Hacker News Reader

Comment by KeplerBoy | Hacker News Reader

That's a problem on a different level of the CUDA stack.

Having a compiler that takes a special C++ or python dialect and compiles it to GPU suitable llvm-ir and then to a GPU binary is one thing (and there's progress on that side: triton, numba, soonish mojo), being able to launch that binary without going through the nvidia driver is another problem.

View on HN

Cannot Vulcan compute be used to execute code on GPU without relying on proprietary libs? Why not?

You still require a Vulkan driver to do anything with it. Until last year, Nvidia hardware required a proprietary Vulkan driver (prior to Nvvk), and anything pre-Pascal still requires that.

Yes but you can use any GPU with Vulkan, not only NVIDIA.

Vulkan Compute's semantics are limited by SPIR-V and thus cannot implement all of the features CUDA provides (ex. there is no proper notion of a "pointer")

Also it's much more convenient to use plain C++ rather than a custom shading language, especially if you're writing complex numerical code or need some heavy templated abstractions to do powerful stuff. And the CUDA tooling itself is just much easier to use compared to Vulkan, with its seamless integration of host / device code.

> [...] there's progress [...]

Don't forget about Julia!

and jax, tinygrad and halide. God it's such an awesome time to be into that stuff.

Yeah, the latter one is more useful for effective lock-in breaking.

Reply on news.ycombinator.com