Why 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.
CUDA-oxide: Nvidia's official Rust to CUDA compiler
11–20 of 132 posts
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#12Why 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.
Is this a serious question or are you just trolling?
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#13Personally 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.
Really hard to find alternatives to Julia for AD as a first class citizen
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#14Why 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.
I mean, AI is not good at writing x86-64 assembly code. Last time I tried (with both Claude and ChatGPT), the AI failed to even create basic programs other than Hello World.
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#15Why 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.
This is a Rust to CUDA converter so I guess it is for codes where the programmer wants it to function properly (Rust) and have good performance (CUDA).
It’s just a matter of different workflows for different users and application.
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#16Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#17Why 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.
I get what you mean but I think if anything AI pairs extremely well with strongly typed languages that are at times cumbersome for humans, but decrease the latency at which AI can get feedback on its code. In my (very) limited experience Rust is an excellent target for AI codegen.
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#18Why 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 want provable, deterministic transformation from the intent (specified in a higher level language) to the target assembly language. LLMs can't reliably output many artifacts for different platforms that behave the same.
4) Hopefully, we are still reviewing the code output by LLMs to some extent.
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#19Personally 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)
Re: CUDA-oxide: Nvidia's official Rust to CUDA compiler
#20Personally 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.
Really hard to find alternatives to Julia for AD as a first class citizen
I think the parent is mostly referring to solutions like Slang.D