One of the big challenges for IC test is making sense of mountains of data, a direct result of more features being packed onto a single die, or multiple chiplets being assembled into an advanced package. Collecting all that data through various agents and building models on the tester no longer makes sense for a couple reasons — there is too much data, and there are multiple customers using the same equipment. Steve Zamek, director of product management at PDF Solutions, and Eli Roth, product manager at Teradyne, explain how to optimize testing around different data sources, how to partition that data between the edge and the cloud, and how to ensure it remains secure.

The post Making Adaptive Test Work Better appeared first on Semiconductor Engineering.

Attention nowadays has turned to the energy consumption of systems that run on electricity. At the moment, the discussion is focused on electricity consumption in data centers: if this continues to rise at its current rate, it will account for a significant proportion of global electricity consumption in the future. Yet there are other, less visible electricity consumers whose power needs are also constantly growing. One example is mobile communications, where ongoing expansion – especially with the new current 5G standard and the future 6G standard – is pushing up the number of base stations required. This, too, will drive up electricity demand, as the latter increases linearly with the number of stations; at least, if the demand per base station is not reduced. Another example is electronics for the management of household appliances and in the industrial sector: more and more such systems are being installed, and their electronics are becoming significantly more powerful. They are not currently optimized for power consumption, but rather for performance.

This state of affairs simply cannot continue into the future for two reasons: first, the price of electricity will continue to rise worldwide; and second, many companies are committed to becoming carbon neutral. Their desire for carbon neutrality in turn makes electricity yet more expensive and restricts the overall quantity much more severely. As a result, there will be a significant demand for efficient electronics in the coming years, particularly as regards electricity consumption.

This development is already evident today, especially in power electronics, where the use of new semiconductor materials such as GaN or SiC has made it possible to reduce power consumption. A key driver for the development and introduction of such new materials was the electric car market, as reduced losses in the electronics leads directly to increased vehicle range. In the future, these materials will also find their way into other areas; for instance, they are already beginning to establish themselves in voltage transformers in various industries. However, this shift requires more factories and more suppliers for production, and further work also needs to be carried out to develop appropriate circuit concepts for these technologies.

In addition to the use of new materials, other concepts to reduce energy consumption are needed. The data center sector will require increasingly better-adapted circuits – ones that have been developed for a specific task, and as a result can perform this task much more efficiently than universal processors. This involves striking the optimum balance between universal architectures, such as microprocessors and graphics cards, and highly specialized architectures that are suitable for only one use case. Some products will also fall between these two extremes. The increased energy efficiency is then “purchased” through the effort and expense of developing exceptionally specially adapted architectures. It’s important to note that the more specialized an adapted architecture is, the smaller the market for it. That means the only way such architectures will be economically viable is if they can be developed efficiently. This calls for new approaches to derive these architectures directly from high-level hardware/software optimization, without the additional implementation steps that are still necessary today. In sum, the only way to make this approach possible is by using novel concepts and tools to generate circuits directly from a high-level description.

The post Efficient Electronics appeared first on Semiconductor Engineering.

There’s a fascinating new lawsuit against Meta that includes a surprisingly novel interpretation of Section 230. If the court buys it, this interpretation could make the open web a lot more open, while chipping away at the centralized control of the biggest tech companies. And, yes, that could mean that the law (Section 230) that is wrongly called “a gift to big tech” might be a tool that undermines the dominance of some of those companies. But the lawsuit could be tripped up for any number of reasons, including a potentially consequential typo in the law that has been ignored for years.

Buckle in, this is a bit of a wild ride.

You would think with how much attention has been paid to Section 230 over the last few years (there’s an entire excellent book about it!), and how short the law is, that there would be little happening with the existing law that would take me by surprise. But the new Zuckerman v. Meta case filed on behalf of Ethan Zuckerman by the Knight First Amendment Institute has got my attention.

It’s presenting a fairly novel argument about a part of Section 230 that almost never comes up in lawsuits, but could create an interesting opportunity to enable all kinds of adversarial interoperability and middleware to do interesting (and hopefully useful) things that the big platforms have been using legal threats to shut down.

If the argument works, it may reveal a surprising and fascinating trojan horse for a more open internet, hidden in Section 230 for the past 28 years without anyone noticing.

Of course, it could also have much wider ramifications that a bunch of folks need to start thinking through. This is the kind of thing that happens when someone discovers something new in a law that no one really noticed before.

But there’s also a very good chance this lawsuit flops for a variety of other reasons without ever really exploring the nature of this possible trojan horse. There are a wide variety of possible outcomes here.

But first, some background.

For years, we’ve talked about the importance of tools and systems that give end users more control over their own experiences online, rather than leaving it entirely up to the centralized website owners. This has come up in a variety of different contexts in different ways, from “Protocols, not Platforms” to “adversarial interoperability,” to “magic APIs” to “middleware.” These are not all exactly the same thing, but they’re all directionally strongly related, and conceivably could work well together in interesting ways.

But there are always questions about how to get there, and what might stand in the way. One of the biggest things standing in the way over the last decade or so has been interpretations of various laws that effectively allow social media companies to threaten and/or bring lawsuits against companies trying to provide these kinds of additional services. This can take the form of a DMCA 1201 claim for “circumventing” a technological block. Or, more commonly, it has taken the form of a civil (Computer Fraud & Abuse Act) CFAA claim.

The most representative example of where this goes wrong is when Facebook sued Power Ventures years ago. Power was trying to build a unified dashboard across multiple social media properties. Users could provide Power with their own logins to social media sites. This would allow Power to log in to retrieve and post data, so that someone could interact with their Facebook community without having to personally go into Facebook.

This was a potentially powerful tool in limiting Facebook’s ability to become a walled-off garden with too much power. And Facebook realized that too. That’s why it sued Power, claiming that it violated the CFAA’s prohibition on “unauthorized access.”

The CFAA was designed (poorly and vaguely) as an “anti-hacking” law. And you can see where “unauthorized access” could happen as a result of hacking. But Facebook (and others) have claimed that “unauthorized access” can also be “because we don’t want you to do that with your own login.”

And the courts have agreed to Facebook’s interpretation, with a few limitations (that don’t make that big of a difference).

I still believe that this ability to block interoperability/middleware with law has been a major (perhaps the most major) reason “big tech” is so big. They’re able to use these laws to block out the kinds of companies who would make the market more competitive and pull down some the walls of walled gardens.

That brings us to this lawsuit.

Ethan Zuckerman has spent years trying to make the internet a better, more open space (partially, I think, in penance for creating the world’s first pop-up internet ad). He’s been doing some amazing work on reimagining the digital public infrastructure, which I keep meaning to write about, but never quite find the time to get to.

According to the lawsuit, he wants to build a tool called “Unfollow Everything 2.0.” The tool is based on a similar tool, also called Unfollow Everything, that was built by Louis Barclay a few years ago and did what it says on the tin: let you automatically unfollow everything on Facebook. Facebook sent Barclay a legal threat letter and banned him for life from the site.

Zuckerman wants to recreate the tool with some added features enabling users to opt-in to provide some data to researchers about the impact of not following anyone on social media. But he’s concerned that he’d face legal threats from Meta, given what happened with Barclay.

Using Unfollow Everything 2.0, Professor Zuckerman plans to conduct an academic research study of how turning off the newsfeed affects users’ Facebook experience. The study is opt-in—users may use the tool without participating in the study. Those who choose to participate will donate limited and anonymized data about their Facebook usage. The purpose of the study is to generate insights into the impact of the newsfeed on user behavior and well-being: for example, how does accessing Facebook without the newsfeed change users’ experience? Do users experience Facebook as less “addictive”? Do they spend less time on the platform? Do they encounter a greater variety of other users on the platform? Answering these questions will help Professor Zuckerman, his team, and the public better understand user behavior online and the influence that platform design has on that behavior

The tool and study are nearly ready to launch. But Professor Zuckerman has not launched them because of the near certainty that Meta will pursue legal action against him for doing so.

So he’s suing for declaratory judgment that he’s not violating any laws. If he were just suing for declaratory judgment over the CFAA, that would (maybe?) be somewhat understandable or conventional. But, while that argument is in the lawsuit, the main claim in the case is something very, very different. It’s using a part of Section 230, section (c)(2)(B), that almost never gets mentioned, let alone tested.

Most Section 230 lawsuits involve (c)(1): the famed “26 words” that state “No provider or user of an interactive computer service shall be treated as the publisher or speaker of any information provided by another information content provider.”

Some Section 230 cases involve (c)(2)(A) which states that “No provider or user of an interactive computer service shall be held liable on account of any action voluntarily taken in good faith to restrict access to or availability of material that the provider or user considers to be obscene, lewd, lascivious, filthy, excessively violent, harassing, or otherwise objectionable, whether or not such material is constitutionally protected.” Many people incorrectly think that Section 230 cases turn on this part of the law, when really, much of those cases are already cut off by (c)(1) because they try to treat a service as a speaker or publisher.

But then there’s (c)(2)(B), which says:

No provider or user of an interactive computer service shall be held liable on account of any action taken to enable or make available to information content providers or others the technical means to restrict access to material described in paragraph (1)

As noted, this basically never comes up in cases. But the argument being made here is that this creates some sort of proactive immunity from lawsuits for middleware creators who are building tools (“technical means”) to “restrict access.” In short: does Section 230 protect “Unfollow Everything” from basically any legal threats from Meta, because it’s building a tool to restrict access to content on Meta platforms?

Or, according to the lawsuit:

This provision would immunize Professor Zuckerman from civil liability for designing, releasing, and operating Unfollow Everything 2.0

First, in operating Unfollow Everything 2.0, Professor Zuckerman would qualify as a “provider . . . of an interactive computer service.” The CDA defines the term “interactive computer service” to include, among other things, an “access software provider that provides or enables computer access by multiple users to a computer server,” id. § 230(f)(2), and it defines the term “access software provider” to include providers of software and tools used to “filter, screen, allow, or disallow content.” Professor Zuckerman would qualify as an “access software provider” because Unfollow Everything 2.0 enables the filtering of Facebook content—namely, posts that would otherwise appear in the feed on a user’s homepage. And he would “provide[] or enable[] computer access by multiple users to a computer server” by allowing users who download Unfollow Everything 2.0 to automatically unfollow and re-follow friends, groups, and pages; by allowing users who opt into the research study to voluntarily donate certain data for research purposes; and by offering online updates to the tool.

Second, Unfollow Everything 2.0 would enable Facebook users who download it to restrict access to material they (and Zuckerman) find “objectionable.” Id. § 230(c)(2)(A). The purpose of the tool is to allow users who find the newsfeed objectionable, or who find the specific sequencing of posts within their newsfeed objectionable, to effectively turn off the feed.

I’ve been talking to a pretty long list of lawyers about this and I’m somewhat amazed at how this seems to have taken everyone by surprise. Normally, when new lawsuits come out, I’ll gut check my take on it with a few lawyers and they’ll all agree with each other whether I’m heading in the right direction or the totally wrong direction. But here… the reactions were all over the map, and not in any discernible pattern. More than one person I spoke to started by suggesting that this was a totally crazy legal theory, only to later come back and say “well, maybe it actually makes some sense.”

It could be a trojan horse that no one noticed in Section 230 that effectively bars websites from taking legal action against middleware providers who are providing technical means for people to filter or screen content on their feed. Now, it’s important to note that it does not bar those companies from putting in place technical measures to block such tools, or just banning accounts or whatever. But that’s very different from threatening or filing civil suits.

If this theory works, it could do a lot to enable these kinds of middleware services and make it significantly harder for big social media companies like Meta to stop them. If you believe in adversarial interoperability, that could be a very big deal. Like, “shift the future of the internet we all use” kind of big.

Now, there are many hurdles before we get to that point. And there are some concerns that if this legal theory succeeds, it could also lead to other problematic results (though I’m less convinced by those).

Let’s start with the legal concerns.

First, as noted, this is a very novel and untested legal theory. Upon reading the case initially, my first reaction was that it felt like one of those slightly wacky academic law journal articles you see law professors write sometimes, with some far-out theory they have that no one’s ever really thought about. This one is in the form of a lawsuit, so at some point we’ll find out how the theory works.

But that alone might make a judge unwilling to go down this path.

Then there are some more practical concerns. Is there even standing here? ¯\_(ツ)_/¯ Zuckerman hasn’t released his tool. Meta hasn’t threatened him. He makes a credible claim that given Meta’s past actions, they’re likely to react unfavorably, but is that enough to get standing?

Then there’s the question of whether or not you can even make use of 230 in an affirmative way like this. 230 is used as a defense to get cases thrown out, not proactively for declaratory judgment.

Also, this is not my area of expertise by any stretch of the imagination, but I remember hearing in the past that outside of IP law, courts (and especially courts in the 9th Circuit) absolutely disfavor lawsuits for declaratory judgment (i.e., a lawsuit before there’s any controversy, where you ask the court “hey, can you just check and make sure I’m on the right side of the law here…”). So I could totally see the judge saying “sorry, this is not a proper use of our time” and tossing it. In fact, that might be the most likely result.

Then there’s this kinda funny but possibly consequential issue: there’s a typo in Section 230 that almost everyone has ignored for years. Because it’s never really mattered. Except it matters in this case. Jeff Kosseff, the author of the book on Section 230, always likes to highlight that in (c)(2)(B), it says that the immunity is for using “the technical means to restrict access to material described in paragraph (1).”

But they don’t mean “paragraph (1).” They mean “paragraph (A).” Paragraph (1) is the “26 words” and does not describe any material, so it would make no sense to say “material described in paragraph (1).” It almost certainly means “paragraph (A),” which is the “good faith to restrict access to or availability of material that the provider or user considers to be obscene, lewd, lascivious, filthy, excessively violent, harassing, or otherwise objectionable” section. That’s the one that describes material.

I know that, at times, Jeff has joked when people ask him how 230 should be reformed he suggests they fix the typo. But Congress has never listened.

And now it might matter?

The lawsuit basically pretends that the typo isn’t there. Its language inserts the language from “paragraph (A)” where the law says “paragraph (1).”

I don’t know how that gets handled. Perhaps it gets ignored like every time Jeff points out the typo? Perhaps it becomes consequential? Who knows!

There are a few other oddities here, but this article is getting long enough and has mostly covered the important points. However, I will conclude on one other point that one of the people I spoke to raised. As discussed above, Meta has spent most of the past dozen or so years going legally ballistic about anyone trying to scrape or data mine its properties in anyway.

Yet, earlier this year, it somewhat surprisingly bailed out on a case where it had sued Bright Data for scraping/data mining. Lawyer Kieran McCarthy (who follows data scraping lawsuits like no one else) speculated that Meta’s surprising about-face may be because it suddenly realized that for all of its AI efforts, it’s been scraping everyone else. And maybe someone high up at Meta suddenly realized how it was going to look in court when it got sued for all the AI training scraping, if the plaintiffs point out that at the very same time it was suing others for scraping its properties.

For me, I suspect the decision not to appeal might be more about a shift in philosophy by Meta and perhaps some of the other big platforms than it is about their confidence in their ability to win this case. Today, perhaps more important to Meta than keeping others off their public data is having access to everyone else’s public data. Meta is concerned that their perceived hypocrisy on these issues might just work against them. Just last month, Meta had its success in prior scraping cases thrown back in their face in a trespass to chattels case. Perhaps they were worried here that success on appeal might do them more harm than good.

In short, I think Meta cares more about access to large volumes of data and AI than it does about outsiders scraping their public data now. My hunch is that they know that any success in anti-scraping cases can be thrown back at them in their own attempts to build AI training databases and LLMs. And they care more about the latter than the former.

I’ve separately spoken to a few experts who were worried about the consequences if Zuckerman succeeded here. They were worried that it might simultaneously immunize potential bad actors. Specifically, you could see a kind of Cambridge Analytica or Clearview AI situation, where companies trying to get access to data for malign purposes convince people to install their middleware app. This could lead to a massive expropriation of data, and possibly some very sketchy services as a result.

But I’m less worried about that, mainly because it’s the sketchy eventuality of how that data is being used that would still (hopefully?) violate certain laws, not the access to the data itself. Still, there are at least some questions being raised about how this type of more proactive immunity might result in immunizing bad actors that is at least worth thinking about.

Either way, this is going to be a case worth following.

The incessant demand for more speed in chips requires forcing more energy through ever-smaller devices, increasing current density and threatening long-term chip reliability. While this problem is well understood, it’s becoming more difficult to contain in leading-edge designs.

Of particular concern is electromigration, which is becoming more troublesome in advanced packages with multiple chiplets, where various bonding and interconnect schemes create abrupt changes in materials and geometries. For example, electrons may travel from a copper trace to a solder bump of SAC (tin-silver-copper), then to an underbump metal based on nickel, and finally to an interposer copper pad. That, in turn, can cause atoms to shift, resulting in failures in solder joints or in copper redistribution layers in high-density fan-out packages.

“From an electromigration perspective, advanced packaging causes increased packaging density, reduced packaging size, and the dimensions of interconnects to shrink, so the current density is now in close proximity to the maximum current density limit per EM design rules,” said Dermott Lynch, director of technical product management in Synopsys‘ EDA Group.

Any additional stresses the package may be subjected to during assembly and use, whether mechanical or thermal, also can help induce or accelerate electromigration. “Electromigration, in general, gets worse due to temperature and stress, both of which advanced packaging increases,” said Lynch. “Electromigration is also cumulative, so essentially it integrates all the temperature highs and stress over the lifetime until an interconnect breaks down or shorts. Larger processing temperature and operation temperature will make it worse, but it also depends on time under that temperature.”

In fact, managing thermal pathways is perhaps the greatest challenge associated the movement toward the ultimate package, a 3D-IC. “Electromigration is very temperature-sensitive,” said Marc Swinnen, director of product marketing in Ansys’ Semiconductor Division. “Depending on your thermal map, your power integrity will have to adapt to the local temperature profile that you have. So when you look at a chip, you can calculate how much power the chip is putting out, but you cannot tell how hot the chip will get because ‘it depends.’ Is it sitting on a cold plate or sitting in the sun in the Sahara? System concerns come in, and multi-physics modeling is important to understanding these co-dependent effects.”

Thermal engineering also means moving heat away from the most vulnerable points of failure, such as solder bumps. “Effective thermal management is essential for bump reliability,” said Curtis Zwenger, vice president of engineering and technical marketing at Amkor. “Engineers are incorporating thermal enhancement techniques, such as the use of thermal interface materials and advanced heat dissipation solutions, to ensure that bumps are not subjected to excessive temperature-related stresses.”

Zwenger noted that engineers are looking into new materials, while optimizing the use of existing materials to minimize the possibility of electromigration. “Semiconductor packaging engineers are implementing a range of measures to enhance bump reliability and maximize bump yield. These strategies include new materials for solder bumps and underbump metallization, optimizing bump size, pitch and shape for reliability, advanced process control methods to control variability and maximize yield, and simulating and modeling reliability.”

What is electromigration?
Electromigration is the mass transport of metal atoms caused by the electron wind from current flowing through a conductor, typically copper. When current density is high enough, metal will diffuse in the direction of current flow, creating tiny hillocks downstream and leaving behind vacancies or voids. With enough electromigration, failures occur due to severe line thinning, causing opens, or due to hillocks that bridge adjacent lines, causing short circuits.

Electromigration is a diffusion-controlled mechanism that can take three forms — bulk, grain boundary, or surface diffusion, depending on the metal. Aluminum migrates by grain boundary diffusion whereas copper migrates on the surface or at its grain boundaries.

For most of the semiconductor industry’s history, electromigration was primarily an on-chip concern, but on-chip EM is largely under control by reliability engineers. But with the scaling and rapid developments in advanced packaging — implementing TSVs, fan-out packaging with redistribution layers, and copper pillar bumps — electromigration has emerged as a major threat at the package level. Current flowing through the solder bump causes joule heating, and heat from other parts of the package may also dissipate through the solder bumps. EM can become an issue for solder joint connections between chip and interposer, or chip and PCB, as well as in RDLs. Solder joint failures typically manifest as voids or cracks.

Fig. 1: Electromigration can create short circuits between two interconnects through the development of hillocks, or an open circuit through the creation of voids in interconnect. Source: Ansys

Electromigration progresses more quickly at higher temperatures, at higher currents, under greater mechanical stress and in the presence of defects or impurities in the metal. Black’s equation describes an interconnect’s mean time-to-failure with respect to its temperature, current density and the activation energy needed to dislodge a metal atom as:

J is the current density, k is Boltzmann’s constant, T is temperature, Ea is the activation energy, and N is a scaling factor that depends on the metal’s properties. Black’s equation is useful because it easily shows how shorter, wider interconnects will tend to have longer MTTF. In addition, electromigration time-to-failure very strongly depends on the interconnect’s temperature. That temperature is primarily the result of the chip’s environmental temperature, self-heating of the conductor caused by current flow, the heat from neighboring interconnects or transistors, and the thermal conductivity of the surrounding material.

It is also important to note that electromigration is a runaway process. As current density and/or temperature increases, electromigration increases, which raises current density, causing more metal to migrate in a destructive feedback loop.

EM failure modes and allowable current density
In the case of copper redistribution layers in polyimide material, as current flows through the RDL, heat accumulates in the conductor due to Joule heating generation, which can degrade performance. As the required current density and Joule heating temperature is increasing in the fine-line Cu RDL structures (<5nm lines and spaces), self-heating is considered a key factor in the reliability of high-density fan out packages.

JiHye Kwon, senior manager of R&D at Amkor, recently used EM testing and Black’s equation to determine the electromigration failure mechanisms for a given RDL stack and high-density fan-out package with 2µm or 10µm wide RDL layers, 1,000µm long. [1]

High density fan-out is an emerging technology, as it features more aggressive scaling than wafer level fan-out packages. The three layers of copper RDL (3µm thick with Ta/Cu seed) were fabricated followed by polyimide fill, copper pillar deposition, die attach, and overmold. Kwon’s team tested both 2 and 10µm RDL at different current densities and temperatures until resistance increased by 100% (EM failure), but the maximum allowed current density corresponded with a 20% resistance increase. The failure modes occurred in two stages, first by void nucleation and growth and second with copper reduction and oxidation. The study yielded Ea and current density exponent values that can be useful in future designs of RDLs.

Meanwhile, a team of researchers from ASE recently demonstrated how susceptibility to electromigration is determined on copper pillar interconnects in flip chip quad flat no-lead (FCQFN) for high-power automotive applications. The multi-layered copper pillar bumps with a Cu/Ni/Sn1.8Ag configuration were bonded to a silver-plated copper leadframe and tested under extreme EM conditions of 10 kA/cm² current density and temperatures of 150°C, 160°C and 180°C, while taking in-situ resistance measurements. [2] The EM failures corresponded with rapid rises in electrical resistance that corresponded with the formation of intermetallic compounds and voids at the Cu/solder interfaces. The team built an EM prediction model of interconnects based on a Black-type EM equation, following the JEDEC standard with five test conditions.

After the statistic calculation from the lifetime of samples, the ASE team determined activation energy of Cu pillar interconnects in the FCQFN package (1.12 ± 0.03 eV). The maximum current of the Cu pillar interconnects allowable lasting 10 years at a 105°C operating temperature at a 0.1% failure rate was larger than 2A for the FCQFN Cu pillar structure. “The FCQFN package has great potential in terms of its excellent anti-EM performance for future high-power applications,” the article said.

Designing/manufacturing for EM resiliency
Building electromigration resilience into advanced devices begins with using only EM-compliant linewidths in circuit designs based on the current density and heat profile that the interconnects will experience during operation over the lifetime of the device. Electromigration mitigation also requires process and materials engineering to ensure durability, for instance, of copper pillar bumps under BGA packages. It also calls for an optimized assembly process window and tight process control to prevent tiny violations of design rules that can later precipitate as EM failures.

As the industry makes its way toward true 3D packages, and eventually 3D-ICs, it seems clear that modeling and simulation will play an increasing role in determining many of the guard rails for manufacturing and assembly before manufacturing and assembly even begins. “Reliability modeling and simulation tools are being used to better understand the reliability of bump structures. This proactive approach helps in identifying potential issues before they arise, enabling engineers to implement preventive measures,” said Zwenger.

Modeling and simulation at the system level also will be essential to understanding the complex interplay between reliability mechanisms with thermal and mechanical stress in multi-chiplet systems during operation.

“Electromigration for stacked die is challenging,” said Synopsys’ Lynch. “Localized, die-to-die workloads cause repetitive current flow in specific areas. This generates local heat, increasing EM resulting in wire degradation, while producing even more heat. Reducing the thermal issue becomes critical to ensuring EM reliability.”

As stated previously, solder bumps can become a site for EM reliability failure. “Engineers fine-tune bump design in terms of bump size, pitch, and shape to ensure uniformity and reliability across the entire package. This includes the adoption of innovative Cu bump structures for improved mechanical and electrical properties,” said Amkor’s Zwenger.

In flip-chip BGA and other flip-chip applications, underfill materials — typically thermoset epoxies — are used to reduce the thermal stresses on solder bumps. “Underfill materials play a critical role in providing mechanical support and thermal stability to the bumps,” Zwenger said. “Engineers are investing in the development of advanced underfill formulations with enhanced properties, such as improved adhesion, thermal conductivity, and stress relief.”

Conclusion
Because of its dependence on temperature, electromigration is a failure mechanism to watch and plan for as devices continue to scale and systems integrators continue to cram more and more chiplets of various functions into advanced packages.

“In advanced technologies, the current density is now in close proximity to the maximum density,” said Synopsys’ Lynch. “Anything that causes an increase in temperature poses a threat. Designers of multi-die systems need to understand the impact of temperature and design systems to remove the heat.”

References

1. JiHye Kwon, “Electromigration Performance Of Fine-Line Cu Redistribution Layer (RDL) For HDFO Packaging,” Semiconductor Engineering, Jan. 18, 2024, https://semiengineering.com/electromigration-performance-of-fine-line-cu-redistribution-layer-rdl-for-hdfo-packaging/
2. -Y. Tsai, et al., “An Electromigration Study of Cu Pillar Interconnects in Flip-chip QFN Packaging under Extreme Conditions for High-power Applications,” 2023 IEEE 25th Electronics Packaging Technology Conference (EPTC), Singapore, 2023, pp. 326-332, doi: 10.1109/EPTC59621.2023.10457564.

Related Reading
What Can Go Wrong In Heterogeneous Integration
Workflows and tools are disconnected, mechanical stress is ill-defined, and complete co-planarity is nearly impossible. But there are solutions on the horizon.
Thermal Integrity Challenges Grow In 2.5D
Work is underway to map heat flows in interposer-based designs, but there’s much more to be done.
Chiplets: 2023 (EBook)
What chiplets are, what they are being used for today, and what they will be used for in the future.

The post Electromigration Concerns Grow In Advanced Packages appeared first on Semiconductor Engineering.

A few months ago, we wondered if Wired had fired its entire fact-checking staff because it published what appeared to be a facts-optional article co-authored by professional consistently wrong Jaron Lanier and an academic I’d not come across before, Allison Stanger. The article suggested that getting rid of Section 230 “could save everything.” Yet the article was so far off-base that it was in the “not even wrong” category of wrongness.

I’m not going to review all the reasons it was wrong. You can go back to my original article for that, though I will note that the argument seemed to suggest that getting rid of Section 230 would both lead to better content moderation and, at the same time, only moderation based on the First Amendment. Both of those points are obviously wrong, but the latter one is incoherent.

Given his long track record of wrongness, I had assumed that much of the article likely came from Lanier. However, I’m going to reassess that in light of Stanger’s recent performance before the House Energy & Commerce Committee. Last week, there was this weird hearing about Section 230, in which the Committee invited three academic critics of Section 230, and not a single person who could counter their arguments and falsehoods. We talked about this hearing a bit in this week’s podcast, with Rebecca MacKinnon from the Wikimedia Foundation.

Stanger was one of the three witnesses. The other two, Mary Anne Franks and Mary Graw Leary, presented some misleading and confused nonsense about Section 230. However, the misleading and confused nonsense about Section 230 at least fits into the normal framework of the debate around Section 230. There is confusion about how (c)(1) and (c)(2) interact, the purpose of Section 230, and (especially) some confusion about CSAM and Section 230 and an apparent unawareness that federal criminal behavior is exempted from Section 230.

But, let’s leave that aside. Because Stanger’s submission was so far off the mark that whoever invited her should be embarrassed. I’ve seen some people testify before Congress without knowing what they’re talking about, but I cannot recall seeing testimony this completely, bafflingly wrong before. Her submitted testimony is wrong in all the ways that the Wired article was wrong and more. There are just blatant factual errors throughout it.

It is impossible to cover all of the nonsense, so we’re just going to pick some gems.

Without Section 230, existing large social media companies would have to adapt. Decentralized Autonomous Organizations, (DAOs) such as BlueSky and Mastodon, would become more attractive. The emergent DAO social media landscape should serve to put further brakes on virality, allowing a more regional social media ecosystem to emerge, thereby creating new demand for local media. In an ideal world, networks of DAOs would comprise a new fediverse (a collection of social networking servers which can communicate with each other, while remaining independently controlled), where users would have greater choice and control over the communities of which they are a part.

So, um. That’s not what DAOs are, professor. You seem to be confusing decentralized social media with decentralized autonomous organizations, which are a wholly different thing. This is kind of like saying “social security benefits” when you mean “social media influencers” because both begin with “social.” They’re not the same thing.

A decentralized social media site is what it says on the tin. It’s a type of social media that isn’t wholly controlled by a single company. Different bits of it can be controlled by others, whether its users or alternative third-party providers. A DAO is an operation, often using mechanisms like cryptocurrency and tokens, to enable a kind of democratic voting, or (possibly) a set of smart contracts, that determine how the loosely defined organization is run. They are not the same.

In theory, a decentralized social media site could be run by a DAO, but I don’t know of any that currently are.

Also, um, decentralized social media can only really exist because of Section 230. “Without Section 230,” you wouldn’t have Bluesky or Mastodon, because they would face ruinous litigation for hosting content that people would sue over. So, no, you would not have either more decentralized social media (which I think is what you meant) or DAOs (which are wholly unrelated). You’d have a lot less, because hosting third-party speech would come with way more liability risk.

Also, there’s nothing inherent to decentralized social media that means you’d “put the brakes on virality.” Mastodon has developed to date in a manner designed to tamp down virality, but Bluesky hasn’t? Nor have other decentralized social media offerings, many of which hope to serve a global conversation where virality is a part of it. And that wouldn’t really change with or without Section 230. Mastodon made that decision because of the types of communities it wanted to foster. And, indeed, its ability to do that is, in part, due to intermediary liability protections like Section 230, that enable the kind of small, more focused community moderation Mastodon embraces already.

It’s really not clear to me that Professor Stanger even knows what Section 230 does.

Non-profits like Wikipedia are concerned that their enterprise could be shut down through gratuitous defamation lawsuits that would bleed them dry until they ceased to exist (such as what happened with Gawker). I am not convinced this is a danger for Wikipedia, since their editing is done by humans who have first amendment rights, and their product is not fodder for virality….

Again, wut? The fact that their editing is “done by humans” has literally no impact on anything here. Why even mention that? Humans get sued for defamation all the time. And, if they’re more likely to get sued for defamation, they’re less likely to even want to edit at all.

And people get mad about their Wikipedia articles all the time, and sometimes they sue over them. Section 230 gets those lawsuits thrown out. Without it, those lawsuits would last longer and be more expensive.

Again, it’s not at all clear if Prof. Stanger even knows what Section 230 is or how it works.

The Facebook Files show that Meta knew that its engagement algorithms had adverse effects on the mental health of teenage girls, yet it has done nothing notable to combat those unintended consequences. Instead, Meta’s lawyers have invoked Section 230 in lawsuits to defend itself against efforts to hold it liable for serious harms

Again, this is just wrong. What the crux of the Facebook Files showed was that Meta was, in fact, doing research to learn about where its algorithms might cause harm in order to try to minimize that harm. However, because of some bad reporting, it now means that companies will be less likely to even do that research, because people like Professor Stanger will misrepresent it, claiming that they did nothing to try to limit the harms. This is just outright false information.

Also, the cases where Meta has invoked Section 230 would be unrelated to the issue being discussed here because 230 is about not being held liable for user content.

The online world brought to life by Section 230 now dehumanizes us by highlighting our own insignificance. Social media and cancel culture make us feel small and vulnerable, where human beings crave feeling large and living lives of meaning, which cannot blossom without a felt sense of personal agency that our laws and institutions are designed to protect. While book publishers today celebrate the creative contributions of their authors, for-profit Internet platforms do not.

I honestly have no idea what’s being said here. “Dehumanizes us by highlighting our own insignificance?” What are you even talking about? People were a lot more “insignificant” pre-internet, when they had no way to speak out. And what does “cancel culture” have to do with literally any of this?

Without Section 230, companies would be liable for the content on their platforms. This would result in an explosion of lawsuits and greater caution in such content moderation, although companies would have to balance such with first amendment rights. Think of all the human jobs that could be generated!

Full employment for tort lawyers! I mean, this is just a modern version of Bastiat’s broken window fallacy. Think of all the economic activity if we just break all the windows in our village!

Again and again, it becomes clear that Stanger has no clue how any of this works. She does not understand Section 230. She does not understand the internet. She does not understand the First Amendment. And she does not understand content moderation. It’s a hell of a thing, considering she is testifying about Section 230 and its impact on social media and the First Amendment.

At a stroke, content moderation for companies would be a vastly simpler proposition. They need only uphold the First Amendment, and the Courts would develop the jurisprudence to help them do that, rather than to put the onus of moderation entirely on companies.

That is… not at all how it would work. They don’t just need to “uphold the First Amendment” (which is not a thing that companies can even do). The First Amendment’s only role is in restricting the government, not companies, from passing laws that infringe on a person’s ability to express themselves.

Instead, as has been detailed repeatedly, companies would face the so-called “moderator’s dilemma.” Because the First Amendment requires distributors to have actual knowledge of content violating the law to be liable, a world without Section 230 would incentivize one of two things, neither of which is “upholding the First Amendment.” They would either let everything go and do as little moderation as possible (so as to avoid the requisite knowledge), or they’d become very aggressive in limiting and removing content to avoid liability (even though this wouldn’t work and they’d still get hit with tons of lawsuits).

We’ve been here before. When government said the American public owned the airwaves, so television broadcasting would be regulated, they put in place regulations that supported the common good. The Internet affects everyone, and our public square is now virtual, so we must put in place measures to ensure that our digital age public dialogue includes everyone. In the television era, the fairness doctrine laid that groundwork. A new lens needs to be developed for the Internet age.

Except, no, that’s just factually wrong. The only reason that the government was able to put regulations on broadcast television was because the government controlled the public spectrum which they licensed to the broadcasters. The Supreme Court made clear in Red Lion that without that, they could not hinder the speech of media companies. So, the idea that you can just apply similar regulations to the internet is just fundamentally clueless. The internet is not publicly owned spectrum licensed to anyone.

While Section 230 perpetuates an illusion that today’s social media companies are common carriers like the phone companies, they are not. Unlike Ma Bell, they curate the content they transmit to users

Again, it appears the Professor is wholly unaware of Section 230 and how it works. The authors of Section 230 made it clear over and over again that they wrote 230 to be the opposite of common carriers. No one who supports Section 230 thinks it makes platforms into common carriers, because it does not. The entire point was to free up companies to choose how to curate content, so as to allow those companies to craft the kinds of communities they wanted. They only people claiming the “illusion” of common carrierness are those who are trying to destroy Section 230.

So there is no “illusion” here, unless you don’t understand what you’re talking about.

The repeal of Section 230 would also be a step in the right direction in addressing what are presently severe power imbalances between government and corporate power in shaping democratic life. It would also shine a spotlight on a globally disturbing fact: the overwhelming majority of global social media is currently in the hands of one man (Mark Zuckerberg), while nearly half the people on earth have a Meta account. How can that be a good thing under any scenario for the free exchange of ideas?

I mean, we agree that it’s bad that Meta is so big. But if you remove Section 230 (as Meta itself has advocated for!), you help Meta get bigger and harm the competition. Meta has a building full of lawyers. They can handle the onslaught of lawsuits that this would bring (as Stanger herself gleefully cheers on). It’s everyone else, the smaller sites, such as the decentralized players (not DAOs) who would get destroyed.

Mastodon admins aren’t going to be able to afford to pay to defend the lawsuits. Bluesky doesn’t have a building full of lawyers. The big winner here would be Meta. The cost to Meta of removing Section 230 is minimal. The cost to everyone trying to eat away at Meta’s marketshare would be massive.

The new speech is governed by the allocation of virality in our virtual public square. People cannot simply speak for themselves, for there is always a mysterious algorithm in the room that has independently set the volume of the speaker’s voice. If one is to be heard, one must speak in part to one’s human audience, in part to the algorithm. It is as if the constitution had required citizens to speak through actors or lawyers who answered to the Dutch East India Company, or some other large remote entity. What power should these intermediaries have? When the very logic of speech must shift in order for people to be heard, is that still free speech? This was not a problem foreseen in the law.

I mean, this is just ahistorical nonsense. Historically, most people had no way to get their message out at all. You could talk to your friends, family, co-workers, and neighbors, and that was about it. If you wanted to reach beyond that small group, you required some large gatekeeper (a publisher, a TV or radio producer, a newspaper) to grant you access, which they refused for the vast majority of people.

The internet flipped all that on its head, allowing anyone to effectively speak to anyone. The reason we have algorithms is not “Section 230” and the algorithms aren’t “setting the volume,” they came in to deal with the simple fact that there’s just too much information, and it was flooding the zone. People wanted to find information that was more relevant to them, and with the amount of content available online, the only way to manage that was with some sort of algorithm.

But, again, the rise of algorithms is not a Section 230 issue, even though Stanger seems to think it is.

Getting rid of the liability shield for all countries operating in the United States would have largely unacknowledged positive implications for national security, as well as the profit margins for US-headquartered companies. Foreign electoral interference is not in the interests of democratic stability, precisely because our enemies benefit from dividing us rather than uniting us. All foreign in origin content could therefore be policed at a higher standard, without violating the first amendment or the privacy rights of US citizens. As the National Security Agency likes to emphasize, the fourth amendment does not apply to foreigners and that has been a driver of surveillance protocols since the birth of the Internet. It is probable that the Supreme Court’s developing first amendment jurisprudence for social media in a post-230 world would embrace the same distinction. At a stroke, the digital fentanyl that TikTok represents in its American version could easily be shut down, and we could through a process of public deliberation leading to new statutory law collectively insist on the same optimization targets for well-being, test scores, and time on the platform that Chinese citizens currently enjoy in the Chinese version of TikTok (Douyin)

Again, this is a word salad that is mostly meaningless.

First of all, none of this has anything to do with Section 230, but rather the First Amendment. And it’s already been noted, clearly, that the First Amendment protects American users of foreign apps.

No one is saying “you can’t ban TikTok because of 230,” they’re saying “you can’t ban TikTok because of the First Amendment.” The Supreme Court isn’t going to magically reinvent long-standing First Amendment doctrine because 230 is repealed. This is nonsense.

And, we were just discussing what utter nonsense it is to claim that TikTok is “digital fentanyl” so I won’t even bother repeating that.

There might also be financial and innovation advantages for American companies with this simple legislative act. Any commercial losses for American companies from additional content moderation burdens would be offset by reputational gains and a rule imposed from without on what constitutes constitutionally acceptable content. Foreign electoral interference through misinformation and manipulation could be shut down as subversive activity directed at the Constitution of the United States, not a particular political party.

This part is particularly frustrating. This is why internet companies already moderate. Stanger’s piece repeatedly seems to complain both about too little moderation (electoral interference! Alex Jones!) and too much moderation (algorithms! dastardly Zuck deciding what I can read!).

She doesn’t even seem to realize that her argument is self-contradictory.

But, here, the supposed “financial and innovation advantages” from American companies being able to get “reputational gains” by stopping “misinformation” already exists. And it only exists because of Section 230. Which Professor Stanger is saying we need to remove to get the very thing it enables, and which would be taken away if it were repealed.

This whole thing makes me want to bang my head on my desk repeatedly.

Companies moderate today to (1) make users’ experience better and (2) to make advertisers happier that they’re not facing brand risk from having ads appear next to awful content. The companies that do better already achieve that “reputational benefit,” and they can do that kind of moderation because they know Section 230 prevents costly, wasteful, vexatious litigation from getting too far.

If you remove Section 230, that goes away. As discussed above, companies then are much more limited in the kinds of moderation they can do, which means users have a worse experience and advertisers have a worse experience, leading to reputational harm.

Today, companies already try to remove or diminish the power of electoral interference. That’s a giant part of trust & safety teams’ efforts. But they can really only do it safely because of 230.

The attention-grooming model fostered by Section 230 leads to stupendous quantities of poor-quality data. While an AI model can tolerate a significant amount of poor-quality data, there is a limit. It is unrealistic to imagine a society mediated by mostly terrible communication where that same society enjoys unmolested, high-quality AI. A society must seek quality as a whole, as a shared cultural value, in order to maximize the benefits of AI. Now is the best time for the tech business to mature and develop business models based on quality.

I’ve read this paragraph multiple times, and I still don’t know what it’s saying. Section 230 does not lead to an “attention-grooming model.” That’s just how society works. And, then, when she says society must seek quality as a whole, given how many people are online, the only way to do that is with algorithms trying to make some sort of call on what is, and what is not, quality.

That’s how this works.

Does she imagine that without Section 230, algorithms will go away, but good quality content will magically rise up? Because that’s not how any of this actually works.

Again, there’s much more in her written testimony, and none of it makes any sense at all.

Her spoken testimony was just as bad. Rep. Bob Latta asked her about the national security claims (some of which were quoted above) and we got this word salad, none of which has anything to do with Section 230:

I think it’s important to realize that our internet is precisely unique because it’s so open and that makes it uniquely vulnerable to all sorts of cyber attacks. Just this week, we saw an extraordinarily complicated plot that is most likely done by China, Russia or North Korea that could have blown up the internet as we know it. If you want to look up XZ Utils, Google that and you’ll find all kinds of details. They’re still sorting out what the intention was. It’s extraordinarily sophisticated though, so I think that the idea that we have a Chinese company where data on American children is being stored and potentially utilized in China, can be used to influence our children. It can be used in any number of ways no matter what they tell you. So I very much support and applaud the legislation to repeal, not to repeal, but to end TikToks operations in the United States.

The national security implications are extraordinary. Where the data is stored is so important and how it can be used to manipulate and influence us is so important. And I think the next frontier that I’ll conclude with this, for warfare, is in cyberspace. It’s where weak countries have huge advantages. They can pour resources into hackers who could really blow up our infrastructure, our hospitals, our universities. They’re even trying to get, as you know, into the House. This House right here. So I think repealing Section 230 is connected to addressing a host of potential harms

Nothing mentioned in there — from supply chain attacks like xz utils, to a potential TikTok ban, to hackers breaking into hospitals — has anything whatsoever to do with Section 230. She just throws it in at the end as if they’re connected.

She also claimed that Eric Schmidt has come out in favor of “repealing Section 230,” which was news to me. It also appears to be absolutely false. I went and looked, and the only thing I can find is a Digiday article which claims he called for reforms (not a repeal). The article never actually quotes him saying anything related to Section 230 at all, so it’s unclear what (if anything) he actually said. Literally the only quotes from Schmidt are old man stuff about how the kids these days just need to learn how to put down their phones, and then something weird about the fairness doctrine. Not 230.

Later, in the hearing, she was asked about the impact on smaller companies (some of which I mentioned above) and again demonstrates a near total ignorance of how this all works:

There is some concern, it’s sometimes expressed from small businesses that they are going to be the subject of frivolous lawsuits, defamation lawsuits, and they can be sued out of business even though they’ve defamed no one. I’m less concerned about that because if we were to repeal section (c)(1) of Section 230 of those 26 words, I think the First Amendment would govern and we would develop the jurisprudence to deal with small business in a more refined way. I think if anything, small businesses are in a better position to control and oversee what’s on their platforms than these monolithic large companies we have today. So with a bit of caution, I think that could be addressed.

The First Amendment always governs. But Section 230 is the “more refined way” that we’ve developed to help protect small businesses. The main function of Section 230 is to get cases, that would be long and costly if you had to defend them under the First Amendment, tossed out much earlier at the motion to dismiss stage. Literally that’s Section 230’s main purpose.

If you had to fight it out under the First Amendment, you’re talking about hundreds of thousands of dollars and a much longer case. And that cost is going to lead companies to (1) refuse to host lots of protected content, because it’s not worth the hassle, and (2) be much more open to pulling down any content that anyone complains about.

This is not speculative. There have been studies on this. Weaker intermediary laws always lead to massive overblocking. If Stanger had done her research, or even understood any of this, she would know this.

So why is she the one testifying before Congress?

I’ll just conclude with this banger, which was her final statement to Congress:

I just want to maybe take you back to the first part of your question to explain that, which I thought was a good one, which is that we have a long history of First Amendment jurisprudence in this country that in effect has been stopped by Section 230. In other words, if you review, if you remove (c)(1), that First Amendment jurisprudence will develop to determine when it is crime fire in a crowded theater, whether there’s defamation, whether there’s libel. We believe in free speech in this country, but even the First Amendment has some limits put on it and those could apply to the platforms. We have a strange situation right now if we take that issue of fentanyl that we were discussing earlier, what we have right now is essentially a system where we can go after the users, we can go after the dealers, but we can’t go after the mules. And I think that’s very problematic. We should hold the mules liable. They’re part of the system.

Yeah. So. She actually went to the whole fire in a crowded theater thing. This is the dead-on giveaway that the person speaking has no clue about the First Amendment. That’s dicta from a case from over 100 years ago, in a case that is no longer considered good law, and hasn’t been in decades. Even worse, that dicta came in a case about jailing war protestors.

She also trots out yet another of Ken “Popehat” White’s (an actual First Amendment expert) most annoying tropes about people opining on the First Amendment without understanding it: because the First Amendment has some limits, this new limit must be okay. That’s not how it works. As Ken and others have pointed out, the exceptions to the First Amendment are an established, known, and almost certainly closed set.

The Supreme Court has no interest in expanding that set. It refused to do so for animal crush videos, so it’s not going to magically do it for whatever awful speech you think it should limit.

Anyway, it was a shame that Congress chose to hold a hearing on Section 230 and only bring in witnesses who hate Section 230. Not a single witness who could explain why Section 230 is so important was brought in. But, even worse, they gave one of the three witness spots to someone who was spewing word salad level nonsense, that didn’t make any sense at all, was often factually incorrect (in hilariously embarrassing ways), and seemed wholly unaware of how any relevant thing worked.

Do better, Congress.

The incessant demand for more speed in chips requires forcing more energy through ever-smaller devices, increasing current density and threatening long-term chip reliability. While this problem is well understood, it’s becoming more difficult to contain in leading-edge designs.

Of particular concern is electromigration, which is becoming more troublesome in advanced packages with multiple chiplets, where various bonding and interconnect schemes create abrupt changes in materials and geometries. For example, electrons may travel from a copper trace to a solder bump of SAC (tin-silver-copper), then to an underbump metal based on nickel, and finally to an interposer copper pad. That, in turn, can cause atoms to shift, resulting in failures in solder joints or in copper redistribution layers in high-density fan-out packages.

“From an electromigration perspective, advanced packaging causes increased packaging density, reduced packaging size, and the dimensions of interconnects to shrink, so the current density is now in close proximity to the maximum current density limit per EM design rules,” said Dermott Lynch, director of technical product management in Synopsys‘ EDA Group.

Any additional stresses the package may be subjected to during assembly and use, whether mechanical or thermal, also can help induce or accelerate electromigration. “Electromigration, in general, gets worse due to temperature and stress, both of which advanced packaging increases,” said Lynch. “Electromigration is also cumulative, so essentially it integrates all the temperature highs and stress over the lifetime until an interconnect breaks down or shorts. Larger processing temperature and operation temperature will make it worse, but it also depends on time under that temperature.”

In fact, managing thermal pathways is perhaps the greatest challenge associated the movement toward the ultimate package, a 3D-IC. “Electromigration is very temperature-sensitive,” said Marc Swinnen, director of product marketing in Ansys’ Semiconductor Division. “Depending on your thermal map, your power integrity will have to adapt to the local temperature profile that you have. So when you look at a chip, you can calculate how much power the chip is putting out, but you cannot tell how hot the chip will get because ‘it depends.’ Is it sitting on a cold plate or sitting in the sun in the Sahara? System concerns come in, and multi-physics modeling is important to understanding these co-dependent effects.”

Thermal engineering also means moving heat away from the most vulnerable points of failure, such as solder bumps. “Effective thermal management is essential for bump reliability,” said Curtis Zwenger, vice president of engineering and technical marketing at Amkor. “Engineers are incorporating thermal enhancement techniques, such as the use of thermal interface materials and advanced heat dissipation solutions, to ensure that bumps are not subjected to excessive temperature-related stresses.”

Zwenger noted that engineers are looking into new materials, while optimizing the use of existing materials to minimize the possibility of electromigration. “Semiconductor packaging engineers are implementing a range of measures to enhance bump reliability and maximize bump yield. These strategies include new materials for solder bumps and underbump metallization, optimizing bump size, pitch and shape for reliability, advanced process control methods to control variability and maximize yield, and simulating and modeling reliability.”

What is electromigration?
Electromigration is the mass transport of metal atoms caused by the electron wind from current flowing through a conductor, typically copper. When current density is high enough, metal will diffuse in the direction of current flow, creating tiny hillocks downstream and leaving behind vacancies or voids. With enough electromigration, failures occur due to severe line thinning, causing opens, or due to hillocks that bridge adjacent lines, causing short circuits.

Electromigration is a diffusion-controlled mechanism that can take three forms — bulk, grain boundary, or surface diffusion, depending on the metal. Aluminum migrates by grain boundary diffusion whereas copper migrates on the surface or at its grain boundaries.

For most of the semiconductor industry’s history, electromigration was primarily an on-chip concern, but on-chip EM is largely under control by reliability engineers. But with the scaling and rapid developments in advanced packaging — implementing TSVs, fan-out packaging with redistribution layers, and copper pillar bumps — electromigration has emerged as a major threat at the package level. Current flowing through the solder bump causes joule heating, and heat from other parts of the package may also dissipate through the solder bumps. EM can become an issue for solder joint connections between chip and interposer, or chip and PCB, as well as in RDLs. Solder joint failures typically manifest as voids or cracks.

Fig. 1: Electromigration can create short circuits between two interconnects through the development of hillocks, or an open circuit through the creation of voids in interconnect. Source: Ansys

Electromigration progresses more quickly at higher temperatures, at higher currents, under greater mechanical stress and in the presence of defects or impurities in the metal. Black’s equation describes an interconnect’s mean time-to-failure with respect to its temperature, current density and the activation energy needed to dislodge a metal atom as:

J is the current density, k is Boltzmann’s constant, T is temperature, Ea is the activation energy, and N is a scaling factor that depends on the metal’s properties. Black’s equation is useful because it easily shows how shorter, wider interconnects will tend to have longer MTTF. In addition, electromigration time-to-failure very strongly depends on the interconnect’s temperature. That temperature is primarily the result of the chip’s environmental temperature, self-heating of the conductor caused by current flow, the heat from neighboring interconnects or transistors, and the thermal conductivity of the surrounding material.

It is also important to note that electromigration is a runaway process. As current density and/or temperature increases, electromigration increases, which raises current density, causing more metal to migrate in a destructive feedback loop.

EM failure modes and allowable current density
In the case of copper redistribution layers in polyimide material, as current flows through the RDL, heat accumulates in the conductor due to Joule heating generation, which can degrade performance. As the required current density and Joule heating temperature is increasing in the fine-line Cu RDL structures (<5nm lines and spaces), self-heating is considered a key factor in the reliability of high-density fan out packages.

JiHye Kwon, senior manager of R&D at Amkor, recently used EM testing and Black’s equation to determine the electromigration failure mechanisms for a given RDL stack and high-density fan-out package with 2µm or 10µm wide RDL layers, 1,000µm long. [1]

High density fan-out is an emerging technology, as it features more aggressive scaling than wafer level fan-out packages. The three layers of copper RDL (3µm thick with Ta/Cu seed) were fabricated followed by polyimide fill, copper pillar deposition, die attach, and overmold. Kwon’s team tested both 2 and 10µm RDL at different current densities and temperatures until resistance increased by 100% (EM failure), but the maximum allowed current density corresponded with a 20% resistance increase. The failure modes occurred in two stages, first by void nucleation and growth and second with copper reduction and oxidation. The study yielded Ea and current density exponent values that can be useful in future designs of RDLs.

Meanwhile, a team of researchers from ASE recently demonstrated how susceptibility to electromigration is determined on copper pillar interconnects in flip chip quad flat no-lead (FCQFN) for high-power automotive applications. The multi-layered copper pillar bumps with a Cu/Ni/Sn1.8Ag configuration were bonded to a silver-plated copper leadframe and tested under extreme EM conditions of 10 kA/cm² current density and temperatures of 150°C, 160°C and 180°C, while taking in-situ resistance measurements. [2] The EM failures corresponded with rapid rises in electrical resistance that corresponded with the formation of intermetallic compounds and voids at the Cu/solder interfaces. The team built an EM prediction model of interconnects based on a Black-type EM equation, following the JEDEC standard with five test conditions.

After the statistic calculation from the lifetime of samples, the ASE team determined activation energy of Cu pillar interconnects in the FCQFN package (1.12 ± 0.03 eV). The maximum current of the Cu pillar interconnects allowable lasting 10 years at a 105°C operating temperature at a 0.1% failure rate was larger than 2A for the FCQFN Cu pillar structure. “The FCQFN package has great potential in terms of its excellent anti-EM performance for future high-power applications,” the article said.

Designing/manufacturing for EM resiliency
Building electromigration resilience into advanced devices begins with using only EM-compliant linewidths in circuit designs based on the current density and heat profile that the interconnects will experience during operation over the lifetime of the device. Electromigration mitigation also requires process and materials engineering to ensure durability, for instance, of copper pillar bumps under BGA packages. It also calls for an optimized assembly process window and tight process control to prevent tiny violations of design rules that can later precipitate as EM failures.

As the industry makes its way toward true 3D packages, and eventually 3D-ICs, it seems clear that modeling and simulation will play an increasing role in determining many of the guard rails for manufacturing and assembly before manufacturing and assembly even begins. “Reliability modeling and simulation tools are being used to better understand the reliability of bump structures. This proactive approach helps in identifying potential issues before they arise, enabling engineers to implement preventive measures,” said Zwenger.

Modeling and simulation at the system level also will be essential to understanding the complex interplay between reliability mechanisms with thermal and mechanical stress in multi-chiplet systems during operation.

“Electromigration for stacked die is challenging,” said Synopsys’ Lynch. “Localized, die-to-die workloads cause repetitive current flow in specific areas. This generates local heat, increasing EM resulting in wire degradation, while producing even more heat. Reducing the thermal issue becomes critical to ensuring EM reliability.”

As stated previously, solder bumps can become a site for EM reliability failure. “Engineers fine-tune bump design in terms of bump size, pitch, and shape to ensure uniformity and reliability across the entire package. This includes the adoption of innovative Cu bump structures for improved mechanical and electrical properties,” said Amkor’s Zwenger.

In flip-chip BGA and other flip-chip applications, underfill materials — typically thermoset epoxies — are used to reduce the thermal stresses on solder bumps. “Underfill materials play a critical role in providing mechanical support and thermal stability to the bumps,” Zwenger said. “Engineers are investing in the development of advanced underfill formulations with enhanced properties, such as improved adhesion, thermal conductivity, and stress relief.”

Conclusion
Because of its dependence on temperature, electromigration is a failure mechanism to watch and plan for as devices continue to scale and systems integrators continue to cram more and more chiplets of various functions into advanced packages.

“In advanced technologies, the current density is now in close proximity to the maximum density,” said Synopsys’ Lynch. “Anything that causes an increase in temperature poses a threat. Designers of multi-die systems need to understand the impact of temperature and design systems to remove the heat.”

References

1. JiHye Kwon, “Electromigration Performance Of Fine-Line Cu Redistribution Layer (RDL) For HDFO Packaging,” Semiconductor Engineering, Jan. 18, 2024, https://semiengineering.com/electromigration-performance-of-fine-line-cu-redistribution-layer-rdl-for-hdfo-packaging/
2. -Y. Tsai, et al., “An Electromigration Study of Cu Pillar Interconnects in Flip-chip QFN Packaging under Extreme Conditions for High-power Applications,” 2023 IEEE 25th Electronics Packaging Technology Conference (EPTC), Singapore, 2023, pp. 326-332, doi: 10.1109/EPTC59621.2023.10457564.

Related Reading
What Can Go Wrong In Heterogeneous Integration
Workflows and tools are disconnected, mechanical stress is ill-defined, and complete co-planarity is nearly impossible. But there are solutions on the horizon.
Thermal Integrity Challenges Grow In 2.5D
Work is underway to map heat flows in interposer-based designs, but there’s much more to be done.
Chiplets: 2023 (EBook)
What chiplets are, what they are being used for today, and what they will be used for in the future.

The post Electromigration Concerns Grow In Advanced Packages appeared first on Semiconductor Engineering.

A few months ago, we wondered if Wired had fired its entire fact-checking staff because it published what appeared to be a facts-optional article co-authored by professional consistently wrong Jaron Lanier and an academic I’d not come across before, Allison Stanger. The article suggested that getting rid of Section 230 “could save everything.” Yet the article was so far off-base that it was in the “not even wrong” category of wrongness.

I’m not going to review all the reasons it was wrong. You can go back to my original article for that, though I will note that the argument seemed to suggest that getting rid of Section 230 would both lead to better content moderation and, at the same time, only moderation based on the First Amendment. Both of those points are obviously wrong, but the latter one is incoherent.

Given his long track record of wrongness, I had assumed that much of the article likely came from Lanier. However, I’m going to reassess that in light of Stanger’s recent performance before the House Energy & Commerce Committee. Last week, there was this weird hearing about Section 230, in which the Committee invited three academic critics of Section 230, and not a single person who could counter their arguments and falsehoods. We talked about this hearing a bit in this week’s podcast, with Rebecca MacKinnon from the Wikimedia Foundation.

Stanger was one of the three witnesses. The other two, Mary Anne Franks and Mary Graw Leary, presented some misleading and confused nonsense about Section 230. However, the misleading and confused nonsense about Section 230 at least fits into the normal framework of the debate around Section 230. There is confusion about how (c)(1) and (c)(2) interact, the purpose of Section 230, and (especially) some confusion about CSAM and Section 230 and an apparent unawareness that federal criminal behavior is exempted from Section 230.

But, let’s leave that aside. Because Stanger’s submission was so far off the mark that whoever invited her should be embarrassed. I’ve seen some people testify before Congress without knowing what they’re talking about, but I cannot recall seeing testimony this completely, bafflingly wrong before. Her submitted testimony is wrong in all the ways that the Wired article was wrong and more. There are just blatant factual errors throughout it.

It is impossible to cover all of the nonsense, so we’re just going to pick some gems.

Without Section 230, existing large social media companies would have to adapt. Decentralized Autonomous Organizations, (DAOs) such as BlueSky and Mastodon, would become more attractive. The emergent DAO social media landscape should serve to put further brakes on virality, allowing a more regional social media ecosystem to emerge, thereby creating new demand for local media. In an ideal world, networks of DAOs would comprise a new fediverse (a collection of social networking servers which can communicate with each other, while remaining independently controlled), where users would have greater choice and control over the communities of which they are a part.

So, um. That’s not what DAOs are, professor. You seem to be confusing decentralized social media with decentralized autonomous organizations, which are a wholly different thing. This is kind of like saying “social security benefits” when you mean “social media influencers” because both begin with “social.” They’re not the same thing.

A decentralized social media site is what it says on the tin. It’s a type of social media that isn’t wholly controlled by a single company. Different bits of it can be controlled by others, whether its users or alternative third-party providers. A DAO is an operation, often using mechanisms like cryptocurrency and tokens, to enable a kind of democratic voting, or (possibly) a set of smart contracts, that determine how the loosely defined organization is run. They are not the same.

In theory, a decentralized social media site could be run by a DAO, but I don’t know of any that currently are.

Also, um, decentralized social media can only really exist because of Section 230. “Without Section 230,” you wouldn’t have Bluesky or Mastodon, because they would face ruinous litigation for hosting content that people would sue over. So, no, you would not have either more decentralized social media (which I think is what you meant) or DAOs (which are wholly unrelated). You’d have a lot less, because hosting third-party speech would come with way more liability risk.

Also, there’s nothing inherent to decentralized social media that means you’d “put the brakes on virality.” Mastodon has developed to date in a manner designed to tamp down virality, but Bluesky hasn’t? Nor have other decentralized social media offerings, many of which hope to serve a global conversation where virality is a part of it. And that wouldn’t really change with or without Section 230. Mastodon made that decision because of the types of communities it wanted to foster. And, indeed, its ability to do that is, in part, due to intermediary liability protections like Section 230, that enable the kind of small, more focused community moderation Mastodon embraces already.

It’s really not clear to me that Professor Stanger even knows what Section 230 does.

Non-profits like Wikipedia are concerned that their enterprise could be shut down through gratuitous defamation lawsuits that would bleed them dry until they ceased to exist (such as what happened with Gawker). I am not convinced this is a danger for Wikipedia, since their editing is done by humans who have first amendment rights, and their product is not fodder for virality….

Again, wut? The fact that their editing is “done by humans” has literally no impact on anything here. Why even mention that? Humans get sued for defamation all the time. And, if they’re more likely to get sued for defamation, they’re less likely to even want to edit at all.

And people get mad about their Wikipedia articles all the time, and sometimes they sue over them. Section 230 gets those lawsuits thrown out. Without it, those lawsuits would last longer and be more expensive.

Again, it’s not at all clear if Prof. Stanger even knows what Section 230 is or how it works.

The Facebook Files show that Meta knew that its engagement algorithms had adverse effects on the mental health of teenage girls, yet it has done nothing notable to combat those unintended consequences. Instead, Meta’s lawyers have invoked Section 230 in lawsuits to defend itself against efforts to hold it liable for serious harms

Again, this is just wrong. What the crux of the Facebook Files showed was that Meta was, in fact, doing research to learn about where its algorithms might cause harm in order to try to minimize that harm. However, because of some bad reporting, it now means that companies will be less likely to even do that research, because people like Professor Stanger will misrepresent it, claiming that they did nothing to try to limit the harms. This is just outright false information.

Also, the cases where Meta has invoked Section 230 would be unrelated to the issue being discussed here because 230 is about not being held liable for user content.

The online world brought to life by Section 230 now dehumanizes us by highlighting our own insignificance. Social media and cancel culture make us feel small and vulnerable, where human beings crave feeling large and living lives of meaning, which cannot blossom without a felt sense of personal agency that our laws and institutions are designed to protect. While book publishers today celebrate the creative contributions of their authors, for-profit Internet platforms do not.

I honestly have no idea what’s being said here. “Dehumanizes us by highlighting our own insignificance?” What are you even talking about? People were a lot more “insignificant” pre-internet, when they had no way to speak out. And what does “cancel culture” have to do with literally any of this?

Without Section 230, companies would be liable for the content on their platforms. This would result in an explosion of lawsuits and greater caution in such content moderation, although companies would have to balance such with first amendment rights. Think of all the human jobs that could be generated!

Full employment for tort lawyers! I mean, this is just a modern version of Bastiat’s broken window fallacy. Think of all the economic activity if we just break all the windows in our village!

Again and again, it becomes clear that Stanger has no clue how any of this works. She does not understand Section 230. She does not understand the internet. She does not understand the First Amendment. And she does not understand content moderation. It’s a hell of a thing, considering she is testifying about Section 230 and its impact on social media and the First Amendment.

At a stroke, content moderation for companies would be a vastly simpler proposition. They need only uphold the First Amendment, and the Courts would develop the jurisprudence to help them do that, rather than to put the onus of moderation entirely on companies.

That is… not at all how it would work. They don’t just need to “uphold the First Amendment” (which is not a thing that companies can even do). The First Amendment’s only role is in restricting the government, not companies, from passing laws that infringe on a person’s ability to express themselves.

Instead, as has been detailed repeatedly, companies would face the so-called “moderator’s dilemma.” Because the First Amendment requires distributors to have actual knowledge of content violating the law to be liable, a world without Section 230 would incentivize one of two things, neither of which is “upholding the First Amendment.” They would either let everything go and do as little moderation as possible (so as to avoid the requisite knowledge), or they’d become very aggressive in limiting and removing content to avoid liability (even though this wouldn’t work and they’d still get hit with tons of lawsuits).

We’ve been here before. When government said the American public owned the airwaves, so television broadcasting would be regulated, they put in place regulations that supported the common good. The Internet affects everyone, and our public square is now virtual, so we must put in place measures to ensure that our digital age public dialogue includes everyone. In the television era, the fairness doctrine laid that groundwork. A new lens needs to be developed for the Internet age.

Except, no, that’s just factually wrong. The only reason that the government was able to put regulations on broadcast television was because the government controlled the public spectrum which they licensed to the broadcasters. The Supreme Court made clear in Red Lion that without that, they could not hinder the speech of media companies. So, the idea that you can just apply similar regulations to the internet is just fundamentally clueless. The internet is not publicly owned spectrum licensed to anyone.

While Section 230 perpetuates an illusion that today’s social media companies are common carriers like the phone companies, they are not. Unlike Ma Bell, they curate the content they transmit to users

Again, it appears the Professor is wholly unaware of Section 230 and how it works. The authors of Section 230 made it clear over and over again that they wrote 230 to be the opposite of common carriers. No one who supports Section 230 thinks it makes platforms into common carriers, because it does not. The entire point was to free up companies to choose how to curate content, so as to allow those companies to craft the kinds of communities they wanted. They only people claiming the “illusion” of common carrierness are those who are trying to destroy Section 230.

So there is no “illusion” here, unless you don’t understand what you’re talking about.

The repeal of Section 230 would also be a step in the right direction in addressing what are presently severe power imbalances between government and corporate power in shaping democratic life. It would also shine a spotlight on a globally disturbing fact: the overwhelming majority of global social media is currently in the hands of one man (Mark Zuckerberg), while nearly half the people on earth have a Meta account. How can that be a good thing under any scenario for the free exchange of ideas?

I mean, we agree that it’s bad that Meta is so big. But if you remove Section 230 (as Meta itself has advocated for!), you help Meta get bigger and harm the competition. Meta has a building full of lawyers. They can handle the onslaught of lawsuits that this would bring (as Stanger herself gleefully cheers on). It’s everyone else, the smaller sites, such as the decentralized players (not DAOs) who would get destroyed.

Mastodon admins aren’t going to be able to afford to pay to defend the lawsuits. Bluesky doesn’t have a building full of lawyers. The big winner here would be Meta. The cost to Meta of removing Section 230 is minimal. The cost to everyone trying to eat away at Meta’s marketshare would be massive.

The new speech is governed by the allocation of virality in our virtual public square. People cannot simply speak for themselves, for there is always a mysterious algorithm in the room that has independently set the volume of the speaker’s voice. If one is to be heard, one must speak in part to one’s human audience, in part to the algorithm. It is as if the constitution had required citizens to speak through actors or lawyers who answered to the Dutch East India Company, or some other large remote entity. What power should these intermediaries have? When the very logic of speech must shift in order for people to be heard, is that still free speech? This was not a problem foreseen in the law.

I mean, this is just ahistorical nonsense. Historically, most people had no way to get their message out at all. You could talk to your friends, family, co-workers, and neighbors, and that was about it. If you wanted to reach beyond that small group, you required some large gatekeeper (a publisher, a TV or radio producer, a newspaper) to grant you access, which they refused for the vast majority of people.

The internet flipped all that on its head, allowing anyone to effectively speak to anyone. The reason we have algorithms is not “Section 230” and the algorithms aren’t “setting the volume,” they came in to deal with the simple fact that there’s just too much information, and it was flooding the zone. People wanted to find information that was more relevant to them, and with the amount of content available online, the only way to manage that was with some sort of algorithm.

But, again, the rise of algorithms is not a Section 230 issue, even though Stanger seems to think it is.

Getting rid of the liability shield for all countries operating in the United States would have largely unacknowledged positive implications for national security, as well as the profit margins for US-headquartered companies. Foreign electoral interference is not in the interests of democratic stability, precisely because our enemies benefit from dividing us rather than uniting us. All foreign in origin content could therefore be policed at a higher standard, without violating the first amendment or the privacy rights of US citizens. As the National Security Agency likes to emphasize, the fourth amendment does not apply to foreigners and that has been a driver of surveillance protocols since the birth of the Internet. It is probable that the Supreme Court’s developing first amendment jurisprudence for social media in a post-230 world would embrace the same distinction. At a stroke, the digital fentanyl that TikTok represents in its American version could easily be shut down, and we could through a process of public deliberation leading to new statutory law collectively insist on the same optimization targets for well-being, test scores, and time on the platform that Chinese citizens currently enjoy in the Chinese version of TikTok (Douyin)

Again, this is a word salad that is mostly meaningless.

First of all, none of this has anything to do with Section 230, but rather the First Amendment. And it’s already been noted, clearly, that the First Amendment protects American users of foreign apps.

No one is saying “you can’t ban TikTok because of 230,” they’re saying “you can’t ban TikTok because of the First Amendment.” The Supreme Court isn’t going to magically reinvent long-standing First Amendment doctrine because 230 is repealed. This is nonsense.

And, we were just discussing what utter nonsense it is to claim that TikTok is “digital fentanyl” so I won’t even bother repeating that.

There might also be financial and innovation advantages for American companies with this simple legislative act. Any commercial losses for American companies from additional content moderation burdens would be offset by reputational gains and a rule imposed from without on what constitutes constitutionally acceptable content. Foreign electoral interference through misinformation and manipulation could be shut down as subversive activity directed at the Constitution of the United States, not a particular political party.

This part is particularly frustrating. This is why internet companies already moderate. Stanger’s piece repeatedly seems to complain both about too little moderation (electoral interference! Alex Jones!) and too much moderation (algorithms! dastardly Zuck deciding what I can read!).

She doesn’t even seem to realize that her argument is self-contradictory.

But, here, the supposed “financial and innovation advantages” from American companies being able to get “reputational gains” by stopping “misinformation” already exists. And it only exists because of Section 230. Which Professor Stanger is saying we need to remove to get the very thing it enables, and which would be taken away if it were repealed.

This whole thing makes me want to bang my head on my desk repeatedly.

Companies moderate today to (1) make users’ experience better and (2) to make advertisers happier that they’re not facing brand risk from having ads appear next to awful content. The companies that do better already achieve that “reputational benefit,” and they can do that kind of moderation because they know Section 230 prevents costly, wasteful, vexatious litigation from getting too far.

If you remove Section 230, that goes away. As discussed above, companies then are much more limited in the kinds of moderation they can do, which means users have a worse experience and advertisers have a worse experience, leading to reputational harm.

Today, companies already try to remove or diminish the power of electoral interference. That’s a giant part of trust & safety teams’ efforts. But they can really only do it safely because of 230.

The attention-grooming model fostered by Section 230 leads to stupendous quantities of poor-quality data. While an AI model can tolerate a significant amount of poor-quality data, there is a limit. It is unrealistic to imagine a society mediated by mostly terrible communication where that same society enjoys unmolested, high-quality AI. A society must seek quality as a whole, as a shared cultural value, in order to maximize the benefits of AI. Now is the best time for the tech business to mature and develop business models based on quality.

I’ve read this paragraph multiple times, and I still don’t know what it’s saying. Section 230 does not lead to an “attention-grooming model.” That’s just how society works. And, then, when she says society must seek quality as a whole, given how many people are online, the only way to do that is with algorithms trying to make some sort of call on what is, and what is not, quality.

That’s how this works.

Does she imagine that without Section 230, algorithms will go away, but good quality content will magically rise up? Because that’s not how any of this actually works.

Again, there’s much more in her written testimony, and none of it makes any sense at all.

Her spoken testimony was just as bad. Rep. Bob Latta asked her about the national security claims (some of which were quoted above) and we got this word salad, none of which has anything to do with Section 230:

I think it’s important to realize that our internet is precisely unique because it’s so open and that makes it uniquely vulnerable to all sorts of cyber attacks. Just this week, we saw an extraordinarily complicated plot that is most likely done by China, Russia or North Korea that could have blown up the internet as we know it. If you want to look up XZ Utils, Google that and you’ll find all kinds of details. They’re still sorting out what the intention was. It’s extraordinarily sophisticated though, so I think that the idea that we have a Chinese company where data on American children is being stored and potentially utilized in China, can be used to influence our children. It can be used in any number of ways no matter what they tell you. So I very much support and applaud the legislation to repeal, not to repeal, but to end TikToks operations in the United States.

The national security implications are extraordinary. Where the data is stored is so important and how it can be used to manipulate and influence us is so important. And I think the next frontier that I’ll conclude with this, for warfare, is in cyberspace. It’s where weak countries have huge advantages. They can pour resources into hackers who could really blow up our infrastructure, our hospitals, our universities. They’re even trying to get, as you know, into the House. This House right here. So I think repealing Section 230 is connected to addressing a host of potential harms

Nothing mentioned in there — from supply chain attacks like xz utils, to a potential TikTok ban, to hackers breaking into hospitals — has anything whatsoever to do with Section 230. She just throws it in at the end as if they’re connected.

She also claimed that Eric Schmidt has come out in favor of “repealing Section 230,” which was news to me. It also appears to be absolutely false. I went and looked, and the only thing I can find is a Digiday article which claims he called for reforms (not a repeal). The article never actually quotes him saying anything related to Section 230 at all, so it’s unclear what (if anything) he actually said. Literally the only quotes from Schmidt are old man stuff about how the kids these days just need to learn how to put down their phones, and then something weird about the fairness doctrine. Not 230.

Later, in the hearing, she was asked about the impact on smaller companies (some of which I mentioned above) and again demonstrates a near total ignorance of how this all works:

There is some concern, it’s sometimes expressed from small businesses that they are going to be the subject of frivolous lawsuits, defamation lawsuits, and they can be sued out of business even though they’ve defamed no one. I’m less concerned about that because if we were to repeal section (c)(1) of Section 230 of those 26 words, I think the First Amendment would govern and we would develop the jurisprudence to deal with small business in a more refined way. I think if anything, small businesses are in a better position to control and oversee what’s on their platforms than these monolithic large companies we have today. So with a bit of caution, I think that could be addressed.

The First Amendment always governs. But Section 230 is the “more refined way” that we’ve developed to help protect small businesses. The main function of Section 230 is to get cases, that would be long and costly if you had to defend them under the First Amendment, tossed out much earlier at the motion to dismiss stage. Literally that’s Section 230’s main purpose.

If you had to fight it out under the First Amendment, you’re talking about hundreds of thousands of dollars and a much longer case. And that cost is going to lead companies to (1) refuse to host lots of protected content, because it’s not worth the hassle, and (2) be much more open to pulling down any content that anyone complains about.

This is not speculative. There have been studies on this. Weaker intermediary laws always lead to massive overblocking. If Stanger had done her research, or even understood any of this, she would know this.

So why is she the one testifying before Congress?

I’ll just conclude with this banger, which was her final statement to Congress:

I just want to maybe take you back to the first part of your question to explain that, which I thought was a good one, which is that we have a long history of First Amendment jurisprudence in this country that in effect has been stopped by Section 230. In other words, if you review, if you remove (c)(1), that First Amendment jurisprudence will develop to determine when it is crime fire in a crowded theater, whether there’s defamation, whether there’s libel. We believe in free speech in this country, but even the First Amendment has some limits put on it and those could apply to the platforms. We have a strange situation right now if we take that issue of fentanyl that we were discussing earlier, what we have right now is essentially a system where we can go after the users, we can go after the dealers, but we can’t go after the mules. And I think that’s very problematic. We should hold the mules liable. They’re part of the system.

Yeah. So. She actually went to the whole fire in a crowded theater thing. This is the dead-on giveaway that the person speaking has no clue about the First Amendment. That’s dicta from a case from over 100 years ago, in a case that is no longer considered good law, and hasn’t been in decades. Even worse, that dicta came in a case about jailing war protestors.

She also trots out yet another of Ken “Popehat” White’s (an actual First Amendment expert) most annoying tropes about people opining on the First Amendment without understanding it: because the First Amendment has some limits, this new limit must be okay. That’s not how it works. As Ken and others have pointed out, the exceptions to the First Amendment are an established, known, and almost certainly closed set.

The Supreme Court has no interest in expanding that set. It refused to do so for animal crush videos, so it’s not going to magically do it for whatever awful speech you think it should limit.

Anyway, it was a shame that Congress chose to hold a hearing on Section 230 and only bring in witnesses who hate Section 230. Not a single witness who could explain why Section 230 is so important was brought in. But, even worse, they gave one of the three witness spots to someone who was spewing word salad level nonsense, that didn’t make any sense at all, was often factually incorrect (in hilariously embarrassing ways), and seemed wholly unaware of how any relevant thing worked.

Do better, Congress.

Experts at the Table: Semiconductor Engineering sat down to discuss Vehicle-To-Everything (V2X) technology and the path to deployment, with Shawn Carpenter, program director for 5G and space at Ansys; Lang Lin, principal product manager at Ansys; Daniel Dalpiaz, senior manager product marketing, Americas, green industrial power division at Infineon; David Fritz, vice president of virtual and hybrid systems at Siemens EDA; and Ron DiGiuseppe, senior marketing manager, automotive IP segment at Synopsys. What follows are excerpts from that conversation.

L-R: Ansys’ Carpenter; Ansys’ Lin; Infineon’s Dalpiaz; Siemens EDA’s Fritz; Synopsys‘ DiGiuseppe.

SE: What is the potential of vehicle-to-everything technology, and what role will the semiconductor ecosystem play in making this a reality?

DiGiuseppe: V2X is a technology that’s not just years, but decades, in the making. It initially started as a dedicated short-range communications (DSRC) type of technology, and has globally transitioned into a cellular technology, although many of those V2X applications are not just cellular. There are other spectrum allocations V2X can run on, including WiFi or other general-use technology. So it’s not limited to cellular. Also, it’s not just a technology. It’s an application, an outcome, and there are a lot of valuable uses, many of which are safety-related, but there are others, such as efficiency of traffic management notifications. V2X has a wide number of uses. The deployment will be done in stages, and there’s a lot of activity even though it’s taken a long time.

Lin: When I see the keyword V2X, it reminds me of everything about how the car can communicate with anything in the world. It’s a very exciting moment that we’re here today to be able to make some kind of technology to enable great communication between vehicles and people, in network infrastructures and car to car communications. Today, there is already something implemented. For instance, in car network systems we can connect our phone to the car already, but we’re still in the first mile. We’ve started on the journey, but we have a long way to go as far as how to connect car-to-car, how to connect the car to the entire infrastructure of networks, and to the internet. There are a lot of unknowns on the road while we start driving on this journey, and safety and security are definitely the biggest concerns. What if my network is being jeopardized?

Dalpiaz: V2X is part of a much bigger smart grid ecosystem. This will certainly play a very important role, especially as the grid becomes smart and decentralized. This is what will enable the future energy ecosystem, having renewable energies, energy storage systems all connected. And as we see more EVs being used as mobile battery storage. this is something that will certainly enable, and is part of, a smart grid ecosystem that everybody’s talking about.

Fritz: The days of independent semiconductor and software development are over. It is the need for OEMs to control their own destiny, driven by growing consumer and competitive demand, that has all but eliminated the ability to sell a one-size-fits-all product. We’ve known for a very long time that software needs to drive semiconductors, and semiconductors need to drive software. This symbiotic relationship, and the tools and methodologies needed to support this paradigm shift, are essential to producing a highly successful, complex, and competitive solution that meets consumer demands.

SE: What are the discrete pieces of V2X that need to be connected?

Dalpiaz: From the semiconductor point of view, especially with the usage of wide bandgap materials, a few companies are seeing that it’s possible to increase efficiency and power density. Being able to not only provide such solutions, but have everything connected in one box, is part of the smart ecosystem. Then, having the electric vehicles, energy storage, solar — everything combined into one box. Twenty years ago, before the iPhone, we used to have a fax machine, a camera for photographs, a computer. The future of this ecosystem is going to have one box sitting in your home, and have all this stuff connected together. So from the semiconductor point of view, especially with silicon carbide, it is something that is possible today, and it can achieve a very high level of efficiency — about 99%, very close to 100%. And of course, we need to make the system smaller to fit in a vehicle.

DiGiuseppe: One of the key stakeholders is the cellular companies. When we look at cellular V2X, one of the main challenges is interoperability. You have different devices in different model-year cars, so for the vehicle-to-vehicle communications, those different devices need to be interoperable. Then, the car will be talking to the infrastructure, so the roadside units need to be interoperable with the cars and devices in the cars. Then, of course, you have vehicle-to-pedestrians, vehicle-to-e-mobility like vehicle-to-bicycles, vehicle-to-motorcycles interoperability between all the devices over the medium. Whether it’s cellular or Wi-Fi or other technologies, it all needs to be interoperable. That will allow deployments in one locality to work in another locality, because even if they’re interoperable in one deployment in one region, we’ve got to make sure they’re also interoperable in other regions. So it’s a large scale interoperability goal.

Lin: Ron, you’re talking about interoperability, and Daniel talked about the ecosystem. From my side, I would also mention some standards are necessary. For EDA, to help build such an ecosystem and chips, we need some rules to give to engineers as to what’s to be followed. There are two important standards in my mind. One is the vehicle safety standard ISO 26262, which regulates a couple of safety standards for on-road vehicle chip design. Another is the cyber security standard, ISO 21434. If I make a tool, I probably will follow those standards, and then think about how the tool could help users decide a pass/failure criteria regarding their design, making sure to meet the security and safety target from the standard.

DiGiuseppe: In addition to standards, last October the U.S. Department of Transportation released its national V2X deployment plan. That plan, which is still in draft feedback stage, lays out — at least in the U.S. — the whole timeline for deployments. That kind of oversight plan overlays onto the standards that Lang was just talking about. That deployment plan outlines the different contributions from all the different stakeholders, from the automakers/OEMs to the software developers for the applications. So overlaid on top of standards is a deployment plan, and a government deployment plan outlines that. Plus, there are a lot of government stakeholders, like the FCC allocating spectrum, and the Department of Transportation deploying all these deployments, and that’s in addition to the technology providers.

Fritz: It would take days to adequately answer those questions, but at the core, the root design components are connectivity, power, performance, and acceleration. Connectivity with the proper protocols allows computational tasks to be distributed. This is particularly important in automotive, where the physical distance between sensing, actuating and computing nodes is critical for predictable performance. In the case of V2X, connectivity enables the normalization of external data, whether it involves smart city infrastructure or another vehicle. It’s important to note that the form of the shared data grows exponentially with the capacity to describe the environment, and therefore the compute requirements to process and understand it. For example, a data form that can describe signage in the U.S. is relatively small, but one that is universal with variations recognizable is much larger and more ambiguous. This drives design parameters that directly impact manufacturing, development, and service cost functions. Further, the normalization of the data has an impact on the overall design and design component interactions. In the case of power, it goes without saying that high compute requirements, and the associated necessary cooling, can have a significant impact on EV range and manufacturing costs. Performance can take many forms, but as software loads increase with hypervisors, specialized operating systems, and protocol stacks, not to mention very complex application software, all must meet stringent mission critical requirements. Finally, acceleration is of growing importance because it allows workloads to be handed off to specialized hardware that is better equipped to handle that load. An example is running AI inferencing on a CPU is typically far slower and more power-hungry than on an NPU, but a GPU could be idle and available to do the same task. On the other hand, a small CNN can be handled quite easily on a CPU with a few simple instructions. It is at the intersection of these major design components where an OEM will find its differentiation. Therefore, having a system capable of exploring this complex hardware and software space quickly, and with a small team, is critical for an OEM to demand of its suppliers what is required for the success of its platforms. Again, controlling your own destiny is essential to survival.

SE: With all of this interoperability, what happens when there are parts of the ‘everything’ — whether it’s the car or the infrastructure or pedestrians — that are not updated with the latest technologies or different aspects of what needs to be there for conductivity?

DiGiuseppe: In addition to that challenge, this includes backward compatibility for automotive. For someone buying a car in 2025, you would expect any V2X technology to work in 2040. But in the meantime, all those standards that we’re talking about are continuing to evolve, so they need to be backward compatible.

Carpenter: This highlights the need for a digital twin capability for modeling this infrastructure to be able to understand that when we get two years down the road, some devices may not be reprogrammable. We may not be able to flash a particular device. We need to be able to look at that, and be able to simulate that in advance to understand what will happen. What will this do? We’re seeing this show a little bit, even giving a nod to what Ron was talking about earlier with interoperability. We have customers who want to be able to validate real hardware stuff that they’re developing on the lab bench, but they want to do it with the fidelity of a real system operating on a car, in a virtual city, with the live interaction of the channel with a gNodeB 5G base station mounted up on a building someplace, and they want to know how this will work in the context of the situation that it’s supposed to serve. And if something goes wrong in that scene, can we introduce something into this device and run our real silicon development platform against it to understand what happens here. If we go into a deep shadow, a deep fade area, and I’m not getting updates, yet I’m hurtling down the road at a certain speed, how long can I do this before I receive corrective information? What if someone’s software deck out there doesn’t get reprogrammed or doesn’t get the latest version of the standard safety protocols or something like that? We’re going to need this ability to carry models of stuff that was built two or three years ago in today’s infrastructure, model that, and understand in advance what’s going to happen with it so that we have an approach to do this. This is what the Department of Defense is doing today with their digital thread enablement, to have a way to capture that with legacy models of what they built years ago, but apply it in modern missions and understand, ‘Does it work? Does it fit? Does it not fit? What do we need to do to the existing system to make sure that we’re safe here?’ That is an approach we clearly see the automakers beginning to look at as a way to future-proof some of these systems and make sure that they’ve got a way to test them as they go forward.

Fritz: It’s become very clear from several popularized incidents that simply stopping and waiting for tech support to find you and get you going again is not going to be a successful strategy. In the end, the vehicle must make decisions at least as thoughtful as an average human would make. This is entirely possible, but not if too much emphasis is placed in the design phase on the dependencies between communicating (or non-communicating) actors. For this reason, we will always require sophisticated decision-making in-vehicle to be widely accepted.

SE: How does the design team stay up to date with everything?

DiGiuseppe: On the vehicle side, they’re going to be relying on over-the-air (OTA) software updates, which is relatively new in the automotive industry. But clearly, once we identify a software update, we’re going to need to roll out that software update, and OTA is obviously going to be used hand-in-hand with the updates to V2X as it moves forward.

SE: From a developer standpoint, they have to design to these all these regulations. What are the issues here?

Lin: As a software developer, if you think about a vehicle 10 years ago, you mainly just replaced hardware. You replaced your brakes, you replaced your engine, adding some fluid. These are all old styles. Right now, if you have the V2X network, you’d expect probably daily updates because software is evolving daily, and your whole communication system infrastructure is under the whole internet evolution, so you’re going to have to keep pace with it. That’s a lot of work for developers.

Carpenter: There could be implications on edge processing. The telecommunications providers are going to need to put a lot more compute closer to the radio head, and clearly they’re already exploring the possibilities of getting not just central processing cores, CPU cores, but there will be GPU cores and Tensor Processing Units, and we don’t know what all yet for AI, that will be a part of this safety infrastructure and information/infotainment delivery. There’s a lot more compute that’s going to have to happen with a much shorter latency. Augmented reality with heads-up displays — imagine the possibilities coming in safety systems with heads-up displays in cars. Then imagine the amount of processing that it’s going to take. So the telecom providers will need to be a major part of that, together with most of the local government regulatory groups that are going to foster that safety system. Each municipality probably has to decide what do they adopt, what level of standard will they use, and deliver. Who invests in that? The future is really exciting, but there are a few things yet to be sorted out in terms of the investment needed to really deliver that promise.

Dalpiaz: I’m more in the infrastructure side, and one of the questions we always have is, ‘With all this focus on renewables and decentralization of the grid, can the grid handle such expectations or such projects?’ Having more people connecting and feeding energy back into the grid, and managing all of this, that’s always the question that you have to go through and consider.

Fritz: The fact is that keeping up to date is not practical. However, that doesn’t mean that a methodology cannot be employed to accept changes into the development system, and therefore be folded into the development process. CI/CD systems with digital twin golden models already are being developed, with nightly regressions run against complex (and possibly changing) requirements. In this way, requirement changes are automatically addressed as they occur, and solutions can be rolled into an Agile methodology through nightly regressions. This is an important benefit of a modern development methodology that has been used in other industries for years, but it’s just now finding purchase in progressive automotive companies.

Related Reading
Growing Challenges For Increasingly Connected Vehicles
OEMs have high expectations for connected vehicles and global growth opportunities, but it’s not that simple.
Software-Defined Vehicles Ready To Roll
New approach could have big effects on cost, safety, security, and time to market.

The post V2X Path To Deployment Still Murky appeared first on Semiconductor Engineering.