602 未加载
评论 #9859224 未加载
RoboTeddy将近 10 年前
Great talk that describes how modern (as of 2011) computer chips are manufactured: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=NGFhc8R_uO4" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=NGFhc8R_uO4</a>
评论 #9856909 未加载
评论 #9856598 未加载
评论 #9859560 未加载
jtchang将近 10 年前
No mention of Intel anywhere in the article and how far along they are. Also 7nm blows my mind. I mean current CPUs already blow my mind with how tiny the transistors are getting.<p>And specially stabilized buildings? &quot;NOBODY MOVE! WE&#x27;RE ETCHING!&quot;
评论 #9856597 未加载
评论 #9857441 未加载
评论 #9856447 未加载
评论 #9856436 未加载
leni536将近 10 年前
The lattice spacing of silicon is ~0.54nm so 7nm is around 13 lattice spacing, it&#x27;s really impressive. Slowly but surely we will hit atomic limits.
评论 #9856838 未加载
BinaryIdiot将近 10 年前
Wow, 7 nanometer is incredible! I wonder how small they can get silicon &#x2F; silicon-germanium based chips before we have to resort to other techniques such as light processors (since light can be closer and even cross each other without issue). 10 nanometers that they&#x27;re introducing next year is also incredible, at least to me since I&#x27;m not a hardware engineer and can&#x27;t imagine how difficult manufacturing these are.
评论 #9856479 未加载
评论 #9856505 未加载
评论 #9856536 未加载
评论 #9856435 未加载
JoachimS将近 10 年前
Very interesting. Good to see that the article points out that going from working transistors to commercial viable industrial process is also a big challenge. There are a lot of technologies and industry players that need to solve big problems before the node can start deliver. But that is what ITRS is for.<p>Also, interesting to see how things like e-beam litography is pushed once again at least a node into the future. We (as in they) are still able to tune and optimize on the same infrastructure.
graycat将近 10 年前
As I recall, there is microelectronics fab work in Taiwan, South Korea, and, in the US, at IBM and Intel, at least. And maybe China and Russia are trying to get caught up in fabs.<p>I wonder: What organization, really, is mostly responsible for the newer fabs? I mean, do each of Samsung, Intel, IBM, etc. do everything on their own? Or is there a main company, maybe Applied Materials, with some help from, say, some small company for UV sources, some optics from, maybe, Nikon, some mechanical pieces, etc., that does the real work for all the fabs?<p>7 nm -- what speed and power increases will that bring over 14 nm, 22 nm or whatever is being manufactured now, etc.?<p>Long live Moore&#x27;s law! It ain&#x27;t over until the fat lady sings, and I don&#x27;t hear any fat lady yet!
评论 #9859523 未加载
评论 #9858928 未加载
nicholas73将近 10 年前
The press articles about this generally are misleading in that they use Silicon-Germanium as the catch phrase that&#x27;s represents the breakthrough. Whereas in fact SiGe processes have been available for at least a decade. I know this because I developed chips for an IBM SiGe process a decade ago, and in college I did a research paper on semiconductor &quot;superlattices&quot; using an old textbook from our school library. It&#x27;s not a new technology by any means.<p>IBM&#x27;s 7nm is a great accomplishment for sure, but we really don&#x27;t know anything about how it was made from the articles. Essentially SiGe is a bit more conductive and can switch faster than normal Si chips, thanks to quantum tunneling.
icanhackit将近 10 年前
Time to start working on the 7km chip. Fibre everywhere, content delivery servers everywhere, game servers out the wazoo so my crappy media streaming gadget or VR headset can remotely pull in the latest movies and games in 4K with minimal lag. You could outfit a few of the world&#x27;s major cities for the cost of a new fab.<p>Unfortunately this won&#x27;t sell new consumer hardware on an regular basis.
评论 #9857195 未加载
评论 #9857560 未加载
LoSboccacc将近 10 年前
Still in research phase, from a company known for having 10% yields last time they innovated in the processor space<p>Also hasn&#x27;t Ibm just sold its division to global foundries? So are they double dipping as usual by licensing them new tech separately?
评论 #9857809 未加载
rurban将近 10 年前
YES! Kill Intel, PPC64 everywhere :)<p>It will not happen, I know, but &quot;Wouldn&#x27;t it be nice&quot; was always one of my favorite Beach Boys song (Pet Sounds!) <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=ofByti7A4uM" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=ofByti7A4uM</a><p>This is THE chance.
评论 #9859035 未加载
评论 #9856922 未加载
zxexz将近 10 年前
I know nothing about silicon fab, but I can&#x27;t help but wonder how they mitigate the effects of quantum tunneling at such a small scale?
nickpsecurity将近 10 年前
It&#x27;s neat but will only benefit the largest companies with the most elite developers. I&#x27;ve learned a lot about hardware development in past year for purposes of imagining clean-slate, subversion-resistant chips. The work it takes to get the 90nm and below chips working, especially inexpensively, is pretty mind boggling with many aspects still dark arts shrouded in trade secrets. Many firms stay at 130-180nm levels with quite a few still selling tech closer to a micron than a 28nm chip. Tools to overcome these challenges cost over a million a seat.<p>So, seeing another process shrink doesn&#x27;t excite me given we haven&#x27;t tapped the potential of what we already have. Lots of technologies help: EDA; FPGA&#x27;s: S-ASIC&#x27;s; multi-project wafers; ASIC-proven I.P. And so on. Yet, even 350nm still isn&#x27;t very accessible to most companies wanting to make a chip because the tools, I.P., and expertise are too expensive (or scarce sometimes). Yet, the benefits are real in so many use-cases (esp security). I&#x27;d like to see more companies dramatically bringing the costs down and eliminating other barriers to entry with affordable prices.<p>Example of the problems and what kind of work we&#x27;re looking at: <a href="http:&#x2F;&#x2F;eejournal.com&#x2F;archives&#x2F;articles&#x2F;20110104-elephant&#x2F;" rel="nofollow">http:&#x2F;&#x2F;eejournal.com&#x2F;archives&#x2F;articles&#x2F;20110104-elephant&#x2F;</a><p>Example direction to go in: <a href="http:&#x2F;&#x2F;fpgacomputing.blogspot.com&#x2F;2008&#x2F;08&#x2F;megahard-corp-open-source-eda-as.html" rel="nofollow">http:&#x2F;&#x2F;fpgacomputing.blogspot.com&#x2F;2008&#x2F;08&#x2F;megahard-corp-open...</a><p>I think the best model, though, is to do what the EDA vendors did: invest money into smart people, including in academia, to solve the NP-hard problems of each tool phase with incremental improvements over time. I&#x27;m thinking a non-profit with continuous funding by the likes of Google, Facebook, Microsoft, Wall St firms, etc. A membership fee plus licensing tools at cost, which continues to go down, might do it. Start with simpler problems such as place-and-route and ASIC gate-level simulation to deliver fast, easy-to-use, low cost tools. Savings against EDA tools bring in more members and customers whose money can be invested in maintaining those tools plus funding hardest ones (esp high-level synthesis). Also, money goes into good logic libraries for affordable process nodes. Non-commercial use is free but I.P. must be shared with members.<p>Setup right, this thing could fund the hard stuff with commercial activity and benefit from academic&#x2F;FOSS style submissions. With right structure, it also won&#x27;t go away due to an acquisition or someone running out of money. Open source projects don&#x27;t die: they just become unmaintained, temporarily or permanently. Someone can pick up the ball later.<p>Thoughts?
chriswilmer将近 10 年前
I don&#x27;t think the diameter of a DNA strand is 2.5nm...
santaclaus将近 10 年前
Return of the PowerPC Mac?
评论 #9856481 未加载
warrenmiller将近 10 年前
Did someone say ASIC?