[Kurtz79]

Does it even make sense calling them 'GPUs' (I just checked NVIDIA product page for the H100 and it is indeed so)?

There should be a quicker way to differentiate between 'consumer-grade hardware that is mainly meant to be used for gaming and can also run LLMs inference in a limited way' and 'business-grade hardware whose main purpose is AI training or running inference for LLMs".

[blitzar]

We are fast approaching the return of the math coprocessor. In fashion they say that trends tend to reappear roughly every two decades, its overdue.

[egorfine]

Yeah I would love for Nvidia to introduce faster update cycle to their hardware, so that we'll have models like "H201", "H220", etc.

I think it will also make sense to replace "H" with a brand number, sort of like they already do for customer GPUs.

So then maybe one day we'll have a math coprocessor called "Nvidia 80287".

[beAbU]

I remember the building hugh end workstations for a summer job in the 2000s, where I had to fit Tesla cards in the machines. I don't remember what their device names were, we just called them tesla cards.

"Accelerator card" makes a lot of sense to me.

[WithinReason]

It's called a tensorcore and it's in most GPUs

[genewitch]

"GPGPU" was something from over a decade ago; for general purpose GPU computing

[hnuser123456]

Yeah, Crysis came out in 2007 and could run physics on the GPU.

[AlphaSite]

I think apple calls them NPUs and Broadcom calls them XPUs. Given they’re basically the number 2 and 3 accelerator manufacturers one of those probably works.

[codedokode]

By the way I wonder, what has more performance, a $25 000 professional GPU or a bunch of cheaper consumer GPUs costing $25 000 in total?

[omneity]

Consumer GPUs in theory and by a large margin (10 5090s will eat an H100 lunch with 6 times the bandwidth, 3x VRAM and a relatively similar compute ratio), but your bottleneck is the interconnect and that is intentionally crippled to avoid beowulf GPU clusters eating into their datacenter market.

Last consumer GPU with NVLink was the RTX 3090. Even the workstation-grade GPUs lost it.

https://forums.developer.nvidia.com/t/rtx-a6000-ada-no-more-...

[sigbottle]

H100s also has custom async WGMMA instructions among other things. From what I understand, at least the async instructions formalize the notion of pipelining, which engineers were already implicitly using because to optimize memory accesses you're effectively trying to overlap them in that kind of optimal parallel manner.

[washadjeffmad]

I just specify SXM (node) when I want to differentiate from PCIe. We have H100s in both.

[addandsubtract]

We could call the consumer ones GFX cards, and keep GPU for the matrix multiplying ones.

[beAbU]

GPU stands for "graphics processing unit" so I'm not sure how your suggestion solves it.

Maybe renaming the device to an MPU, where the M stands for "matrix/math/mips" would make it more semantically correct?

[rebolek]

I think that G was changed to "general", so now it's "general processing unit".

[rpdillon]

This doesn't seem to be true at all. It's a highly specialized chip for doing highly parallel operations. There's nothing general about it.

I looked around briefly and could find no evidence that it's been renamed. Do you have a source?

[fouc]

CPU is already the general (computing) processing unit so that wouldn't make sense

[amelius]

Well, does it come with graphics connectors?

[OliverGuy]

Nope, doesn't have any of the required hardware to even process graphics iirc

[diggan]

Although the RTX Pro 6000 is not consumer-grade, it does come with graphics ports (four Displayports) and does render graphics like a consumer card :) So seems the difference between the segments is becoming smaller, not bigger.

[simpleintheory]

That’s because it’s intended as a workstation GPU not one used in servers

[diggan]

Sure, but it still sits in the 'business-grade hardware whose main purpose is AI training or running inference for LLMs" segment parent mentioned, yet have graphics connectors so the only thing I'm saying is that just looking at that won't help you understand what segment the GPU goes into.

[namibj]

I'd Like to point at the first revision AMD MI50/MI60 cards which were at the time the most powerful GPUs on the market at least by memory bandwidth.

Defining GPU as "can output contemporary display connector signal and is more than just a ramdac/framebuffer-to-cable translator, starting with even just some 2D blitting acceleration.