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

441–450 of 581 posts

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

#441

Post by AnthonyMouse »

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; there's always been some speed penalty.

LPCAMM2 supports up to 9600MT/s, which appears to be the same speed Apple is using.

> I'm not sure we've ever seen a system demonstrated using LPCAMM or similar for a 512-bit bus

Servers commonly use a 768-bit DDR5 memory bus per socket even without LPCAMM and LPCAMM allows shorter traces than traditional DIMMs. It's basically down to most existing DDR5 system boards/sockets having been designed before anyone was trying to run LLMs on consumer hardware, e.g. AM5 has a 128-bit memory bus and you're not changing that without a new socket. But every memory generation gets a new socket anyway, and the existing Threadripper Pro socket has a 512-bit memory bus as well.

Moreover, making the bus wider is "easy" -- the main problem with it is that it adds cost. Apple's least expensive machines use the same 128-bit memory bus as most PCs and the ones with the 512-bit bus cost as much as Threadripper if not more.

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

#442

Post by monster_truck »

fg137 wrote: post #134

I don't think this is going to get any traction in the general consumer world, even less relevant than Apple Vision Pro. (HN reaction to Vision Pro back in 2024 is almost hilarious if not ridiculous, looking at it today. I knew it would be a flop and I was so right.)

Wild that it took me so much scrolling to find some sense!

Spark DGX also remains a nothingburger, I would be livid if I spent this kind of money and had to waste time chasing down power cap bugs or A/B/C testing each firmware version to find the one that is least slow and also does not fail https://dredyson.com/the-hidden-truth-about-dgx-spark-perfor...

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

#443

Post by dannyw »

hungryhobbit wrote: post #105
wazdra wrote: post #74

Earlier quoted context omitted.

This is assuming that you'll be priced the fraction of computing that you consumed. But you are actually paying for their infrastructure, for the R&D (and also the computation that went into training the model) etc. It is not clear that, for your own small computations, this kind of costs are needed, but you will still pay your share in the investment the provider made so that they could serve everyone's computation…

But, currently ... you're not. AI companies are operating at a loss, and are being subsidized by their investors. Local may or may not be cheaper than remote now, depending on the details, but the factors you describe won't affect the math nearly as much as they will once that subsidization ends.

Not for API pricing. The latest models are not subsidised API wise anymore.

Qwen3.6 is practically indistinguishable to Sonnet 4.6 at least in my personal experience. And sonnet 4.6 is not that cheap.

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

#445

Post by Aperocky »

crazygringo wrote: post #362
GuestFAUniverse wrote: post #88

And who in 2026 is still anal-fixated on a "Windows" PC? It's just a personal computer. It normally runs multiple operating systems just fine. Windows PC sounds like people talking about tech who are either payed by M$, or embed pictures into Word documents to send them. Nobody has to kill the fun those OS agnostic machine allow, by artificially bind them to a shitty OS.

> And who in 2026 is still anal-fixated on a "Windows" PC? I'm assuming it's just clarifying this isn't about Macs. The term "PC" is ambiguous, since it can either refer to all personal computers in its original meaning, or to the IBM PC lineage that is mainly contrasted with Macs. Remember the famous "I'm a Mac, I'm a PC" ads. When you just say "PC", people today genuinely don't know which meaning you are referring…

Well, there's the other problem, windows sucks.

I prefer Windows XP, or even Windows Vista, to Windows 11 with its copilot. And it's been a downhill race, even macs are more of your own personal machine than Windows today, which is saying a lot.

PC should be a PC, Windows is as they advertised, a Copilot PC.

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

#446

Post by wren6991 »

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.

I'm not sure what you mean by this. Memory bandwidth is the main bottleneck for single-user decode. The bottleneck is actually more severe for end-user inference than cloud inference, because end users don't have the option to increase arithmetic intensity by computing tokens for multiple clients in the same pass.

One thing we've learned from Apple is the viability of spamming more LPDDR5X channels (up to 1024-bit total bus width on M3U) as a means of achieving high bandwidth while keeping the cost/capacity reasonable.

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

#447

Post by stego-tech »

maccard wrote: post #372
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…

> 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.

I live with a game dev myself, so I get it. Hell, it's hard even for PC developers who want to do things without leaning on abstraction layers or existing engines. Managing multiple discrete memory pools, asset swaps or calls between them, getting the respective subsystems to exchange data at just the right time so as not to impact other code and drag down performance - it's fucking hard in general.

A unified pool of memory suddenly makes that simultaneously easier, but also far more flexible, which frees up developer time and bandwidth to focus on other, more important tasks.

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

#448

Post by stego-tech »

to11mtm wrote: post #324
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)

It doesn't -have- to be that way necessarily... LPCAMM2/SOCAMM2 exist, heck I think Framework is using LPCAMM2 in one of their new laptops. Heck, I'm willing to bet that a lot of manufacturers would rather go that route than soldered in, if for no other reason than the relative cost of warranty work between the two. However, people probably need to stop being obsessed with ultrathin laptops for that to happen.

I came here to say just this myself! Modern DIMM formats make SFF/portable builds with unified memory pools far more plausible than prior designs. There's absolutely no reason desktop machines couldn't implement similar DIMM formats or design a new board standard around something similar.

Unified memory doesn't have to be soldered on or serviceable. That's a choice Apple made because it fit their product vision, but it's not mandatory in the slightest.

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

#449

Post by stego-tech »

saltcured wrote: post #292
pbalau wrote: post #271

Earlier quoted context omitted.

What is the difference between unified memory and shared memory? Shared memory existed since the first CPU with an embedded GPU came to market and you could set in BIOS how much memory goes to what component. I do have an opinion about how unified memory could be different, but I want a proper explanation.

I'm not sure everyone uses the terms consistently, but the difference is that the old "shared" memory was reserving a section to act as VRAM under the control of the GPU, ignored by the OS. The CPU ran the same kind of code pretending there is a "bus transfer" between host memory and graphics memory. In unified memory, all the memory is host memory and data can go from program to GPU with zero copy movements. The add…

You got it in one! That's exactly what makes unified memory superior for current use cases, and different from the shared memory woes of old.

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

#450

Post by userbinator »

wmf wrote: post #216
sherazp995 wrote: post #114

Wait a minute! Nvidia going from GPU to CPU now?

Nvidia has been making CPUs for 10-15 years.

Much longer than that...

https://theretroweb.com/chipsets/182

https://www.nvidia.com/en-us/drivers/uli-m6117c/

Post reply on HN