CUDA-l2: Surpassing cuBLAS performance for matrix multiplication through RL

https://github.com/deepreinforce-ai/CUDA-L2

by dzign • 8 months ago

132 13 8 months ago

github.com

stonogo• 8 months ago

Am I reading this wrong, or does this only support FP16 inputs, and compares its performance against an FP32 solver?

Bulat_Ziganshin• 8 months ago

They compare HGEMM implementations. At least CUBLAS has HGEMM functions.

HGEMM means half-precision (i.e. FP16) general matrix multiplication

j2kun• 8 months ago

They claim the algorithm "discovered" the new techniques, but the methods described in section 5 do not seem all that novel to me. It smells like it could be "laundering" the literature [1] and reshuffling existing techniques. This is not inherently a bad thing, but I would hope that if it is borrowing existing techniques, the appropriate citation would eventually make it into this paper.

[1] https://www.argmin.net/p/lore-laundering-machines

AlexCoventry• 8 months ago

In the future, we will all be Jürgen Schmidhuber. :-)

hedgehog• 8 months ago

I hate to break it to you but the original work on that topic was by Schmidhuber & Schmidhuber back in 1963.

alyxya2• 8 months ago

There generally aren't new techniques when optimizing something ubiquitous. Instead, there are a lot of ways to apply existing techniques to create new and better results. Most ideas are built on top of the same foundational principles.

slashdave• 8 months ago

I am not sure about that. However, what is clear is that if there is a new technique, it will not be found by this LLM.

josephg• 8 months ago

Yes. And there’s still lots of places where you can get significant speed ups by simply applying those old techniques in a new domain or a novel way. The difference between a naive implementation of an algorithm and an optimised one is often many orders of magnitude. Look at automerge - which went from taking 30 seconds on a simple example to tens of milliseconds.

I think about this regularly when I compile C++ or rust using llvm. It’s an excellent compiler backend. It produces really good code. But it is incredibly slow, and for no good technical reason. Plenty of other similar compilers run circles around it.

Imagine an llvm rewrite by the people who made V8, or chrome or the unreal engine. Or the guy who made luajit or the Go compiler team. I’d be shocked if we didn’t see an order of magnitude speed up overnight. They’d need some leeway to redesign llvm IR of course. And it would take years to port all of llvm’s existing optimisations. But my computer can retire billions of operations per second. And render cyberpunk at 60fps. It shouldn’t take seconds of cpu time to compile a small program.

Q6T46nT668w6i3m• 8 months ago

You’re not kidding. I just looked. There isn’t anything novel in that section. I assumed from the description they found novel methods but this is standard GPU Gems advice.

alyxya2• 8 months ago

The chart confused me because I expected to see performance numbers of CUDA-L2 compared to the others, but instead it shows a chart showing the speedup percentage of CUDA-L2 over the others. In some sense, the bar chart effectively inverts the performance of torch.matmul and cuBLAS with how much percentage it shows. 0% on the bar chart would only mean equal performance.

konradha• 8 months ago

I've been trying my hand at RL envs for various sparse matrix algorithms in CUDA. It's easy to generate code that "looks good", "novel" and "fast". Escaping the distribution and actually creating novel sequences of instructions or even patterns (has any model come with something as useful as fan-in/fan-out or double buffering patterns that's now ubiquituous?) seems difficult to say the least.

roflmaostc• 8 months ago

Q: What if I need matrix dimensions (M, N, K) not found in your configurations? A: 1. You can find the nearest neighbor configuration (larger than yours) and pad with zeros. 2. Feel free to post your dimensions on GitHub issues. We are happy to release kernels for your configuration.

Lol, this will be potentially much slower than using the general matmul kernel.

However, I like this kind of research because it really exploits specific hardware configurations and makes it measurable faster (unlike some theoretical matmul improvements). Code specialization is cheap, and if it saves in the order of a few %, it quickly reimburses its price, especially for important things like matmul.

CUDA-l2: Surpassing cuBLAS performance for matrix multiplication through RL

Related Stories