By Junko Yoshida

What’s at stake:
Picture chips in data centers silently failing, leaving no trace in system logs. Such undetectable errors could steadily spread contagion across several services. Consider such a scenario in a two-engine airplane. Suppose one of the engines silently dies, unnoticed. After landing, the pilot takes off again for a new mission, assuming he has two functioning engines. One could say that this is impossible because the pilot can see — and hear — the busted engine. Unlike the plane, a busted engine in a datacenter hyperscaler can’t be seen or heard, and won’t kill anyone. But the silent crash of a critical component could trigger system-wide failures.

Designers, manufacturers and users of chips have long dreaded “soft errors,” if chips subjected to particle strikes from cosmic rays suffer unexpected bit flips.

Meanwhile, hyperscalers are lately alarmed about “hard errors” in chips with a physical defect that slipped through the manufacturing testing process or degraded gradually while deployed for a long time.

Both types of error are devastating to computing systems, especially when their “silence” affects critical missions. When chips give no indication that something has gone wrong or miscalculated, the phenomenon is called “Silent Data Corruption (SDC).”

By Bolaji Ojo

Intel Corp.’s massive challenges and the efforts of its recent leaders to thread their way back to growth have become the subject of MBA studies.

Additional fodder for business school forensic examination of Intel cropped up last week in CEO Patrick Gelsinger’s subtle but intriguing hints about the chipmaker’s future.

After repeatedly insisting that the microprocessor supplier’s revitalization plans do not include a breakup, Gelsinger last week said: “We’re building two world-class companies,” referring to the company’s products group and Intel Foundry Services, the unit created to provide outsourced semiconductor manufacturing services to other chipmakers.

To further deepen the mystery, Gelsinger said his goal is to turn the company’s products group into a “world-class fabless company.” Will these two entities co-exist under the same stable or will they separate and fashion their separate futures as independent entities?

By Junko Yoshida

What’s at stake:
To Cuda or not to Cuda revives the decades-old debate over licensed vs. open-source software. But at stake is the safety, for those who choose to develop their own AV software stack outside the context of a safety-certified Nvidia’s SoC and Drive OS. The onus of qualification is now placed on the carmakers’ system integrators. It’s “a huge undertaking,” to say the least, according to a safety expert.

In designing next-generation highly automated vehicles, carmakers’ top priority has to be the right advanced automotive SoC. OEMs need a highly integrated chip with enough processing capability to power neural networks, support sensor fusion and manage central engine functions in new ADAS models.

By Ron Wilson

What’s at stake:
2 nm process nodes will require novel transistors and will push the limits of EUV lithography. But if the interconnect can’t scale as well as the transistors, the new processes will deliver neither the speed, nor the density, nor the power savings designers are seeking.

As the leading edge of the semiconductor manufacturing industry — that is, Intel, Samsung, and TSMC — grinds inexorably toward the 2 nm process node, there has been much discussion of new kinds of transistors and of the new demands on EUV lithography. But another element of process technology is equally critical to the success of 2nm, and equally hard to scale: the interconnect wires that connect the transistors into circuits, and the circuits into functional blocks.

By Junko Yoshida

CrowdStrike released a preliminary incident report on the catastrophic software update that caused a global IT outage last Friday.

The company’s proposed remedies, in a section entitled “How Do We Prevent This From Happening Again?” parallel recommendations in our previous story. 

CrowdStrike now says it will “implement a staggered deployment strategy for Rapid Response Content.” But some details in the preliminary report are surprising, particularly CrowdStrike’s explanation of how it implemented massively deploy its so-called “Rapid Response Content” without testing.

It turns out, as professor Phil Koopman of Carnegie Mellon University, concluded in our recent interview, that Crowdstrike tests software changes subject to phased release by IT groups. “But it pushes data changes straight to production with NO TESTING. The only precaution is a check by CrowdStrike’s own Content Validator.” The Content Validator was defective, added Koopman, “allowing bad content to get through.”

By Junko Yoshida

What’s at stake:
Renesas and NXP are rolling out software-defined vehicle development platforms. A platform encompassing hardware, software and cloud-based tools is a huge advancement compared to past offerings to the automotive industry. But no one dares to promise their effectiveness in a real world where OEMs design SDVs with hardware and software from multiple vendors.

To serve the plans of OEMs designing software-defined vehicles (SDVs), Renesas has unveiled an SDV development platform called “ROX” (R-Car Open Access),” boasting that it integrates “all essential hardware, operating systems (OS), software and tools” automakers need to rapidly develop next-generation vehicles “with secure and continuous software updates,” said Renesas.

Similarly, NXP Semiconductors announced earlier this year “CoreRide” designed to address the complexity, scalability and costs carmakers face as they transition their creaky E/E architecture to newer software-defined vehicle architectures.

This initiative by the two leading automotive chip suppliers illustrates their urgent perception that they must minimize the impact of the software crisis facing many car OEMs.

By Ron Wilson

What’s at stake:
There is growing discussion of AI in chip design. Could this be mainly marketing, or could it reflect a new weapon in the EDA armory? If the latter, AI could take on some of the most intractable challenges of designing multi-die systems.

Global industry is placing huge bets that artificial intelligence will create a step-function increase in productivity. From customer service to materials handling, from bond trading to medical research, this faith thrives across a broad domain. But what exactly do these faithful mean when they say AI? There are many species in that phylum. And how exactly will AI — demonstrably excellent at pattern recognition and parlor games, but with fundamental limitations when it comes to accuracy and predictability — make knowledge workers more productive?

The EDA industry, with its witheringly complex tasks, massive data sets, vastly skilled practitioners, and utter intolerance of error, offers an excellent laboratory for exploring these questions. The emerging field of high-performance multi-die modules in particular includes some of the most formidable challenges. And among the tasks in this area, the challenge of multi-physics analysis of modules — analyzing the interacting electromagnetic, thermal, and mechanical properties of a module design — can be most daunting. This may be a great place to ask our questions.

By Junko Yoshida

What’s at stake:
The CHIPS and Science Act has created the opportunity — and federal subsidies — for semiconductor companies both big and small to return chip production capacity to the United States. But thus far, the Department of Commerce’s decision-making process has been shrouded in mystery. The latest announcement of Rogue Valley Microdevices getting the grant gives us a glimpse into the federal government’s inner workings.

Without the power of major market share, what does it take to horn into federal funding action?  Likely ingredients include chutzpah, street cred, and experience in the technology biz. These qualities exist emphatically at Rogue Valley Microdevices (Medford, Oregon), a pure-play MEMS foundry founded by Jessica Gomez, once a lab operator at Standard Microsystems (SMSC) in Long Island, New York. Gomez worked at a small aging fab — attached to the then SMSC’s headquarters — where the company made MEMS inkjet printheads. 

Gomez’s journey started with a local community college science degree. She gained first-hand operational experience at SMSC and went on to run a foundry service at a short-lived MEMS company in California. This background convinced Gomez that she could establish her own MEMS foundry. She launched Rogue Valley Microdevices (RVM) in 2003.