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

281–290 of 581 posts

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

#281

Post by Gareth321 »

pbalau wrote: post #271
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…

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.

System RAM has much lower bandwidth and less predictable access. Notably, the transfer from system to GPU is very slow. About 30x slower. LLMs aren’t designed to queue or parallelise operations to account for this. They just become much slower.

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

#282

Post by speed_spread »

rvba wrote: post #104
bigyabai wrote: post #101

Earlier quoted context omitted.

> It's just a personal computer Your x86 machines were, but these are ARM SOCs. Many of them don't even support UEFI, let alone the upstream Linux kernel.

Getting rid of UEFI is bad?

However bad UEFI is, it's still better than the fragmented ARM boot wasteland.

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

#283

Post by Salgat »

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…

That was the main reason for the big hype around Memristors 15 years ago. High density, high speed persistent memory to completely remove the need for hdd/ssds, potentially even removing the need for external memory altogether. So frustrating that it still seems like we're a long ways from that becoming reality. There's some renewed interest in Memristors as they can simulate neural network connections in models, so maybe the funding will return for it.

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

#285

Post by Salgat »

jmyeet wrote: post #213
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…

Unified memory is only a feature because NVidia so aggressively uses VRAM for market segmentation. The 5090 ($2k MSRP but realistically $3-3.5k) is almost the same as the RTX 6000 Pro (~$10k). Same memory bandwidth (1800GB/s). Slightly different CUDA cores (21k vs 24k). Big difference? VRAM (32GB vs 96GB). NVidia ultimately doesn't want to upset this segmentation so the RTX Spark will never undermine their other offe…

To this day I do not get why Intel doesn't just offer massive memory options for their cards. Just charge what it costs to add the extra memory, no upcharge, and they will never be able to keep up with demand. Cheap VRAM is enough to justify a lot of open source investment into challenging CUDA.

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

#286

Post by Gareth321 »

mariopt wrote: post #201

I think most people are not understanding what this kind of laptop will provide. Before we get local AI, we'll be using hybrid AI. Running big models locally is unrealistic ($$$$$) but, if you imagine an Agentic Workflow where some bits run on the cloud and other smaller tasks locally, it's an amazing deal. You don't need Opus/Code/DeepSeek/Kimi/etc to do basic stuff that models like Gemma4:12b/Qwen-27b can do locall…

Given the incredible progress of local models, on present trajectory I think we see comparable levels of performance to frontier models in two years on 128GB unified RAM and 6-bit quantisation. Note how the frontier models are now hitting superior benchmarks with only 200,000 tokens. I think we still have a long way to go with distillation.

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

#287

Post by zozbot234 »

kgeist wrote: post #256
epolanski wrote: post #237

Earlier quoted context omitted.

1. Deepseek V4 is still in preview (training is not finished) 2. Qwen is much more demanding and borderline unusable on consumer hardware because it's a dense model. The 27B parameters are active all time for each token. It's not a MoE architecture where a router activates only some of them. 3. Qwen doesn't like quantization at all.

I have to disagree with most claims. I run Qwen3.6-27b at 260k context and 40-60 tok/sec. It handles most coding problems as well as Sonnet 4.6 under OpenCode on our production tasks. (As an experiment, I run the same prompts for the same issues in parallel for Qwen 3.6 and Sonnet 4.6 and usually see little difference in performance). I see zero degradation from quantization in practice. Settings: RTX 5090, 5-bit wei…

A 260k context (close to the stock maximum for Qwen, though it's possible to extend it) will take ~16GB RAM for storing the KV cache, barring quantization tricks which severely degrade quality. That's a whole lot more than what DeepSeek requires for a similar context length, and makes it infeasible to batch multiple inferences together. This used to be the status quo for consumer inference, in fact it still is for models like Kimi and GLM (which can sometimes be smarter than even DeepSeek V4 Pro!) but we can also do better nowadays.

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

#288

Post by MrBuddyCasino »

dagmx wrote: post #147
MrBuddyCasino wrote: post #135

Earlier quoted context omitted.

The 900 GB/s is from the NVLink-C2C interconnect, if you were wondering about that. They quote "up to 900 GB/s of bidirectional bandwidth between GPU and CPU". Mind you thats not to/from memory, which indeed only has 273 GB/s.

Ah I see. But the only C2C equivalent on the Apple side is the UltraFusion which is 2.5TB/s if I recall correctly.

Yes its not an "Apple M killer" at all. Also, the available official performance numbers are partially overstated (1 Petaflop is only possible for sparse FP4 models, "in theory").

Perhaps a sobering rule of thumb: if it was actually useful, you couldn't buy them because someone would scoop them all up to shove them in a DC and make money with it.

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

#289

Post by ImprobableTruth »

pbalau wrote: post #271
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…

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.

Shared memory of the past meant reserving a part of the memory for the GPU, which could then not be used or accessed by the CPU. If the CPU wanted to access something, it had to copy it from the GPU's section of the memory to its own. Unified memory means both just fully share the same memory.

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

#290

Post by testing22321 »

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 Unified Memory pool is the “game changer”

M1 knocking from 2020.

Gamed changed, past tense, six years ago. This is catch-up.

Post reply on HN