News Nvidia Outlines Jensen 'Huang's Law' of Computing

Toggle sidebar Toggle sidebar
Status
Not open for further replies.
its kind of pathetic that nvida is going that way. make video cards with less raw performance, so you have to use one of their techs to give you the performance you should be getting in the 1st place.. good job nvidia.... good job. rip off your costumers even more.....

its a good thing i am still looking at getting one of amds cards instead...
 
  • Like
Reactions: AndrewJacksonZA
The reality-distortion field is strong, in this guy.

'Over the last decade, as Nvidia GPUs shifted from 28nm to 5nm processes, the semiconductor process improvements have "only accounted for 2.5x of the total gains," asserted Dally at Hot Chips.'
​
That's if you only look at the frequency gains from process advancement! If you also account for density, it's waaaay higher!

Basically, they're just claiming to have rediscovered something we knew all along, since well before the dawn of hardware-accelerated graphics chips, which is that fixed-function, purpose-built logic is a lot faster than general-purpose computers!

All of the stuff about custom data formats was true of graphics, back in the old days (and even to some extent, today). Things like 16-bpp color by packing (5, 5, 6)-bit tuples into a 16-bit integer. What happened since the early days of 3D graphics cards is that the silicon improvements came so fast that GPU makers were able to offer a lot of programmability and generality. Then, AI came along, and was sufficiently compute-bound and bottlenecked on specific types of computation that it made sense to have specialized, fixed-function logic for it, just as we have for texturing, ROPs, ray-tracing, etc.

So, just multiply together the 2.5x frequency boost, the additional cores enabled by process density improvements, and the improvements by making fixed-function logic for AI, and that gets you most of the way to their 1000x number. The rest comes from things like larger caches and various other tweaks.

'Huang's Law' - what self-congratulatory nonsense. All he really pointed out was something the supercomputer industry knew since the 60's, which is that you can scale faster by also adding/increasing parallelism than simply relying on scalar performance improvements.
 
Last edited:
  • Like
Reactions: JakeTheMate, domih, AndrewJacksonZA and 2 others
Why do people doubt Jensen so much but believed Jobs and Gates at face value in addition to putting them on pedestals?
 
xmod said:
Why do people doubt Jensen so much but believed Jobs and Gates at face value in addition to putting them on pedestals?
Click to expand...
They have different strengths. Jobs was visionary (also a tyrant) while Gates pioneered much of the pre-cloud software business model and was pretty ruthlessly competitive.

Jensen might have a knack for business, and certainly has a flair for cut-throat competition, but he's no technical genius. So, calling it "Huang's Law" is utterly laughable, not only because he's far from the first to observe it, but because he's not even the same level of technical mind as Gordon Moore. It's 100% PR.

One thing Jensen shares with Bill Gates is that they both started as hardware or software developers. From what I've picked up, Jobs mooched off the technical work of others, his entire career. Even back when he worked at Fairchild, word has it he basically just got Wozniak to do his work for him. Not that Jobs didn't have strengths, but they just weren't technical and he didn't truly start in the trenches the way Gates, Huang, Page, and Brin did. Heck, even Zuckerberg started out coding in his dorm room.

The thing that bugs me about Huang is that he's so bombastic and really doesn't sound particularly smart, to me. That doesn't mean he doesn't have a real knack for business, but I find it absurd to talk about him like a technical genius - he's not.
 
Last edited:
  • Like
Reactions: CTPAHHIK and AndrewJacksonZA
"As people debate whether Moore’s Law is slowing, remains applicable, or is even dead or alive in the 2020s, Nvidia scientists herald the impressive momentum behind Huang’s Law".

This is written and reads the same exact way Tesla and Apple "our leader is infallible " PR nonsense does.

Jensen's days at Nvidia are numbered. Same with Cook, Musk and others. They're not people defining tech evolution. They're modern day crooks.
 
vertuallinsanity said:
"As people debate whether Moore’s Law is slowing, remains applicable, or is even dead or alive in the 2020s, Nvidia scientists herald the impressive momentum behind Huang’s Law".

This is written and reads the same exact way Tesla and Apple "our leader is infallible " PR nonsense does.
Click to expand...
LOL, such PR doesn't work for Musk. No matter what message they try to put out, he'll just walk all over it. He cannot be managed.

vertuallinsanity said:
Jensen's days at Nvidia are numbered. Same with Cook, Musk and others. They're not people defining tech evolution. They're modern day crooks.
Click to expand...
I don't see any of them being replaced, as long as the numbers keep going up. Cook is in a separate category, because Jensen and Musk were founders (unless you mean Twitter; also not literally a founder of Tesla, but got in early). I also think Musk owns enough of his companies that it wouldn't be easy to get rid of him.
 
  • Like
Reactions: Lucky_SLS
I have to say, I'm finding myself a bit worn out by the references to 'inference' and 'AI' in every other article lately.

Which is largely on me. I used to be well up on the topic of advancements in computing/chips etc, but I find my age has made me fall behind the times somewhat.

I think I need someone to explain to me the purpose of AI to a consumer, as if they were explaining it to a child. All I've come across so far is that it can recognise images and languages and speech, provides guidance and helps with things like online shopping. If that's the extent of what it can provide (for a typical consumer), I'm distinctly unimpressed.
 
Neilbob said:
I think I need someone to explain to me the purpose of AI to a consumer, as if they were explaining it to a child. All I've come across so far is that it can recognise images and languages and speech, provides guidance and helps with things like online shopping. If that's the extent of what it can provide (for a typical consumer), I'm distinctly unimpressed.
Click to expand...
Perhaps you're unimpressed because you're not looking at side-by-side comparisons with the best non-AI approaches to solving some of those hard problems. I think that's why AI sort of flew below the radar, for a lot of people - they didn't see it doing anything new. They merely heard it was important and that it was solving old problems better. Yawn.

Well, that's probably why generative AI took so many people by surprise. Finally, it's doing something computers have never really done, before - and often at a level many thought only a human could achieve.

I assume you've seen examples of ChatGPT-generated poems, songs, short stories, etc. I assume you've also seen AI-generated image content. But, here's a twist on the latter with some clear utility:
​
​

The comments on the video say it doesn't always work that well. However, the fact that it works at all is pretty mind-blowing, IMO. Seems like really powerful tool, for the working artist.
 
  • Like
Reactions: Neilbob
bit_user said:
The comments on the video say it doesn't always work that well. However, the fact that it works at all is pretty mind-blowing, IMO. Seems like really powerful tool, for the working artist.
Click to expand...
Fair enough, that is fairly impressive, though the same problem remains for me: I don't see the point for the majority of regular people.

Sigh. I'm sure this is just me being a miserable old grump again. I'll concede I can see how this can develop in other, broader directions in the future - assuming the singularity doesn't develop first of course 😀
 
Yes, Nvidia is greedy. Yes, Huang is not a technical wizkid. But we can give him the credit to shaping up AI development and bringing the tech to us - even if its in a monopolistic and anti competitive way.

Nvidia Remix is the tech I am excited about more than DLSS and ray tracing. So yes, huge props to developing and delivering AI tech and features!
 
Last edited:
  • Like
Reactions: bit_user
Status
Not open for further replies.

TRENDING THREADS

Latest posts

Moderators online

Share this page

COMPANY
RESOURCES
FOLLOW
Top Bottom