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.

Goodbye, Motherboard. Hello, Silicon-Interconnect Fabric

345 pointsby craigjbover 5 years ago

20 comments

craigjbover 5 years ago
It&#x27;s been fun to see Dr. Subu present this concept and prototypes at several conferences, and the level of integration possible is absolutely insane. I think the industry is definitely moving toward chiplets, such as the latest AMD release.<p>I definitely think we will see more chiplets and more standardization on interfaces between chiplets. The focus will be on how to minimize energy per bit transferred (a big topic in Subu&#x27;s talks) and how to minimize the die area used for inter-chiplet communication. In monolithic silicon, you don&#x27;t have to think about die area, since your parallel wires between sections might just need a register or two along the way. With chiplets, you typically can&#x27;t run wires at that density yet, so you still have some serialization&#x2F;deserialization hardware. But, since it&#x27;s not crossing multiple high inductance solder balls and PCB traces, you can get away with less. Hopefully also you can get away without area-intensive resynchronization, PLLS, etc.<p>I think it will definitely be awhile before this kind of integration is used outside of niche cases though. The costs are just insane. You have to pre-test all manufactured chiplets before integration, and that test engineering is nothing to sneeze at. If you don&#x27;t then you have all kinds of commercials issues about who is liable for the $500k prototype one bad chip broke.<p>On the bright side, I see the chiplet approach benefitting other integration technologies. For example, wafer level and panel level embedded packaging technologies can be used for 1-2um interconnects now. You won&#x27;t get a wafer sized system out of it with any kind of yield, but it&#x27;s probably the direction mobile chips and wearables will go.<p>Anyway, disorganized info-dump over.
评论 #21075419 未加载
评论 #21079909 未加载
评论 #21079800 未加载
评论 #21077694 未加载
评论 #21097880 未加载
评论 #21100298 未加载
bArrayover 5 years ago
Yeah... I&#x27;m not entirely convinced about this future.<p>* PCBs are cheaper to manufacturer than silicon wafers.<p>* PCBs can be arbitrarily created and adjusted with little overhead cost (time and money).<p>* PCBs can be re-worked if a small hardware fault(s) is found.<p>* PCBs can carry large amount of power.<p>* PCBs can help absorb heat away from some components.<p>* PCBs have a small amount of flexibility, allowing them to absorb shock much easier.<p>* PCBs can be cut in such a way as to allow for mounting holes or be in relatively arbitrary shapes.<p>* PCBs can be designed to protect some components from static damage.<p>What I can see on the other hand is some packages end up being dropped into the PCB and soldered at the sides. Sometimes this is done with large through-hole capacitors, where the legs are bent and the capacitor sits in the middle of the PCB (inside a cut hole). Other than ball packages, you could could probably drop the majority into the PCB itself.<p>The other obvious option for manufacturers will be to put more tech on a single die, but then other problems are also raised. For example, some parts are binned based on their tested results.
评论 #21077724 未加载
评论 #21078010 未加载
jpm_sdover 5 years ago
&quot;Power turned out to be a major constraint. At a chip’s standard 1-volt supply, the wafer’s narrow wiring would consume a full 2 kilowatts. Instead, we chose to up the supply voltage to 12 V, reducing the amount of current needed and therefore the power consumed. That solution required spreading voltage regulators and signal-conditioning capacitors all around the wafer, taking up space that might have gone to more GPU modules.&quot;<p>Uh, this seems like a pretty serious downside.
评论 #21074956 未加载
评论 #21079815 未加载
评论 #21074793 未加载
评论 #21078024 未加载
seltzered_over 5 years ago
“Silicon-interconnect fabric, or Si-IF, offers an added bonus. It’s an excellent path toward the dissolution of the f(relatively) big, complicated, and difficult-to-manufacture systems-on-chips that currently run everything from smartphones to supercomputers. In place of SoCs, system designers could use a conglomeration of smaller, simpler-to-design, and easier-to-manufacture chiplets tightly interconnected on an Si-IF.”<p>Reading this reminded me of a remark from Bunnie Huang’s teardown of a dirt cheap ‘gongkai’ cellphone (<a href="https:&#x2F;&#x2F;www.bunniestudios.com&#x2F;blog&#x2F;?p=4297" rel="nofollow">https:&#x2F;&#x2F;www.bunniestudios.com&#x2F;blog&#x2F;?p=4297</a>): “To our surprise, this $3 chip didn’t contain a single IC, but rather, it’s a set of at least 4 chips, possibly 5, integrated into a single multi-chip module (MCM) containing hundreds of wire bonds. I remember back when the Pentium Pro’s dual-die package came out. That sparked arguments over yielded costs of MCMs versus using a single bigger die [...] I also remember at the time, Krste Asanović, then a professor at the MIT AI Lab now at Berkeley, told me that the future wouldn’t be system on a chip, but rather “system mostly on a chip”. The root of his claim is that the economics of adding in mask layers to merge DRAM, FLASH, Analog, RF, and Digital into a single process wasn’t favorable, and instead it would be cheaper and easier to bond multiple die together into a single package. It’s a race between the yield and cost impact (both per-unit and NRE) of adding more process steps in the semiconductor fab, vs. the yield impact (and relative reworkability and lower NRE cost) of assembling modules. Single-chip SoCs was the zeitgeist at the time (and still kind of is), so it’s interesting to see a significant datapoint validating Krste’s insight.”<p>I wonder if there’s any advantages to si-if from an ewaste (aka reverse logistics, cradle-to-cradle) perspective
mooman219over 5 years ago
Another drawback the article doesn&#x27;t mention is tight component coupling removes the ability to treat the components as separate pieces. This can make repair or upgrades extremely difficult. This might be desirable for companies against the right to repair; if it&#x27;s illegal to use software to prevent repair, making it sufficiently difficult by hardware design is a possibility.
评论 #21074755 未加载
评论 #21074720 未加载
评论 #21074533 未加载
评论 #21074411 未加载
评论 #21074387 未加载
ChuckMcMover 5 years ago
This step is inevitable in my opinion. This is especially true for mixed signal (that is some digital and some analog components) systems. It&#x27;s early fore-bearer (multi-chip modules or MCM) was instrumental in IBM getting its later mainframes to hit the density and thermal constraints.<p>Like the authors, when I saw AMD&#x27;s chiplet pictures for the Zen2 chips I felt that we would see this expanded. Intel has also done some interesting optical chip to chip interconnects that would facilitate assembling these newer multichip modules into chassis that route signals to and from the outside world.<p>The next (and perhaps last) element to fall into place is a way to efficiently cool these systems. One of the problems that large data centers face is not that they want &quot;smaller&quot; boxes but that they need to pull enough heat out of a rack of servers in order for them to reliably function.
评论 #21079129 未加载
mhb_engover 5 years ago
For reference, there are companies that have developed this to a commercially viable level. First that comes to mind is ZGlue, a company that has the design tools, interconnect fabric, and chiplet ecosystem required to deliver these kinds of devices.<p><a href="https:&#x2F;&#x2F;www.zglue.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.zglue.com&#x2F;</a>
评论 #21079837 未加载
Yaa101over 5 years ago
The downside is that independent entities are not anymore able to design hardware projects, there are only a few companies that can design and make such integrated circuits. Cpu&#x27;s are not only made for computers but for all sorts of appliances. Time will tell if these big companies will sell chiplets and the tech to assemble them onto silicon to 3rd paties. PCB tech is fairly democratic in that sense.
评论 #21079149 未加载
korethrover 5 years ago
I kinda like this idea, but I think it only makes sense where the end product sold to the intended consumer is wholly integrated. So, this might make sense for a smartphone. Or perhaps custom systems in Google- or Amazon- scale datacenters, with a number of different custom types tuned to exactly the work each is intended to do, and packed as densely as the intersection between thermodynamics and economics will allow.<p>But, I don&#x27;t think we can escape the need for packages and PCBs entirely. At some point, you&#x27;re going to need to interface with something that either A) you don&#x27;t or can&#x27;t control, or B) something at appropriate scale for interfacing with the humans whom the fancy system is ultimately supposed to serve. In either case, here come standard connections that are much bigger than the chiplet dies or the interconnect fabric between them, and thus, the need for PCBs to connect the Systems-on-a-wafer to the outside world.<p>As such, I think it will be a while before I can pick components out on Mouser&#x27;s website, and have all those component chiplets fused to an interconnect wafer and delivered to my home or employer&#x27;s shipping dock (though that would be damned awesome).
评论 #21074605 未加载
cududaover 5 years ago
Color me skeptical, but I remember being 12 seeing this on The Screen Savers on TechTV in 2003
holy_cityover 5 years ago
I like the idea of faster and smaller devices but dislike the idea of expensive production methods that are only realizable with heavy capital investment and large volumes of products.<p>Like I can realize a PCB prototype in my apartment (or rather, my parking lot without telling my landlord), or rent a CNC machine at a makerspace&#x2F;public library to do it. If I need the thing fabbed with a nice solder mask and silk screen, I can have it made for &lt; $20 domestically with under two weeks lead time. Component sourcing is even easier.<p>But where do I go to have the chiplets I need for the circuit? Organize the logistics to ship them to the clean-room where they can be packaged on this fabric? How many widgets do I need to ship for this to be viable, or for the contract fab to not laugh at me? How do I prototype? How long is the lead time?<p>It just seems like there&#x27;s a <i>lot</i> in the way of this being viable for run of the mill projects.
评论 #21075064 未加载
评论 #21080008 未加载
tartavullover 5 years ago
You can order custom pcb from China for a couple of dollars. How likely is that this technology will be affordable at small quantities?
评论 #21074826 未加载
评论 #21079317 未加载
localhostover 5 years ago
Does anyone know how this compares with AMD&#x27;s Infinity Fabric? How is it similar or different from it?
评论 #21077920 未加载
a0zUover 5 years ago
It seems like promising technology but the cost of making these chiplets must outweigh their benefits.
wand3rover 5 years ago
I think it should be called Silicon Fabricated Interconnect so we can just call it Si-Fi...
NetOpWibbyover 5 years ago
Cyberpunk 2077, here we come!
BAReF00tover 5 years ago
Gloodbye customizability and modularity, from a user standpoint.<p>I guess Apple will hire them pretty soon.
cphooverover 5 years ago
Will this increase the number of bit flips from cosmic rays?
评论 #21074820 未加载
ColanRover 5 years ago
It sounds like hardware side of computer science is rediscovering the UNIX philosophy - each unit does one thing, well, with standardized interfaces.
Causality1over 5 years ago
&gt;pack dozens of servers’ worth of computing capability onto a dinner-plate-size wafer of silicon.<p>Congratulations on the insurance money from your building burning to the ground.