#mlir
LLVM Weekly - #619, November 10th 2025. DFAJumpThreading on by default for CoreMark perf boost, further CAS development, MLIR pygments lexer improvements, Arm contributions to LLVM 21, and more llvmweekly.org/issue/619
LLVM Weekly - #619, November 10th 2025
llvmweekly.org
November 10, 2025 at 8:11 PM
Thanks to Jeremy Kun for his #mlir tutorial! 💙We forked and retooled for WinOS w/his blog as docs in the repo. Will go through and update for 2025 using his tutes as a guide and make adjustments. Plans are for MacOS & Linux with CMake - then Bazel afterward. 🎄#fsharp github.com/speakeztech/...
mlir-tutorial/docs/tutorials at WinOS-CMake · speakeztech/mlir-tutorial
MLIR For Beginners tutorial. Contribute to speakeztech/mlir-tutorial development by creating an account on GitHub.
github.com
November 12, 2025 at 3:21 AM
AWESOME! Yeah I remember seeing something about it in my investigations but hadn't dived deep into it because I was focused mostly on MLIR integration. Thanks for bringing this up!
November 2, 2025 at 2:10 PM
I'm at this point right now, but Im using chumsky/MLIR to parse and compile to spir-v.
October 12, 2025 at 7:50 PM
I have seen the light yay and it is

Rust + Julia + MLIR = The Holy Trinity
October 11, 2025 at 5:29 AM
Learning MLIR, actually low-key kind of excited at the prospect of making my own language.
October 4, 2025 at 10:44 AM
LLVM Weekly - #611, September 15th 2025. Ripple: A Compiler-Interpreted API for Efficient SIMD Programming, guidelines for adding/enabling new passes, on 'de-typification' of LLVM IR, lit using internal shell by default for LLVM tests, MLIR IRDL roadmap, and more llvmweekly.org/issue/611
LLVM Weekly - #611, September 15th 2025
llvmweekly.org
September 15, 2025 at 5:33 PM
i thought about doing something like this for fusion operations with triton or MLIR, but i think that's actually just a full phd topic of work because i'd need to develop some sort of proof engine for it
December 29, 2024 at 5:02 AM
I’m not the best person to answer that question. But I would want mixed signal to be a first class priority. If MLIR can’t fill that gap, it will make our jobs a lot more difficult! E.g. I imagine analog being useful for “fast weights” in continual learning and slow weights in digital.
November 23, 2024 at 6:57 PM
I had a great experience working with Chisel and believe in its big future. Seeing how novel compiler projects such as MLIR will impact hardware design is exciting. Look at CIRCT project if you are interested in more.
January 31, 2024 at 2:48 PM
Yesterday, I merged in a tutorial on mlir-opt (https://mlir.llvm.org/docs/Tutorials/MlirOpt/), the main debugging tool for running passses on MLIR code. This is roughly the upstremable parts of my first MLIR tutorial entry,
August 2, 2024 at 11:37 PM
Jag har sådana röjminnen från MLIR. Såg dem live på Magasinet i Gbg, så är nog färgad av den upplevelsen :)
March 22, 2025 at 8:20 PM
laranjadinho, eu só dou uma brincada no mundo dos compiladores, acho llvm muito brabo, tu acha que mlir vai vim ou é só promessa
January 17, 2025 at 11:55 PM
anunciaram vagas pra maintainer no mlir e fiquei com vontade de participar mas não sei se tenho capacidade pra tanto
May 17, 2025 at 12:03 AM
LLVM Weekly - #601, July 7th 2025. AsiaLLVM Dev Meeting videos posted, LLD support for GCC LTO, disallowing struct/array IR values inside functions, XeVM MLIR dialect, and more llvmweekly.org/issue/601
LLVM Weekly - #601, July 7th 2025
llvmweekly.org
July 7, 2025 at 6:43 PM
Mojo🔥: AI Programming Language

In this post, I’ve covered:

🧠 How Mojo fits into the future of AI infrastructure
⚙️ A high-level overview of LLVM & MLIR
🚀 Mojo’s core features and memory management, with examples
MOJO: AI Programming Language
Bridging Python's Simplicity with Rust's Performance
open.substack.com
August 2, 2025 at 10:16 PM
Looking forward to winter sun in Barcelona for #HiPEAC25 in a couple of weeks time, am involved in organising a workshop on #xDSL which is a Python MLIR compiler toolkit and talking about our work driving #FPGAs , #AIEs and #RISCV from Fortran
The Python-based xDSL compiler toolkit has now been downloaded over 100,000 times.

EPCC's Nick Brown has organised a workshop at #HiPEAC25 to bring together the xDSL community & explore the toolkit's future development. Read more on our website: https://buff.ly/4271a3n
January 9, 2025 at 11:55 AM
それではお聞き下さい。シブがき隊「Zokkon命(Love)」。
⋯あっ! なんか、かっこいいじゃん、ドキュメンタリ映画みたいだ。最高級の惚れ方をしたのね、星は寅に。
www.youtube.com/watch?v=mlir...
Zokkon命 シブがき隊
音がいまいち
www.youtube.com
July 20, 2024 at 4:52 PM
bindings to MLIR dialects in an intuitive and easy-to-use manner. By building on the Julia programming language, and its expressive features such as multiple dispatch and its extensible compiler, we design and implement a framework to generate MLIR [4/5 of https://arxiv.org/abs/2503.04771v1]
March 10, 2025 at 5:59 AM
behaviors to suit the non-UB assumptions required by compiler optimizations. (2) Lowering Support: Converts the given MLIR program into an executable form, enabling execution result comparisons, and selects a suitable lowering path for the program to [4/8 of https://arxiv.org/abs/2504.01379v1]
April 3, 2025 at 6:00 AM
Explorando las Diferentes Formas de Construir Herramientas con LLVM y MLIR

https://eldinero.lat/posts/A01B2C53-629F-48C2-B3B0-8A25858B5ED9
June 2, 2025 at 8:13 AM
[RFC] MLIR Dialect for WebAssembly Article URL: https://discourse.llvm.org/t/rfc-mlir-dialect-for-webassembly/86758 Comments URL: https://news.ycombinator.com/item?id=44229587 Points: 3 # Comments: 0 Interest | Match | Feed

Interest | Match | Feed
Origin
bsky.app
June 9, 2025 at 9:45 PM
その前段階としてのPoC実装もこちらにあった。

speakez-llc/fsharp-mlir-hello: Proof of Concept using MLIR and LLVM to build binaries from F# code github.com/speakez-llc/...
GitHub - speakez-llc/fsharp-mlir-hello: Proof of Concept using MLIR and LLVM to build binaries from F# code
Proof of Concept using MLIR and LLVM to build binaries from F# code - speakez-llc/fsharp-mlir-hello
github.com
July 7, 2025 at 6:24 AM
A 4 trillion USD company is well-established today but that may change as early as next year, thanks to disruptive technology - MLIR and Mojo. #ai
This New Language Might Kill NVIDIA’s GPU Monopoly
hackernoon.com
July 11, 2025 at 4:21 AM