Nvidia CEO Jensen Huang announces new AI chips: ‘We need bigger GPUs’

Post by anon291 » Tue, Mar 19, 2024, 4:01 AM UTC

0xcde4c3db wrote: post #108

herecomethefuzz wrote: post #84

"Platform company" means multi-chip in this case? Seems logical since it's becoming impractical to cram so many transistors on a single die.

I don't really understand the bird's-eye view of the product line, but judging by some of the raw physical numbers and configurations Jensen was bragging about, it means that they want to basically play the mainframe game of locking high-end applications into proprietary middleware running on proprietary chassis with proprietary cluster interconnect (hello, Mellanox acquisiton).

Post by nemothekid » Tue, Mar 19, 2024, 4:21 AM UTC

dheera wrote: post #181

cebert wrote: post #178

> “Nvidia … is becoming less of a mercenary chip provider and more of a platform provider, like Microsoft or Apple, on which other companies can build software. I can understand from a growth perspective why it’s more profitable for Nvidia if it can become more of a platform service for AI. However, that’s difficult to balance that and partnerships the company already has with AWS and Microsoft. I’d expect to see som…

My prediction is eventually there will be anti-trust ligitation, they will be required to open the CUDA standard, after which AMD will become a competitor. NVIDIA could voluntarily open the standard to avoid this ligitation if they wanted to, though, and IMO it would be the smart thing to do, but almost every corporation in history has chosen the ligitation instead.

Post by wmf » Tue, Mar 19, 2024, 4:37 AM UTC

anon291 wrote: post #191

dheera wrote: post #181

Earlier quoted context omitted.

My prediction is eventually there will be anti-trust ligitation, they will be required to open the CUDA standard, after which AMD will become a competitor. NVIDIA could voluntarily open the standard to avoid this ligitation if they wanted to, though, and IMO it would be the smart thing to do, but almost every corporation in history has chosen the ligitation instead.

The cuda api is essentially open... Hip is basically a copy. CUDA is such a misnomer. Amd doesn't have tensorRT, cuDNN, cutlass, etc. Forcing Nvidia to make these work on AMD is like forcing Microsoft to make windows work on apple hardware... Not going to happen.

Post by buildbot » Tue, Mar 19, 2024, 4:43 AM UTC

jxy wrote: post #179

Havoc wrote: post #120

Earlier quoted context omitted.

>bit misleading. Only partially, because in LLMs FP4 isn't half as useful as FP8. So if you have gear that crushes at FP4 then that's what you use and you benefit from that increased speed (at minimal accuracy loss). Definitely some marketing creativity in there, but its not entirely wrong as a measure of real world usage

curiously, what real world usage actually uses FP4? AFICT, most of the LLMs still use BF16, and even the quantizations down to 4bits and 2bits end up back to 16bit or INT8 for actual computations.

Post by oblio » Tue, Mar 19, 2024, 4:46 AM UTC

throw0101b wrote: post #136

ryandrake wrote: post #49

Earlier quoted context omitted.

If you are a true believer that AI is not a craze, then the stock can only go up from here. If you think there is a chance that everyone gets bored of AI and moves on to some other fad that is not in Nvidia’s wheelhouse, then it’s probably down from here. I’m staying out of this bet: don’t have the stomach for it.

> If you think there is a chance that everyone gets bored of AI and moves on to some other fad that is not in Nvidia’s wheelhouse, then it’s probably down from here. You may wish to look at history to see how things can work out: Cisco had a P/E ratio of 148 in 1999: * https://www.dividendgrowthinvestor.com/2022/09/cisco-systems... The share price tanked, but that does not mean that people got bored of the Internet a…