talks-media

Talks, posters, and videos across EuroLLVM, DATE/OSDA, and outreach

Teaching

See courses for the ACM Europe School on MLIR and the ARITH 2026 CIRCT tutorial.

Talks and seminars

2026

  1. MLIRWS
    Progressive Arithmetic Lowering from Tensor Kernels to Synthesizable Datapaths
    Progressive Arithmetic Lowering from Tensor Kernels to Synthesizable Datapaths
    Louis Ledoux, Pierre Cochard, and Florent de Dinechin
    EuroLLVM Developers’ Meeting 2026, Apr 2026
    MLIR Workshop communication

2025

  1. Holigrail
    FloPoCo and MLIR: a multi-level compilation framework for many intents
    FloPoCo and MLIR: a multi-level compilation framework for many intents
    Pierre Cochard, and Louis Ledoux
    Holigrail Seminar, Sorbonne University, Sep 2025
    Invited talk

2024

  1. The Walls and the Dark Silicon Era: An Arithmetic Perspective
    The Walls and the Dark Silicon Era: An Arithmetic Perspective
    Louis Ledoux
    Dec 2024

2019

  1. Accelerating DL inference with (Open)CAPI and posit numbers
    Louis Ledoux, and Marc Casas
    OpenPOWER summit 2019, Oct 2019

Posters

2026

  1. ACM School
    HAriCo: Floating-Point MLIR to CIRCT Datapaths
    Louis Ledoux
    ACM Europe School on MLIR, A Coruña, Spain, Aug 2026
    Poster
  2. PEPR IA
    Multi-Level Compilation of AI Tensors and Activation Functions to Silicon
    Louis Ledoux
    PEPR IA Days, Rennes, France, Jun 2026
    Poster
  3. FDF
    Progressive Arithmetic Optimizations: Tensor and DSP Kernels to Synthesizable Datapaths
    Progressive Arithmetic Optimizations: Tensor and DSP Kernels to Synthesizable Datapaths
    Louis Ledoux, Pierre Cochard, and Florent de Dinechin
    3rd FPGA Developers’ Forum (FDF) meeting, May 2026
    Poster
  4. Floating-Point Datapaths in CIRCT via HAriCo and harico-arith-to-comb Lowering
    Louis Ledoux, Pierre Cochard, and Florent de Dinechin
    EuroLLVM Developers’ Meeting 2026, Apr 2026
    Poster
  5. Aussois
    Arithmetic Lowering with Emeraude-MLIR: Bridging Tensor and DSP Kernels to Silicon Datapaths
    Arithmetic Lowering with Emeraude-MLIR: Bridging Tensor and DSP Kernels to Silicon Datapaths
    Louis Ledoux, Pierre Cochard, and Florent de Dinechin
    PEPR IA Embarquee workshop, Aussois, Jan 2026
    Poster

2025

  1. Towards Multi-Level Arithmetic Optimizations
    Pierre Cochard, Luc Forget, Florent de Dinechin, and
    EuroLLVM 2025, Apr 2025
    Poster

2024

  1. LLMMMM: Large Language Models Matrix-Matrix Multiplications Characterization on Open Silicon
    Louis Ledoux, and Marc Casas
    11th BSC Symposium, May 2024
    Poster
  2. The Grafted Superset Approach: Bridging Python to Silicon with Asynchronous Compilation and Beyond
    Louis Ledoux, and Marc Casas
    DATE, Mar 2024
    Poster

2023

  1. An Open-Source Framework for Efficient Numerically-Tailored Computations
    Louis Ledoux, and Marc Casas
    BSCSymposium23, May 2023
    Poster

Videos

Outreach