Earlier quoted context omitted.
[flagged]
The majority of computer owners on planet Earth
But also the majority of programmers?
CUDA-oxide: Nvidia's official Rust to CUDA compiler
21–30 of 132 posts
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#22Why do we bother with programming languages today? Why not have the LLMs just write assembly code and skip the human readable part? We are not reviewing it anymore anyway.
Because when this idiotic hypemachinery finally dies an agonising, painful death, some of us still want to work with computers
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#23Here's the repo link https://github.com/NVlabs/cuda-oxide
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#24Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#25Personally I really don't want new GPU languages that do not have AD as a first class citizen. I mean rust is an improvement over C++ CUDA but still.
There is actually work on adding autodiff to Rust, maybe not really first class citizen, but at least build in: https://doc.rust-lang.org/std/autodiff/index.html (it is still at a pre-RFC stage so it is not something that soon will be added)
Incredible, I have never heard of std::autodiff before. Isn't it rare for a programming language to provide AD within the standard library? Even Julia doesn't have it built-in, I wouldn't expect Rust out of all languages to experiment it in std.
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#26Why do we bother with programming languages today? Why not have the LLMs just write assembly code and skip the human readable part? We are not reviewing it anymore anyway.
A lot of really good reasons: 1) Higher level code is easier for LLMs to review and iterate upon. The more the intent is clear from the code, the easier it is for humans and LLMs to work with. 2) LLMs get stuck or fail to solve a problem sometimes. It is preferable to have artifacts that humans can grok without the massive extra effort of parsing out assembly code. 3) Assembly code varies massively across targets. We…
I'd add to that
1.5) Having a compiler in the loop that does things like enforcing type constraints (and in the case if Rust in particular, therefore memory safety guarantees) is really useful both for humans and LLMs.
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#27This is amazing.. ive been working with custom CUDA kernels and https://crates.io/crates/cudarc for a long time, and this honestly looks like it could be a near drop-in replacement. im especially curious how build times would compare? Most Rust CUDA crates obv rely on calling CMake or nvcc, which can make compilation painfully slow. coincidentally, just last week i was profiling build times and found that tools like…
Do other people agree cuda-oxide looks like a near dorp in replacement for cudarc?
That would be amazing, but probably not imo complementarily so.
I am curious what distinguished cuda-oxide. Beyond it being totally under nv control.
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#28Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#29Personally I really don't want new GPU languages that do not have AD as a first class citizen. I mean rust is an improvement over C++ CUDA but still.
every GPU related post has a comment which makes my eyes roll all the way back. this is the one for this post.
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#30Hell yea! I have been doing it with Cudarc (Kernels) and FFI (cuFFT). Using manual [de]serialization between byte arrays and rust data structs. I hope this makes it lower friction!