2024 EuroLLVM - MLIR Linalg Op Fusion - Theory & Practice
2024 European LLVM Developers' Meeting https://llvm.org/devmtg/2024-04/ ------ MLIR Linalg Op Fusion - Theory & Practice Speaker: Javed Absar ------ Slides: https://llvm.org/devmtg/2024-04/slide... ----- Linalg is an important dialect in MLIR. Many external projects also use Linalg as key dialect to enter the MLIR world. It is an instantiation of what is called - StructuredOps i.e. structured types and structured iterators working coherently together. This talk will first cover some essential concepts of Linalg to give the audience an understanding of linalg ops and transformations. Then it will focus on op fusion in linalg. At end of the talk the audience will have a better understanding on Linalg Op Fusion and adjacent topics. ----- Videos Edited by Bash Films: http://www.BashFilms.com

2024 EuroLLVM - Faster Compilation with GlobalISel: Skipping LLVM-IR

2025 EuroLLVM - An Introduction to Tensor Tiling in MLIR

Palantir built the application layer on the NSA surveillance state

2024 EuroLLVM - Teaching MLIR concepts to undergraduate students

Visualizing transformers and attention | Talk for TNG Big Tech Day '24

The mind-bending reality of quantum mechanics - with Jim Al Khalili

Something is jamming GPS over Europe. Here's what we found

The Insane Genius of a Formula 1 Gearbox

Turing Award Winner: Disagreeing with Google, Postgres, Future Problems | Mike Stonebraker

MLIR Open Meeting 2022-01-27: Introduction to Linalg.generic

TSMC's Incredible 2nm Curvy Masks

If You Have A Bad Memory, I’ll Help You Fix It In 28 Minutes

Scott Aaronson - The TRUTH About Quantum Computing

2024 EuroLLVM - Transform-dialect schedules: writing MLIR-lowering pipelines in MLIR

Yann LeCun | Self-Supervised Learning, JEPA, World Models, and the future of AI

CppCon 2017: Teresa Johnson “ThinLTO: Scalable and Incremental Link-Time Optimization”

2023 EuroLLVM - MLIR Dialect Design and Composition for Front-End Compilers

2024 EuroLLVM - How Slow is MLIR

1: Introduction to Neural Networks and Deep Learning; Training Deep NNs

