Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI unveils its first custom chip, built by Broadcom

techcrunch.com

Post reply on HN
Print view View original

411–420 of 496 posts

Re: OpenAI unveils its first custom chip, built by Broadcom

#411

Post by kmacdough »

otterdude wrote: post #176
zgao wrote: post #125

Earlier quoted context omitted.

Chip CEO here. It really depends on what "design" or "production" means. Does "design" mean that the design was complete? Does "production" mean the beginning of production, i.e. tapeout? If measuring from RTL-freeze to tapeout, this is a fairly typical (even somewhat unimpressive) timeline (accounting for some unexpected issues) for a large, complex 3nm chip. If measuring from concept (no RTL at all, block diagram o…

Not a chip CEO, but I read this article and thought that they're working on some kind of application specific chip only for serving models. Similar to how an FPGA can optimize certain tasks. Given constant weights / biases of a Transformer / DNN you could use pipelining to feed forward calculations through the array one layer at a time. For DNN's with thousands of layers you might see 1:1 speed up per layer channel.…

With a striking lack of numbers, I'm not confident. I my experience, everything underspecified in a marketing release is unflattering. They're also not a chip designing company, but they're probably trying to keep up on the eyes of investors. As the article mentions, several of their competitors are chip designers and already have working procuction inference chips.

Re: OpenAI unveils its first custom chip, built by Broadcom

#412

Post by Kiro »

sharkjacobs wrote: post #61

> Developed from design to production in nine months, accelerated by OpenAI’s models > the use of OpenAI models to accelerate parts of the design and optimization process. I wish there was more about this. As is I kind of have to assume that this is just meaningless marketing, like saying development was accelerated by Microsoft Office or their 5k LG Ultrafine 40-inch monitors. Like, if this was as big a deal as it k…

I think this kind of "hard work" is a perfect fit for AI, and something where the complexity for a human is incorrectly extrapolated to LLMs.

Tirelessly wading through heaps of specifications and documentation with very clear goal definitions is hard for a human but easy for an AI. Meanwhile, taking UX and edge cases into account in a business application is easy for a human but hard for an AI.

Re: OpenAI unveils its first custom chip, built by Broadcom

#413

Post by SwellJoe »

kmacdough wrote: post #411
otterdude wrote: post #176

Earlier quoted context omitted.

Not a chip CEO, but I read this article and thought that they're working on some kind of application specific chip only for serving models. Similar to how an FPGA can optimize certain tasks. Given constant weights / biases of a Transformer / DNN you could use pipelining to feed forward calculations through the array one layer at a time. For DNN's with thousands of layers you might see 1:1 speed up per layer channel.…

With a striking lack of numbers, I'm not confident. I my experience, everything underspecified in a marketing release is unflattering. They're also not a chip designing company, but they're probably trying to keep up on the eyes of investors. As the article mentions, several of their competitors are chip designers and already have working procuction inference chips.

When you have a few billion dollars you can hire chip people and partner with a chip company.

That's not to say I expect they'll ship something competitive with Google's custom AI hardware on the first go, since Google has been at it for quite a while, but there's very few technical problems large sums of money won't solve.

Re: OpenAI unveils its first custom chip, built by Broadcom

#414

Post by SwellJoe »

otterley wrote: post #386
jwHollister wrote: post #380

Earlier quoted context omitted.

wow if they can get something like this working, what happens to all this infrastructure? Hyperscalers have to be assuming the lifespan of that stuff wrong considering the next gen will be 1000x more efficient.

The question isn’t whether it works (it does); the question is whether there are buyers for hardware that is obsolete the day it ships. Models evolve much more quickly than hardware can keep up.

The models have to run on something or they're useless. They can't run on future hardware today, and people want to use models today. So, if hardware is obsolete the day it ships, we're all using obsolete hardware, and there's no alternative to that.

Re: OpenAI unveils its first custom chip, built by Broadcom

#416

Post by freakynit »

marcosqanil wrote: post #406
freakynit wrote: post #368

Earlier quoted context omitted.

This may be extreme, or, completely stupid, but, why are we not using genetics to "grow" chips in a chemical soup yet? Similar to Verilog/VHDL, don't we have some similar language to express circuits using gene sequences?

I've worked for one of Europe's biggest synthetic biology labs and I know lots of biologists are low-key interested, but current players in semiconductors see it as kind of a tarpit. IBM used to have a program using DNA origami for lithography back in 2009, which makes sense as lithography masks are a pain to make. I really wish I know why the program was stopped, but most of the researchers are retired by now. As to…

Would it be comparatively easy to make neuromorphic chips instead of traditional chips? I believe probabilistic algorithms like those employed by LLM's must be more tolerable to working with defects as well..?

Re: OpenAI unveils its first custom chip, built by Broadcom

#417

Post by cm2187 »

indigo945 wrote: post #404
otterley wrote: post #386

Earlier quoted context omitted.

The question isn’t whether it works (it does); the question is whether there are buyers for hardware that is obsolete the day it ships. Models evolve much more quickly than hardware can keep up.

One obvious use case is edge computing, such as in industrial applications that cannot tolerate the risk of a network link or cloud service going down. Even embedded use cases are possible, such as an image classifier model in a security camera.

In fact any application where the task is stable and the model good enough to address that task. As you suggest, industrial applications where a robot must deal with variants of the same repetitive task. Or a military drone which needs to be jamming proof.

Re: OpenAI unveils its first custom chip, built by Broadcom

#419

Post by WithinReason »

seydor wrote: post #115
sharkjacobs wrote: post #61

> Developed from design to production in nine months, accelerated by OpenAI’s models > the use of OpenAI models to accelerate parts of the design and optimization process. I wish there was more about this. As is I kind of have to assume that this is just meaningless marketing, like saying development was accelerated by Microsoft Office or their 5k LG Ultrafine 40-inch monitors. Like, if this was as big a deal as it k…

realistically, how hard are AI accelerators to design?

The hardware? Not too difficult, there are dozens of startups. The software? Only NVIDIA could do it so far sufficiently well.

Re: OpenAI unveils its first custom chip, built by Broadcom

#420

Post by dubbie99 »

VorpalWay wrote: post #237
knicholes wrote: post #147

Earlier quoted context omitted.

Right. KiCAD for PCB design. Blender for 3D CAD. Oh, are you saying I should have used something other than the KiCAD MCP server for better results?

Designing circuit board and 3D models (even using something like OpenSCAD) is a very spatial process today. You are dealing with coordinates one way or another. This is very unlike how FPGA and (I assume) ASIC is done. That is more like a traditional programming language but everything happens all at once (no sequence of statements outside tests, if you need that you have to write a state machine yourself). You defin…

Autorouting PCBs doesn’t really give usable results on all but the simplest cases. It seems to be a very difficult problem to solve even though a human doing it is only following a relatively simple bunch of rules and goals in his or her head.
Post reply on HN