Hacker News new | ask | show | jobs
by pjmlp 582 days ago
First they need to support everything that CUDA is capable of in programing language portfolio, tooling and libraries.
1 comments
bryanlarsen 582 days ago
A typical LLM might use about 0.1% of CUDA. That's all that would have to be ported to get that LLM to work.
link
pjmlp 582 days ago
Which is missing the point why CUDA has won.

Then again, maybe the goal is getting 0.1% of CUDA market share. /s

link
imtringued 582 days ago
Nvidia has won because their compute drivers don't crash people's systems when they run e.g. Vulkan Compute.

You are mostly listing irrelevant nice to have things that aren't deal breakers. AMD's consumer GPUs have a long history of being abandoned a year or two after release.

link
pjmlp 582 days ago
CUDA C++, CUDA Fortran, CUDA Anything PTX, plus libraries, IDE integration, GPU graphical debugging, aren't only nice to have things.
link
its_down_again 582 days ago
In the words of Gilfoyle-- I'll bite. Why has CUDA won?
link
pjmlp 582 days ago
CUDA C++, CUDA Fortran, CUDA Anything PTX, plus libraries, IDE integration, GPU graphical debugging.

Coupled with Khronos, Intel, AMD never delivering anything comparable with OpenCL, Apple losing interest after Khronos didn't took OpenCL into the direction they wanted, Google never adopting it favouring their Renderscript dialect.

link