CUDA Tile Open Sourced

Post by saagarjha » Fri, Dec 26, 2025, 2:32 AM UTC

pjmlp wrote: post #5

jauntywundrkind wrote: post #2

Will be interesting to see if Nvidia and other have any interest & energy getting this used by others, if there actually is an ecosystem forming around it. Google leading XLA & IREE, with awesome intermediate representations, used by lots of hardware platforms, and backing really excellent Jax & Pytorch implementations, having tools for layout & optinization folks can share: they really build an amazing community. Th…

For NVidia it suffices this is a Python JIT allowing programming CUDA compute kernels directly in Python instead of C++, yet another way how Intel and AMD, alongside Khronos APIs, lag behind in great developer experiences for GPU compute programming. Ah, and Nsight debugging also supports Python CUDA Tiles debugging. https://developer.nvidia.com/blog/simplify-gpu-programming-w...

Post by CamperBob2 » Fri, Dec 26, 2025, 2:40 AM UTC

saagarjha wrote: post #48

CamperBob2 wrote: post #7

Fun game: see how many clicks it takes you to learn what MLIR stands for. I lost count at five or six. Define your acronyms on first use, people.

This is a GitHub repo for compiler engineers.

Post by trueismywork » Fri, Dec 26, 2025, 2:54 AM UTC

fooblaster wrote: post #29

Let's see if developers sleepwalk into another trap to keep us locked into nvidia's hardware for the next decade.

Post by ipnon » Fri, Dec 26, 2025, 3:09 AM UTC

CamperBob2 wrote: post #54

ipnon wrote: post #46

Earlier quoted context omitted.

GPU programming definitely is not beginner friendly. There's a much higher learning curve than most open source projects. To learn basic Python you need to know about definitions and loops and variables, but to learn CUDA kernels you need to know maybe an order of magnitude more concepts to write anything useful. It's just not worth the time to cater to people who don't RTFM, the README would be twice as long and be…

That's the whole problem. I had to "R" multiple "FMs" before one of them bothered to define the acronym. Stop carrying water for poor documentation practice.

Post by almostgotcaught » Fri, Dec 26, 2025, 3:19 AM UTC

jauntywundrkind wrote: post #2

Will be interesting to see if Nvidia and other have any interest & energy getting this used by others, if there actually is an ecosystem forming around it. Google leading XLA & IREE, with awesome intermediate representations, used by lots of hardware platforms, and backing really excellent Jax & Pytorch implementations, having tools for layout & optinization folks can share: they really build an amazing community. Th…