I don’t know enough to say they’ll fail or be successful but I am wondering who will underwrite this IPO — they must have balls of steal and confidence gallore
AI chipmaker Cerebras files for IPO
91–100 of 138 posts
Re: AI chipmaker Cerebras files for IPO
#92Earlier quoted context omitted.
I think the wafer itself isn’t the whole deal. If you watch their videos and read the link you posted the wafer size allows them to stack them in a block with integrated power and cooling at a higher density than blades and attach enormous amounts of memory. Not including the system, cooling, cluster, etc seems like a relatively unfair comparison too given the node includes all of those things - which are very expens…
At the end of the day, Cerebras has not submitted any MLPerf results (of which I am aware). That means they are hiding something. Something not very competitive. So, performance is iffy. Density for density sake doesn’t matter since clusters are power limited.
I guess it's a software problem.
Without optimized implementations their performance will look like shit, even if their chip were years ahead of the competition.
Building efficient implementations with an immature ecosystem and toolchain doesn't sound like a good time. But yeah, huge red flag. If they can't get their chip to perform there's no hope for customers.
Re: AI chipmaker Cerebras files for IPO
#93NVIDIA is pretty established but there's also Intel, AMD, Google to contend with. Sure Cerebras is unique in that they make one large chip out of the entire wafer but nothing prevents these other companies from doing the same thing. Currently they are choosing not to because of wafer economics but if they chose to, Cerebras would pretty much lose their advantage. https://www.servethehome.com/cerebras-wse-3-ai-chip-la…
> 56x the size of H100 but only 8x the performance improvement isn't something I would brag about. It doesn't sound like it's too bad for a 9 year old company. Nvidia had a 20-year head start. I would expect that they will continue to shrink it and increase performance. At some point, that might become compelling?
Nvidia is also going to keep improving, so it will be a moving target.
Re: AI chipmaker Cerebras files for IPO
#94On the one hand, the financials are terrible for an IPO in this market. On the other, Nvidia is worth 3trn so they can sell a pretty good dream of what success looks like to investors. Personally I would expect them to get a valuation well about the 4bln from the 2021 round, despite the financials not coming close to justifying it.
IPOs are coming back. Expect pretty big ones in 2025.
Re: AI chipmaker Cerebras files for IPO
#95Earlier quoted context omitted.
> 56x the size of H100 but only 8x the performance improvement isn't something I would brag about. It doesn't sound like it's too bad for a 9 year old company. Nvidia had a 20-year head start. I would expect that they will continue to shrink it and increase performance. At some point, that might become compelling?
Nvidia is also going to keep improving, so it will be a moving target.
That's true, but the advantage of having a head start does eventually diminish. They won't catch up to Nvidia in the next couple of years, but they could eventually be a real competitor.
Re: AI chipmaker Cerebras files for IPO
#96Earlier quoted context omitted.
At the end of the day, Cerebras has not submitted any MLPerf results (of which I am aware). That means they are hiding something. Something not very competitive. So, performance is iffy. Density for density sake doesn’t matter since clusters are power limited.
I guess it's a software problem. Without optimized implementations their performance will look like shit, even if their chip were years ahead of the competition. Building efficient implementations with an immature ecosystem and toolchain doesn't sound like a good time. But yeah, huge red flag. If they can't get their chip to perform there's no hope for customers.
This hypothesis is an eerily exact instance of the tinygrad (tinycorp) thesis, along the lines of
“nvidia’s chip is better than yours. If you can’t make your software run well on nvidia’s chip, you have no hope of making it run well on your chip, least of all the first version of your chip.”
That’s why tinycorp is betting on a simple ML framework (tinygrad, which they develop and make available open source) whose promise is, due to the few operations needed by the framework: it’ll be very easy to get this software to run on a (eg your) new chip and then you can run ML workloads.
I’m not a (real) expert in the field but find the reasoning compelling. And it might be a good explanation for the competition for nvidia existing in hardware, but seemingly not in reality (ie including software that does something with it).
Re: AI chipmaker Cerebras files for IPO
#97The only way for Cereberas to actually succeed in the market is to raise funds. They need better software, better developer relations, and better hardware too. It's a gamble, but if they can raise enough money then there's a chance of success, whereas if they can't it's pretty hopeless.
Re: AI chipmaker Cerebras files for IPO
#98The real winner in chip war is TSMC. Everyone is using them to make chips.
Yeah I also have a feeling more value will gravitate towards the really hard stuff once we’ve got the NN architectures fairly worked out and stable.
To put my money where my mouth is I’m long TSMC and ASML among others, and (moderately) short NVidia. Very long the industry as a whole though.
Re: AI chipmaker Cerebras files for IPO
#99Earlier quoted context omitted.
I guess it's a software problem. Without optimized implementations their performance will look like shit, even if their chip were years ahead of the competition. Building efficient implementations with an immature ecosystem and toolchain doesn't sound like a good time. But yeah, huge red flag. If they can't get their chip to perform there's no hope for customers.
This hypothesis is an eerily exact instance of the tinygrad (tinycorp) thesis, along the lines of “nvidia’s chip is better than yours. If you can’t make your software run well on nvidia’s chip, you have no hope of making it run well on your chip, least of all the first version of your chip.” That’s why tinycorp is betting on a simple ML framework (tinygrad, which they develop and make available open source) whose pro…
Yes, sure. I'm occasionally reading up on what George Hotz is doing with tinygrad and him ranting about AMD hardware certainly has influenced my opinion on non-Nvidia hardware to some degree - even though I take his opinion with a grain of salt, he and his team are clearly encountering some non-trivial issues.
I would love to try some of the stuff I do with CUDA on AMD hardware to get some first-hand experience, but it's a though sell: They are not as widely available to rent and telling my boss to order a few GPUs, so we can inspect that potential mess for ourselves is not convincing either.
Re: AI chipmaker Cerebras files for IPO
#100NVIDIA is pretty established but there's also Intel, AMD, Google to contend with. Sure Cerebras is unique in that they make one large chip out of the entire wafer but nothing prevents these other companies from doing the same thing. Currently they are choosing not to because of wafer economics but if they chose to, Cerebras would pretty much lose their advantage. https://www.servethehome.com/cerebras-wse-3-ai-chip-la…
Correction: it's 8x the TFLOPS of a DGX (8 H100), not 1 H100. But it's true that if it stays at $3M it's probably too much and I don't think the memory bottleneck on gpus is large enough to justify this price/performance.
So, the corrected statement is:
"56x the size of H100 but only 64x the performance improvement"
Doesn't sound too shabby.