IIRC, it was Carl Bruggeman's IPSA Thesis that showed us how to laser out bad cores.
100x defect tolerance: How we solved the yield problem
91–100 of 186 posts
Re: 100x defect tolerance: How we solved the yield problem
#92Earlier quoted context omitted.
Why does their chip have to be rectangular, anyways? Couldn't they cut out a (blocky) circle too?
The cost driver for fabbing out wafers is the number of layers and the number of usable devices per wafer. Higher layer count increases cost and tends to decrease yield, and more robust designs with higher yields increase usable devices per wafer. If circles or other shapes could help with either of those, they would likely be used. Generally the end goal is to have the most usable devices per wafer, so they'll be pa…
Right, but they're making just one usable device per wafer already.
Re: 100x defect tolerance: How we solved the yield problem
#93Earlier quoted context omitted.
Is the wafer itself so expensive? I assume they don't pattern the unused area, so the process should be quicker?
> I assume they don't pattern the unused area I’m out of date on this stuff, so it’s possible things have changed, but I wouldn’t make that assumption. It is (used to be?) standard to pattern the entire wafer, with partially-off-the-wafer dice around the edges of the circle. The reason for this is that etching behavior depends heavily on the surrounding area — the amount of silicon or copper whatever etched in your n…
All the process steps are limited by wafers for hour. Lithography (esp EUV) might be slightly faster, but that's not 30% of total steps, since you generally have deposit and etch/implant for every lithography step.
It's close to a dead loss in process cost.
Re: 100x defect tolerance: How we solved the yield problem
#94I think this is an important step, but it skips over that 'fault tolerant routing architecture' means you're spending die space on routes vs transistors. This is exactly analogous to using bits in your storage for error correcting vs storing data. That said, I think they do a great job of exploiting this technique to create a "larger"[1] chip. And like storage it benefits from every core is the same and you don't nee…
> Xilinx was still aggressively suing people who put SERDES ports on FPGAs This so isn't important to your overall point, but where would I begin to look into this? Sounds fascinating!
Not OP but I was curious too. Here's all I could find that seemed related: https://www.businesswire.com/news/home/20200121005582/en/Xil...
Re: 100x defect tolerance: How we solved the yield problem
#95I live in a small city/large town that has a large number of craft breweries. I always marveled at how these small operations were able to churn out so many different varieties. Turns out they are actually trying to make their few core recipes but the yield is so low they market the less consistent results as...all that variety I was so impressed with.
Re: 100x defect tolerance: How we solved the yield problem
#96Earlier quoted context omitted.
The enthalpy of vaporization of water (at standard pressure) is listed by Wikipedia[1] as 2.257 kJ/g, so boiling 462 grams would require an additional 1.04 MJ, adding 26 seconds. Cerebras claims a "peak sustained system power of 23kW" for the CS-3 16 Rack Unit system[2], so clearly the power density is lower than for an H100. [1] https://en.wikipedia.org/wiki/Enthalpy_of_vaporization#Other... [2] https://cerebras.ai/…
On a tangent: has anyone built an active cooling system which operates in a partial vacuum? At half atmospheric pressure, water boils at around 80 C, which i believe is roughly the operating temperature for a hard-working chip. You could pump water onto the chip, have it vapourise, taking away all that heat, then take the vapour away and condense it at the fan end. This is how heat pipes work, i believe, but heat pip…
No need to bother with a partial vacuum when ethanol boils at around 80 C as well and doesn't destroy electronics. I'm not aware of any active cooling systems utilizing this though.
Re: 100x defect tolerance: How we solved the yield problem
#97Earlier quoted context omitted.
The enthalpy of vaporization of water (at standard pressure) is listed by Wikipedia[1] as 2.257 kJ/g, so boiling 462 grams would require an additional 1.04 MJ, adding 26 seconds. Cerebras claims a "peak sustained system power of 23kW" for the CS-3 16 Rack Unit system[2], so clearly the power density is lower than for an H100. [1] https://en.wikipedia.org/wiki/Enthalpy_of_vaporization#Other... [2] https://cerebras.ai/…
On a tangent: has anyone built an active cooling system which operates in a partial vacuum? At half atmospheric pressure, water boils at around 80 C, which i believe is roughly the operating temperature for a hard-working chip. You could pump water onto the chip, have it vapourise, taking away all that heat, then take the vapour away and condense it at the fan end. This is how heat pipes work, i believe, but heat pip…
I found this review from 2019 of mechanically pumped heat pipe technologies. I skimmed the intro. Looks like it already has a foothold in aerospace.
https://www.sciencedirect.com/science/article/abs/pii/S13594...
Re: 100x defect tolerance: How we solved the yield problem
#98Earlier quoted context omitted.
"While I continue to believe that many people are going to collectively lose trillions of dollars ultimately pursuing "AI" at this stage" Can you please explain more why you think so ? Thank you.
It's a hype cycle with many of the hypers and deciders having zero idea about what AI actually is and how it works. ChatGPT, while amazing, is at its core a token predictor, it cannot ever get to an AGI level that you'd assume to be competitive to a human, even most animals. And just as every other hype cycle, this one will crash down hard. The crypto crashes were bad enough but at least gamers got some very cheap GP…
> And just as every other hype cycle, this one will crash down hard.
Isn't that an inherent problem with pretty much everything nowadays: crypto, blockchain, AI, even the likes of serverless and Kubernetes, or cloud and microservices in general.
There's always some hype cycle where the people who are early benefit and a lot of people chasing the hype later lose when the reality of the actual limitations and the real non-inflated utility of each technology hits. And then, a while later, it all settles down.
I don't think the current "AI" is special in any way, it's just that everyone tries to get rich (or benefit in other ways, as in the microservices example, where you still very much had a hype cycle) quick without caring about the actual details.
Re: 100x defect tolerance: How we solved the yield problem
#99[dead]
Re: 100x defect tolerance: How we solved the yield problem
#100Earlier quoted context omitted.
"While I continue to believe that many people are going to collectively lose trillions of dollars ultimately pursuing "AI" at this stage" Can you please explain more why you think so ? Thank you.
I would guess you're not asking a serious question here but if you were feel free to contact me, it's why I put my email address in my profile.
Why are you assuming bad faith?