Completed chips coming in from the foundry are topic to a battery of assessments. For these destined for important programs in automobiles, these assessments are notably intensive and might add 5 to 10 p.c to the price of a chip. However do you actually need to do each single check?
Engineers at NXP have developed a machine-learning algorithm that learns the patterns of check outcomes and figures out the subset of assessments which are actually wanted and people who they might safely do with out. The NXP engineers described the method on the IEEE International Test Conference in San Diego final week.
NXP makes all kinds of chips with complicated circuitry and advanced chip-making technology, together with inverters for EV motors, audio chips for consumer electronics, and key-fob transponders to safe your automotive. These chips are examined with totally different alerts at totally different voltages and at totally different temperatures in a check course of known as continue-on-fail. In that course of, chips are examined in teams and are all subjected to the whole battery, even when some components fail a few of the assessments alongside the best way.
Chips have been topic to between 41 and 164 assessments, and the algorithm was capable of advocate eradicating 42 to 74 p.c of these assessments.
“Now we have to make sure stringent high quality necessities within the discipline, so we’ve got to do a number of testing,” says Mehul Shroff, an NXP Fellow who led the analysis. However with a lot of the particular manufacturing and packaging of chips outsourced to different firms, testing is without doubt one of the few knobs most chip firms can flip to manage prices. “What we have been making an attempt to do right here is provide you with a approach to cut back check price in a manner that was statistically rigorous and gave us good outcomes with out compromising discipline high quality.”
A Check Recommender System
Shroff says the issue has sure similarities to the machine learning-based recommender systems utilized in e-commerce. “We took the idea from the retail world, the place a knowledge analyst can take a look at receipts and see what objects individuals are shopping for collectively,” he says. “As a substitute of a transaction receipt, we’ve got a singular half identifier and as an alternative of the objects {that a} shopper would buy, we’ve got a listing of failing assessments.”
The NXP algorithm then found which assessments fail collectively. In fact, what’s at stake for whether or not a purchaser of bread will wish to purchase butter is sort of totally different from whether or not a check of an automotive half at a specific temperature means different assessments don’t should be performed. “We have to have one hundred pc or close to one hundred pc certainty,” Shroff says. “We function in a unique area with respect to statistical rigor in comparison with the retail world, but it surely’s borrowing the identical idea.”
As rigorous because the outcomes are, Shroff says that they shouldn’t be relied upon on their very own. It’s a must to “make sure that it is sensible from engineering perspective and that you may perceive it in technical phrases,” he says. “Solely then, take away the check.”
Shroff and his colleagues analyzed knowledge obtained from testing seven microcontrollers and purposes processors constructed utilizing superior chipmaking processes. Relying on which chip was concerned, they have been topic to between 41 and 164 assessments, and the algorithm was capable of advocate eradicating 42 to 74 p.c of these assessments. Extending the evaluation to knowledge from different sorts of chips led to an excellent wider vary of alternatives to trim testing.
The algorithm is a pilot venture for now, and the NXP staff is seeking to increase it to a broader set of components, cut back the computational overhead, and make it simpler to make use of.
From Your Website Articles
Associated Articles Across the Internet
