Analysis of Floating-Point Matrix Multiplication Computed via Integer Arithmetic

MaRDI QIDQ7180929arXivFDO

Authors Ahmad Abdelfattah, Jack Dongarra, Massimiliano Fasi, Mantas Mikaitis, Françoise Tisseur

Publication date 2025

Published in arXiv

Mathematics Subject Classification ID

Numerical linear algebra (65F99) Roundoff error (65G50) Numerical algorithms for specific classes of architectures (65Y10)

arXiv classification

math.NA

Cited in

(1)

• LampAttention: Look-Ahead Mixed-Precision FlashAttention for Dedicated Accelerators

This page was built for publication: Analysis of Floating-Point Matrix Multiplication Computed via Integer Arithmetic

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7180929)