Error Analysis of Matrix Multiplication Emulation Using Ozaki-II Scheme

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Uchino, Yuki, Ozaki, Katsuhisa, Imamura, Toshiyuki
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908807689404416
author Uchino, Yuki
Ozaki, Katsuhisa
Imamura, Toshiyuki
author_facet Uchino, Yuki
Ozaki, Katsuhisa
Imamura, Toshiyuki
contents The Ozaki-II scheme is an emulation method that leverages the Chinese Remainder Theorem to compute high-precision matrix multiplication via a sequence of low-precision matrix multiplications. In this scheme, the attainable numerical accuracy improves as the number of low-precision matrix multiplications increases. Previous numerical studies have shown that single- and double-precision matrix multiplication using the Ozaki-II scheme achieves higher throughput than that of standard BLAS routines on modern AI hardware equipped with fast INT8 matrix multiply-accumulate units with INT8 inputs and INT32 accumulation. However, the accuracy of the Ozaki-II scheme can degrade when the exponent distribution of the input matrices is wide, in which case a large number of low-precision matrix multiplications is required to obtain high-precision results. In this paper, we present a rigorous deterministic error analysis of the Ozaki-II scheme. The proposed analysis not only clarifies the accuracy behavior of the method but also enables the estimation of the number of low-precision matrix multiplications required to achieve a desired level of numerical accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02549
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Error Analysis of Matrix Multiplication Emulation Using Ozaki-II Scheme
Uchino, Yuki
Ozaki, Katsuhisa
Imamura, Toshiyuki
Numerical Analysis
Distributed, Parallel, and Cluster Computing
The Ozaki-II scheme is an emulation method that leverages the Chinese Remainder Theorem to compute high-precision matrix multiplication via a sequence of low-precision matrix multiplications. In this scheme, the attainable numerical accuracy improves as the number of low-precision matrix multiplications increases. Previous numerical studies have shown that single- and double-precision matrix multiplication using the Ozaki-II scheme achieves higher throughput than that of standard BLAS routines on modern AI hardware equipped with fast INT8 matrix multiply-accumulate units with INT8 inputs and INT32 accumulation. However, the accuracy of the Ozaki-II scheme can degrade when the exponent distribution of the input matrices is wide, in which case a large number of low-precision matrix multiplications is required to obtain high-precision results. In this paper, we present a rigorous deterministic error analysis of the Ozaki-II scheme. The proposed analysis not only clarifies the accuracy behavior of the method but also enables the estimation of the number of low-precision matrix multiplications required to achieve a desired level of numerical accuracy.
title Error Analysis of Matrix Multiplication Emulation Using Ozaki-II Scheme
topic Numerical Analysis
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2602.02549