Rendered at 01:11:11 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
saagarjha 7 minutes ago [-]
> On the H200s used for most of this work, the GPU's main memory is HBM, or high-bandwidth memory. Ironically, this is the slowest memory on the chip.
Nit: HBM is off chip, unlike shared memory and registers
augment_me 4 hours ago [-]
Crazy to not see a word about benchmarking/evaluation of the kernels.
IMO at this time when all performant GPU kernels are generated/hill-climbed, its the largest source of error we see.
Should be kernel run with a hot or cold cache in practice? Should your kernel be bitwise equivalent to a ref? What error margins should your kernel have to ref? How many times are you running the kernel to avoid thermal noise? Are you running on separate GPUs to avoid overfitting the current hardware? Can you cudagraph-compiling your kernel to remove launch overhead? Are you A/B B/A interleaving your kernel/reference runs to avoid running thermal bias?
saagarjha 9 minutes ago [-]
It’s not crazy at all, the blog post is clearly about human-guided optimization with LLMs rather than hillclimbing with an autonomous agent.
augment_me 5 minutes ago [-]
All of the above is as-relevant in human-guided optimization.
Farmadupe 33 minutes ago [-]
As someone who loves being able to press a button to receive matmuls tuned to the 3090 by his feet, are there rules of thumb to work out how to set thresholds for evals?
Do I want to set a particular threshold on any individual op (or a layer for a given transformer)? e.g "for this test set, 99% of l2norms being within 1e-4 error of the golden reference kernel"
Or do I want to just shortcut all that and go with task based evals? eg "word error no worse than 1% greater than the reference speech-to-text model"?
I'm assuming the latter is the way to go in the first instance?
augment_me 10 minutes ago [-]
It depends on if you do training or inference and also at what scale.
For your task with the 3090, and I assume inference, I would like you suggest do end-to-end on target task.
Sometimes for example, a normalization layer can cancel out/fix an error from a previous layer, then it makes no sense to spend flops to save the numerics.
This is kind of a wild west in inference serving, you sometimes change exp to tanh, sometimes go full 4bit, sometimes remove full layers because you still perform fine on the end-task.
Numerics and correctness are more important for training kernels and backwards passes
kollegekid 2 hours ago [-]
The writing here is so clear. Do you use Llms to write?
saagarjha 10 minutes ago [-]
My guess is that the LLMs helped with the diagrams but the writing is mostly or completely from a human. It’s quite good (and has a few typos :P)
Nit: HBM is off chip, unlike shared memory and registers
IMO at this time when all performant GPU kernels are generated/hill-climbed, its the largest source of error we see.
Should be kernel run with a hot or cold cache in practice? Should your kernel be bitwise equivalent to a ref? What error margins should your kernel have to ref? How many times are you running the kernel to avoid thermal noise? Are you running on separate GPUs to avoid overfitting the current hardware? Can you cudagraph-compiling your kernel to remove launch overhead? Are you A/B B/A interleaving your kernel/reference runs to avoid running thermal bias?
Do I want to set a particular threshold on any individual op (or a layer for a given transformer)? e.g "for this test set, 99% of l2norms being within 1e-4 error of the golden reference kernel"
Or do I want to just shortcut all that and go with task based evals? eg "word error no worse than 1% greater than the reference speech-to-text model"?
I'm assuming the latter is the way to go in the first instance?
For your task with the 3090, and I assume inference, I would like you suggest do end-to-end on target task.
Sometimes for example, a normalization layer can cancel out/fix an error from a previous layer, then it makes no sense to spend flops to save the numerics.
This is kind of a wild west in inference serving, you sometimes change exp to tanh, sometimes go full 4bit, sometimes remove full layers because you still perform fine on the end-task.
Numerics and correctness are more important for training kernels and backwards passes