CUDA Tile Open Sourced
github.com
CUDA Tile Open Sourced
1–10 of 111 posts
Re: CUDA Tile Open Sourced
#2Will 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.
There's still so much room for planning/scheduling, so much hardware we have yet to target. RISC-V has really interesting vector instructions, for example, and it seems like there's so much exploration / work to do to better leverage that.
Nvidia has partners everywhere now. Nvlink is used by Intel, AWS Tritanium, others. Yesterday the Groq exclusive license that Nvidia paid to give to Groq?! Seeing how and when CUDA Tiles emerges: will be interesting. Moving from fabric partnerships, up up up the stack.
Re: CUDA Tile Open Sourced
#3Will 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…
On the RISC-V vector instructions, could you elaborate? Are the vector extensions substantially different from those in ARM or x86?
Re: CUDA Tile Open Sourced
#4Will 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…
> There's still so much room for planning/scheduling, so much hardware we have yet to target
this is nicely illustrated by this recent article:
Re: CUDA Tile Open Sourced
#5Will 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...
Re: CUDA Tile Open Sourced
#6Will 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…
On the RISC-V vector instructions, could you elaborate? Are the vector extensions substantially different from those in ARM or x86?
it's fairly similar to Arm's sve2, but very different from the x86 side in that the instructions are variable length rather than fixed
Re: CUDA Tile Open Sourced
#7Fun 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.
Re: CUDA Tile Open Sourced
#8Will 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...
Slang is a fantastic developer experience.
Re: CUDA Tile Open Sourced
#9Fun 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.
I did it in three. I selected it in your comment, and then had to hit "more" to get to the menu to ask Google about it, which brought me to https://www.google.com/search?q=MLIR which says: MLIR is an open-source compiler infrastructure project developed as a sub-project of the LLVM project. Hopefully
Get better at computers and stop needing to be spoon-fed information, people!
Re: CUDA Tile Open Sourced
#10Writing this in Mojo would have been so much easier