I’m starting a bi-weekly newsletter on all the GPU things under the LLVM umbrella: GPU backends in LLVM, GPU dialects in MLIR, middle-end work related to GPU compilation, external LLVM- and MLIR-based GPU compilers, relevant conference talks, etc. I’m going to publish new issues every other Friday on llvm-dev and a dedicated website: https://llvm-gpu-news.github.io.
The first issue is available at: https://llvm-gpu-news.github.io/2020/12/11/issue-1.html.
I’m also pasting the content below, in case you prefer to read in your email client.
The high-level goals are to surface common themes in GPU compilation for different hardware, and to raise awareness of the general LLVM community about important aspects of GPU compilation.
thanks for this effort, very interesting!
OpenMP offloading is actively developed and I was even thinking
to produce a irregular OpenMP newsletter. While I might still do,
I think we should have the OpenMP GPU content in here as well.
What is a good way to do that?
OpenMP sounds like a great addition and is well within the scope of this newsletter.
I think it would be best if you submitted OpenMP news as pull request or github issues for future llvm gpu news issues. This should be straightforward because all you need is to edit markdown files. For example, see https://github.com/llvm-gpu-news/llvm-gpu-news.github.io/blob/main/docs/_posts/2020-12-11-issue-1.md.
If that doesn’t work for you, feel free to send me a set of keywords and places to scan periodically for new content, e.g., phabricator search filter, mailing lists to watch, etc.