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

Nvidia is proposing a beast of a CPU system for Windows PCs

twitter.com

Post reply on HN
Print view View original

491–500 of 581 posts

Re: Nvidia is proposing a beast of a CPU system for Windows PCs

#491

Post by someguyornotidk »

arjie wrote: post #265
modeless wrote: post #119

The Qualcomm Snapdragon X2 Elite Extreme trounces Nvidia's chip in single core CPU performance. It beats Intel and AMD's best, too. It has unified memory. It's the only CPU in the same league as Apple's M-series in both CPU performance and power efficiency. And it's available in laptops today, not later this year. People are sleeping on Qualcomm.

Garbage operating system support. If you can’t do Linux support it’s a bit pointless because there’s two platforms for this that matter: Linux and Darwin. Qualcomm is like AMD was for GPUs for like decades. Lots of announcements and people on the Internet are huge fans based on web pages they’ve read but if you try to make it work it’s a nightmare. Snapdragon X Elite doesn’t work on Linux so it’s a pointless platform…

Yep, very much this. I don't bother looking to them for anything in this space because the hostility they show towards general Linux support appears to be rooted in principle and appears to be very much deliberate. It almost feels like Linux support would run counter to how they want their processors to be used.

Whether this is true or not, it's pretty safe to assume anything based on their stuff is not for me.

Re: Nvidia is proposing a beast of a CPU system for Windows PCs

#492

Post by Joel_Mckay »

tjoff wrote: post #347
stego-tech wrote: post #197

The Unified Memory pool is what will continue to be the “game changer” in systems architecture, especially outside of data centers. The reality is even cutting edge games and consumer workloads don’t actually take full use of the PCIe bandwidth of the GPU or the bandwidth of its GDDR memory. Even local AI use cases don’t substantially or meaningfully benefit from faster memory, at least to average consumers. A unifie…

Don't really buy the economic argument. For 99% pf all workloads you need at least an order of magnitude more system memory than gpu memory. Most systems barely need more gpu memory than what is required for video, browsing etc. Just because we found a new usecase doesn't flip that on its head. Besides, I want to keep doing what I'm doing today. So if I need 128GB today and my local AI needs 128 GB then I'd need 256…

Jensen Huang has publicly stated he wants a future where "AI" agents use more PC computers than people.

It is ambitious, and absurd... like all CEOs that eventually go loopy. =3

Re: Nvidia is proposing a beast of a CPU system for Windows PCs

#493

Post by Lplololopo »

arka2147483647 wrote: post #323
cm2187 wrote: post #307

Earlier quoted context omitted.

And conveniently, by making your machine non upgradeable, it allows the manufacturer to enforce market segmentation / charge a huge premium for small RAM upgrade ( a la Apple)

There is LPCAMM2, if manufacturers want to use it. So, it does not have to be soldered.

Its still further away than the Ram on a packaged CPU and latency is limited by speed of light/electrons on that scale.

Re: Nvidia is proposing a beast of a CPU system for Windows PCs

#494

Post by Lplololopo »

stego-tech wrote: post #197

The Unified Memory pool is what will continue to be the “game changer” in systems architecture, especially outside of data centers. The reality is even cutting edge games and consumer workloads don’t actually take full use of the PCIe bandwidth of the GPU or the bandwidth of its GDDR memory. Even local AI use cases don’t substantially or meaningfully benefit from faster memory, at least to average consumers. A unifie…

" Even local AI use cases don’t substantially or meaningfully benefit from faster memory, at least to average consumers."

What do you mean by this? Memory bandwidth is fundamental to the speed of an local AI model

Re: Nvidia is proposing a beast of a CPU system for Windows PCs

#495

Post by izacus »

mlinhares wrote: post #180
jeroenhd wrote: post #171

Earlier quoted context omitted.

> I avoid them on phones as well by just buying Apple To each their own, but I don't recall Apple ever mainlining any of their drivers on Linux. You're rightfully angry on the laptop side of things, but Apple is much worse than Qualcomm when it comes to open source support for their phones. Qualcomm probably shouldn't have promised Linux support in the first place. Everyone seems to love Apple's hardware even though…

Apple doesn’t sell general purpose computers outside of their own hardware so this doesn’t make any sense.

It makes absolutely the same amount of sense as the original critique - you just prefer to defend one bad actor because you like the brand.

Re: Nvidia is proposing a beast of a CPU system for Windows PCs

#496

Post by zozbot234 »

someguyornotidk wrote: post #491
arjie wrote: post #265

Earlier quoted context omitted.

Garbage operating system support. If you can’t do Linux support it’s a bit pointless because there’s two platforms for this that matter: Linux and Darwin. Qualcomm is like AMD was for GPUs for like decades. Lots of announcements and people on the Internet are huge fans based on web pages they’ve read but if you try to make it work it’s a nightmare. Snapdragon X Elite doesn’t work on Linux so it’s a pointless platform…

Yep, very much this. I don't bother looking to them for anything in this space because the hostility they show towards general Linux support appears to be rooted in principle and appears to be very much deliberate. It almost feels like Linux support would run counter to how they want their processors to be used. Whether this is true or not, it's pretty safe to assume anything based on their stuff is not for me.

It's the usual issue with Qualcomm SoCs being designed as bespoke embedded platforms as opposed to standard general-purpose compute. So Linux support for these chips ends up being heavily vendor specific, i.e. it's not just Qualcomm it's also the platform OEMs.

Re: Nvidia is proposing a beast of a CPU system for Windows PCs

#497

Post by danslo »

arjie wrote: post #265
modeless wrote: post #119

The Qualcomm Snapdragon X2 Elite Extreme trounces Nvidia's chip in single core CPU performance. It beats Intel and AMD's best, too. It has unified memory. It's the only CPU in the same league as Apple's M-series in both CPU performance and power efficiency. And it's available in laptops today, not later this year. People are sleeping on Qualcomm.

Garbage operating system support. If you can’t do Linux support it’s a bit pointless because there’s two platforms for this that matter: Linux and Darwin. Qualcomm is like AMD was for GPUs for like decades. Lots of announcements and people on the Internet are huge fans based on web pages they’ve read but if you try to make it work it’s a nightmare. Snapdragon X Elite doesn’t work on Linux so it’s a pointless platform…

Support is slowly landing... https://www.phoronix.com/news/Lenovo-Yoga-Slim-7x-Gen11-Linu...

Re: Nvidia is proposing a beast of a CPU system for Windows PCs

#498

Post by lelanthran »

wtallis wrote: post #373
MBCook wrote: post #345

Earlier quoted context omitted.

I mean is it possible to make unified memory systems with good performance or is it not really feasible due to memory timing/trace length issues? It’s possible if you’re willing to go with much slower RAM than GPUs like but CPUs often use. Thats what integrated graphics laptops have done for a long time right? But can you get high end CPU and GPU performance with unified memory and maintain user upgradable memory in…

> I mean is it possible to make unified memory systems with good performance or is it not really feasible due to memory timing/trace length issues? LPCAMM and similar solutions exist, but have never been demonstrated running at speeds that match what the leading soldered memory systems are using; there's always been some speed penalty. I'm not sure we've ever seen a system demonstrated using LPCAMM or similar for a 5…

> LPCAMM and similar solutions exist, but have never been demonstrated running at speeds that match what the leading soldered memory systems are using;

Does it need to be leading, though? Being median is just fine for what high-RAM systems are intended to be used for.

Re: Nvidia is proposing a beast of a CPU system for Windows PCs

#499

Post by maccard »

Stevvo wrote: post #429
maccard wrote: post #372

Earlier quoted context omitted.

> The reality is even cutting edge games and consumer workloads don’t actually take full use of the PCIe bandwidth of the GPU or the bandwidth of its GDDR memory Game dev here. For anyone reading this - it’s not because we’re lazy, it’s because _it’s really hard to do_. One of the biggest differences between the current generation consoles and the current gen PCs is unified memory.

What? It's incredibly easy to take full use of memory bandwidth. For example, put proper volumetric smoke/fire/explosion sim in your game. But game developers don't do that because they are lazy.

No, we don’t do it because the tradeoff isn’t worth it. A gpu based particle sim is very difficult to do well - it’s easy (but computationally expensive) to do a volumetric sim, but when you want that simulation to interact with world geometry correctly it comes with an explosion in complexity and performance.

I promise you want our games to look as good as you want them to look.

Re: Nvidia is proposing a beast of a CPU system for Windows PCs

#500

Post by moffkalast »

bigyabai wrote: post #426
moffkalast wrote: post #260

Earlier quoted context omitted.

They have a lot of software groundwork ahead of them to make an ARM CPU viable for any kind of desktop use outside direct inference or training usage too. AMD has the advantage that their x86 machines run everything, Apple maintains the whole MacOS stack, while Nvidia can barely scrape together one Ubuntu release per Jetson generation, it's beyond embarrassing. Maybe they ought to put those agents they keep droning a…

> Nvidia can barely scrape together one Ubuntu release per Jetson generation Why would they do more? It's an LTS distro, the Nvidia drivers are updated for as long as the hardware's compute capability is supported. Nvidia's ARM drivers are updated constantly, and battle-tested as the backbone in hundreds of thousands of Grace ARM servers.

Yes it's an LTS, which means it only makes sense to build something on it early in its release cycle, so the platform itself needs to keep up with new releases. Orins will go EoL next year, so good luck with that.

That's not even considering the lazy out tree patchwork support Nvidia does for their products on top of that. Maybe it's different in this case for Windows since it forces a rolling release, but I seriously doubt they'll do it properly instead of forking some version and keeping it around for 10 years like absolute idiots.

Post reply on HN