swerner

It may look like that from the inside. From the outside, as a user, it looks like Meta only wants to connect customers with advertisers.

I’ve worked gate for years, so I’ve seen plenty of RVs and camper trailers from the inside, and you do get an impression of the people that travel in them. Everyone’s there - be it tie die and patchouli hippies, be it hunting gear and MRE preppers, college party kids or mom and pop coming because it was on some travel destination list.

Camp with hippies, and you’ll be at a hippie festival. Camp with ravers, you’ll be at a rave. You can camp with a church group there, with philosophers (we had them as neighbors one year), with families with small kids, or with (disarmed) 2A gun nuts.

It’s what seven days of sleep deprivation, dehydration and probably substance abuse do to you.

The kinds of drugs people at burning man prefer to take are not very likely to lead to death from overdose.

Really? My takeaway is “there’s a reason we keep motor vehicles out of pedestrian zones”. A surprisingly high number of vehicle related incidents for a 5mph zone.

This was just one web search away: https://www.aol.com/articles/burning-man-deaths-look-every-1...

Given that firearms are prohibited and motor vehicle traffic is limited to 5mph, that alone would take out two unnatural causes of death. Also, drowning is a lot less likely to occur in the desert.

Proximity to borders leaves the government the possibility that if it really, really wanted to search a property, they'd just have to cede some land in a 100mile radius to a foreign country and instantly create an international border wherever they need one.

If your stack is open source, why not? I’ve had good results with pointing an LLM to a debug build of the GPU compiler when I saw it crash. It just seems you need to periodically remind them that gdb exists to prevent it from littering your drivers with printfs.

Wait, I have an idea: What is your qualification for talking about graphics programming? If you cannot provide credentials, I will have no other choice than to claim you don’t know what you’re talking about, based on the criteria by which you judged my comments so far.

Not everything is AI and dot products of massive vectors, there are still applications that do other maths on GPUs

My thinking was rather that most of our current programming languages put memory layout fully into the programmer’s responsibility - I can think off hand of a language where the compiler makes performance decisions like whether your structure are SoA, AoS or SoAoS, what alignment, padding, strides and float types to use.

Automatic decisions about when to use cooperative loads through shared local mem versus gathers from global mem and hardware caches are also something that such a hypothetical compiler would have to make.

Vulkan compute is not really designed or intended to be a CUDA competitor, its feature set is much more restricted, and Vulkan host side code is much more verbose than CUDA. OpenCL or SYCL are much closer in features to CUDA. I found that when using SYCL on Nvidia, debugging symbols etc can be passed through and you can use tools like NSight Compute to profile it as if it were CUDA.

For a performant portable language, we’d have to go to a higher level where you describe what to do and leave the how to do to the compiler. It would then need to be able to adjust memory layout, access patterns, data type choice to the underlying hardware. I’m not sure if this is possible to do reliably - the closest we have right now may in fact be highly detailed plain English descriptions of the algorithms fed to an LLM prompted to produce assembly.

Yes, unfortunately. Otherwise we could just implement all of SYCL and OpenCL on top of Vulkan and live happily ever after.

TIL, I didn’t know that. I always assumed it came from level zero”, the Intel computer layer that ZLUDA was translating to before its developer was hired by AMD to target HIP.

What domain do you think I was talking about?

Oh, absolutely. Nvidia is the modern day “nobody gets fired for buying IBM”. The reason we’re still using Unix is not because it’s the best, but because it had to much inertia to let any alternative become its successor. Similarly, C and HTML are maybe the most terrible yet extremely useful languages we have.

Unfortunately, many of very good ideas end with “it’s open source, anyone can contribute” because very few actually do.

Most modern graphics is compute. Pixar, Dreamworks, Sony, etc do not use Vulkan to render their movies. It’s CPUs or CUDA.

“graphics people do not (and cannot) write CUDA kernels/shaders” is just not true at all. All it would take to verify that would be things like reading the introduction of the OptiX documentation, a small sample of SIGGRAPH GPU papers or the Blender/Cycles source code.

Outsider to what?

If it helps you at all:

“if you've never debugged a GPU synchronization error or kernel panic due to some GPU firmware bug or fought absolute shit profilers hunting for perf”

I have done all of those things. As part of my full time job, for years.

Now that we’ve put all of that aside, can we stop talking about me and go back to discussing moats? What do you think are top three things that are holding customers back from buying AMD GPUs instead of Nvidia GPUs?

I could be misremembering, but I think Jensen Huang himself once called CUDA or the CUDA ecosystem their moat, and it certainly seems to be accepted narrative in the tech press. They may be wrong there, and you sharing your first hand experience here would be helpful to many of us readers here.

I don't think we're at a point yet where anyone would trust ZLUDA enough to ship commercial products that rely on it. I would be delighted though, if anyone can prove me wrong.

I could post the GitHub URLs of all the shader code I wrote that’s running on countless GPUs right now, but what would it change? I’m still just a random guy on the internet with an opinion that happens to be different from your opinion.

You can simply disagree with me, regardless of my experience (or lack thereof).

To my knowledge, SPIR-V on Intel will stay, and be it only because it’s part of the OpenCL and Vulkan standards.

They were maintained by Codeplay - paid for my Intel. Nvidia can make contributions anytime they want, and here is the problem: Nvidia does not want to. Until each vendor starts pitching in with contributing their backend to an open standard, you will have to rely on others doing it for them.

I’m too old to participate in internet pissing contests.

If that is your standard, I do have an idea what I’m talking about.

The problem with OneAPI is naming. It leads people to believe that is another competing standard where in fact is is simply just an implementation of a standard compliant SYCL compiler. If it just had been named “Intel SYCL compiler”, similar to the existing and accepted Intel OpenCL compiler, it would have been easier.

What would you expect the hardware consortium to coordinate on? Unified ISA?

What do you mean by holistic? SYCL is an open versioned standard that allows for vendor specific extensions. The problem is not that there isn’t a proper standard, the problem is that many hardware vendors - or software developers simply don’t want to adopt it.

Intel (via Codeplay) was handing it out on a silver platter - Nvidia on SYCL, full top chain, and people still wouldn’t want it.

AI will take down Nvidia’s moat. When it becomes trivial to translate CUDA/PTX to HIP, SYCL or Metal, CUDA is no longer the moat, it becomes the intermediate representation.