331–340 of 380 posts
Fun fact: More than half of all engineers at NVIDIA are software engineers. Jensen has deliberately and strategically built a powerful software stack on top of his GPUs, and he's spent decades doing it. Until Intel finds a CEO who is as technical and strategic, as opposed to the bean-counters, I doubt that they will manage to organize a successful counterattack on CUDA.
Fun fact: More than half of all engineers at NVIDIA are software engineers. Jensen has deliberately and strategically built a powerful software stack on top of his GPUs, and he's spent decades doing it. Until Intel finds a CEO who is as technical and strategic, as opposed to the bean-counters, I doubt that they will manage to organize a successful counterattack on CUDA.
> ...as opposed to the bean-counters
Intel whining about the CHIPS Act, while doing huge layoffs, while continuing massive stock buybacks, while continuing to pay dividends...
I'm not impressed.
I'd expect a corporation facing an existential crisis would make some tough decisions and accept the consequences. I know that Wall St (investors) is the tail wagging the dog. But I expect a leader to hold off the vultures (ghouls) long enough to do the necessary pivots.
At least Intel's doom spiral isn't as grimm as the condundrum facing the automobile manufacturers. They need to prop up their declining business units, pay off their loan sharks (investors), somehow resolve their death embrace with the unions, transform culture (bust up their organizational siloes), transform relationships with their suppliers, AND somehow get capital (cheap enough) to fund their pivots.
I'm sure Intel has the technical chops to do great things. But financially their half-measures strategy doesn't instill confidence.
Source: Just a noob reading the headlines. Am probably totally off base.
Earlier quoted context omitted.
> but nobody gets that it's the software and ecosystem. Really? Because I’m confident Intel knows exactly what it’s about. Have you looked at their contributions to Linux and open source in general? They employ thousands of software developers.
Which is why intel left nvidia and everyone else in the dust with CUDA, which they developed. Oh, wait…
Them understanding what was coming doesn't mean they have a magic wand to instantly have a fully competitive product. You can't write a CUDA competitor until you've gotten the framework laid. The fact they invested so heavily in their GPUs makes it pretty obvious they weren't caught off-guard, but catching up takes time. Sometimes you can't just throw more bodies at the problem...
If they create a better tool chain, ecosystem, and programming experience than CUDA and compatible with all computational platforms at their peak performance - awesome! Everyone wins! Until then, it's a bit funny claim, especially considering what a failure OpenCL was (programmer's experience and fading support). Or trying to do GPGPU with compute shaders in DX/GL/Vulkan. Are they really "motivated"? Because they had…
I wish AMD or Intel would just ship a giant honking CPU with 1000s of cores that doesn't need any special purpose programming languages to utilize. Screw co-processors. Screw trying to make yet another fucked up special purpose language -- whether that's C/C++-with-quirks or a half-assed Python clone or whatever. Nuts to that. Just ship more cores and let me use real threads in regular programming languages.
In practice, people weren’t afraid to roll up their sleeves and write CUDA code. If you wanted good performance you had to think about data parallelism anyways, and at that point you’re not benefiting from x86 backwards compatibility. It was a fascinating dream while it lasted though.
Earlier quoted context omitted.
Perhaps they're doubling down, but even doubling down is not enough to say that they're serious about it since they've been so neglectful for so many years - for example, right now they explicitly say that many of AMD GPUs are not supported by ROCm; if they're not willing to put their money where their mouth is and do the legwork to ensure support for powerful cards they sold just a few years ago, how can they say yo…
People argue for ROCm to support older cards because that is all they have accessible to them. AMD has lagged on getting expensive cards into the hands of end users because they've focused only on building super computers. I predict that access to the newer cards is a more likely scenario. Right now, you can't rent a MI250 or even MI300x, but that is going to change quickly. Azure is going to have them, as well as ot…
I'm considering adding ROCm support for some ML-enabled tool - no matter if it's a commercial product or an open source library - the thing I need from AMD is to ensure that the ROCm support I make will work without hassle for these end-users with random old AMD gaming cards (because these are the only users who need the tool to have ROCm support), and if ROCm upstream explicitly drops support for some cards because AMD no longer regularly test it, well, the ML tool developers aren't going to do that testing for them either; that's simply AMD intentionally refusing to do even the bare minimum (do a lot of testing for a wide variety of hardware to fix compatibility issues) that I'd expect to be table stakes for saying that "AMD is doubling down on ROCm".
Earlier quoted context omitted.
> People argue for ROCm to support older cards because that is all they have accessible to them. What they really need is to support the less expensive cards, of which the older cards are a large subset. There are a lot of people who will make contributions and fix bugs if they can actually use the thing. Some CS student at the university has to pay tuition and therefore only has an old RX570, and that isn't going to…
The older cards are going to be supported by Mesa and RustiCL for the foreseeable future. Rocm is not the only game in town, far from it.
Earlier quoted context omitted.
Both AMD and Intel (and Qualcomm to some degree) just don't seem to get how you beat NVIDIA. If they want to grab a piece of NVIDIA's pie, they do NOT need to build something better than an H100 right away. There are a million consumers who are happy with a 4090 or 4080 or even 3080 and would love for something that's equally capable at half price, and moreover, actually available for purchase, from Amazon/NewEgg/whe…
That's not going to work because each GPU has a different internal architecture and aligning the way data is fed with how stream processors operate is different for each architecture (stuff like how memory buffers are organized/aligned/paged etc.). AMD is very incompatible to Nvidia at the lowest level so things/approaches that are fast on Nvidia can be 10x slower on AMD and vice versa.
That's fine but the job of software is to abstract that out. The code should at least compile, even if it is 10x less efficient and if multiple awkward sets of instructions need to be used instead of one.
If Pytorch can be recompiled for AMD overnight with zero effort (only `ln -s amdcc nvcc`, `ln -s /usr/local/cuda /usr/local/amda`) they will gain some footing against Nvidia.
Earlier quoted context omitted.
>Literally, every single announcement (and action) coming out of AMD these days is that they are serious about the software. I don't see any reason at this point to doubt them. I have a bridge to sell.
It is way, way better in the last year or so. Perfectly reasonable cards for inference if you actually understand the stack and know how to use it. Is nVidia faster? Sure, but at twice the price for 20-30% gains. If that makes sense for you, keep paying the tax.
Earlier quoted context omitted.
People argue for ROCm to support older cards because that is all they have accessible to them. AMD has lagged on getting expensive cards into the hands of end users because they've focused only on building super computers. I predict that access to the newer cards is a more likely scenario. Right now, you can't rent a MI250 or even MI300x, but that is going to change quickly. Azure is going to have them, as well as ot…
The way I see it, the whole point of ROCm support is being able to service the many users who have pre-existing AMD cards and nothing else available. If someone is going to rent a GPU, I don't need to bother with adding extra features for them, because they can just rent a CUDA-capable GPU instead. I'm considering adding ROCm support for some ML-enabled tool - no matter if it's a commercial product or an open source…
ROCm is a stack of a whole lot of stuff. I don't see a stack of software being "the whole point".
> the thing I need from AMD is to ensure that the ROCm support I make will work without hassle for these end-users with random old AMD gaming cards (because these are the only users who need the tool to have ROCm support)
From wikipedia:
"ROCm is primarily targeted at discrete professional GPUs"
They are supporting Vega onwards and are clear about the "whole point" of ROCm.
Earlier quoted context omitted.
Normally, I wouldn't do that, but this time I felt like both comments were intentionally inflammatory and then the context for my response was lost. "literally nothing" is also wrong given that they just had a large press announcement on Dec 6th (yt as part of my response below), where they spent 2 hours saying (and showing) they are serious. The second comment was made and then immediately deleted, in a way that was…
I deleted it because I was in an extremely bad mood and later realized it was simply wrong of me to post it and vent my unrelated frustration in those comments. I think it's in extremely bad taste to repost what I wrote when I made the clear choice to delete it.