Article Dans Une Revue Works in Progress in Embedded Computing Journal Année : 2025

Towards Optimized Arithmetic Circuits with MLIR

Résumé

Numerical programs are typically conceived with real numbers in mind. However, programming languages operate at a lower abstraction level with fixed-width machine arithmetic. This abstraction gap limits the scope of legal arithmetic optimizations in compilers, in particular when targetting hardware.

This work introduces a set of MLIR dialects that explicitly separate concerns between real-valued computation and low-level arithmetic representation. The RealArith dialect captures mathematical intent, enabling algebraic rewrites and approximationaware transformations. The FixedPointArith dialect expresses quantized arithmetic with fine-grained control over bit widths. This separation enables arithmetic optimizations beyond those supported by conventional compilers. An example end-to-end lowering flow performs polynomial approximation, then generates fixed-point Horner-form architectures tailored for hardware synthesis. Early hardware results on signal processing benchmarks demonstrate the potential of this approach.

Fichier principal
Vignette du fichier
dsdwip2025.pdf (2.44 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05385229 , version 1 (27-11-2025)

Licence

Identifiants

Citer

Louis Ledoux, Pierre Cochard, Florent de Dinechin. Towards Optimized Arithmetic Circuits with MLIR. Works in Progress in Embedded Computing Journal, 2025, 11 (1), pp.4. ⟨10.64552/wipiec.v11i1.90⟩. ⟨hal-05385229⟩
80 Consultations
153 Téléchargements

Altmetric

Partager

  • More