Comment by linuxhansl
13 hours ago
Off-topic and somewhat of a rant, but I'd far prefer us all focusing on open standards like HIP, SYCL, OpenCL, etc.
It's unbearable that most LLM inference happens on closed H/W, closed drivers, and closed SDKs.
13 hours ago
Off-topic and somewhat of a rant, but I'd far prefer us all focusing on open standards like HIP, SYCL, OpenCL, etc.
It's unbearable that most LLM inference happens on closed H/W, closed drivers, and closed SDKs.
On the SDK front, you tried just having an agent reimplement the model you're interested in and just use the weights? I've taken to treating off the shelf implementations as reference implementations anyway, because I can often squeeze out significantly better performance for my configuration and use case by having Codex hammer at it for a few hours.
Hugging face is working on something like this where well known models get fused into a single implementation.
Could you share the prompts and workflow? I’ve tried this too, but with mixed success when it comes to creating custom tile kernels.
I would really appreciate your input!
It's been pretty ad hoc, but my prompts are nothing special. Things I generally do:
1. Top end model on high/xhigh thinking (last time I did it it was Sol xhigh I think)
2. Make sure it creates some representative fixtures of different sizes and sets up a good testing, profiling and benchmarking loop that doesn't require my input.
3. Make sure it has access to reference implementation code
Edit: Oh and one obvious pitfall that for some reason I still have to remind even smart models of from time to time: make sure it knows not to try to parallelize its benchmark runs. I've occasionally had an agent struggle to figure out absolutely nonsensical data because it tried to run multiple tests on the same compute hardware simultaneously.
The problem with the open standards is that their dev UX is absolutely horrible. You can't neglect usability, and then be surprised that there are no users.
This is at the core of the matter for me, and my knowledge is too weak to understand why this is the case. I don't enjoy the idea of relying on Nvidia's stack for GPU compute, but the alternatives I've tried (e.g. Vulkan compute) are higher friction to use. I am trying to reconcile why; Nvidia shouldn't have this moat.
My software is labeled "CPU only unless using an nVidia GPU". I would prefer to strikethrough "nVidia". Incidentally, this means no more Mac support.
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.
4 replies →
Commercially it's better to have AMD support CUDA which can help break Nvidia soft monopoly.
yeh - exactly.
Sucks like important libraries like Alphafold are locked into CUDA. Its ridiculous for researchers.
I would too, but sadly that's Khronos' job to organize, and they've had trouble getting American vendors to work together.
It's likely that CUDA will continue dominating until they put aside their differences. The current MLX/MPS/ROCm ecosystems are too fractured to threaten Nvidia.
Maybe a not-Khronos org should try
Wdym American Vendors?
Intel uses SPIRV iirc
> Intel uses SPIRV iirc
They're migrating away from SPIR-V to their own, Intel PISA: https://discourse.llvm.org/t/rfc-upstreaming-the-pisa-backen...
3 replies →
I'm talking about holistic efforts like OpenCL, and standards that would be equivalent to Nvidia's "Compute Capability" versioning.
The basic underlying tech can be agreed on, but Apple/AMD/Intel all have different GPU priorities that limit their ability to agree on a CUDA-adjacent hardware platform.
6 replies →
it will only get worse now when hughingface was bough by nvidia, not immediately, but in span of year or years...
It's impossible to have an open standard. Hardware accelerators are nothing alike and have different perf characteristics. Each kernel is tuned to the hardware. The idea of writing a performant kernel in opencl is a fantasy.
Source: worked at a bunch of accelerator companies in the kernels or equivalent team. They're nothing alike.
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.
It's not possible to do reliably. None of the models in current use today use any esoteric math. It's extremely easy to implement the math behind both the inference and learning of all modern models.
2 replies →