Reproducible and Accurate Matrix Multiplication for GPU Accelerators - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Reproducible and Accurate Matrix Multiplication for GPU Accelerators

Abstract

Due to non-associativity of floating-point operations and dynamic scheduling on parallel architectures, getting a bitwise reproducible floating-point result for multiple executions of the same code on different or even similar parallel architectures is challenging. In this paper, we address the problem of reproducibility in the context of matrix multiplication and propose an algorithm that yields both reproducible and accurate results. This algorithm is composed of two main stages: a filtering stage that uses fast vectorized floating-point expansions in con-junction with error-free transformations; an accumulation stage based on Kulisch long accumulators in a high-radix carry-save representation. Finally, we provide implementations and performance results in parallel environments like GPUs.
Fichier principal
Vignette du fichier
paper.pdf (181 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01102877 , version 1 (13-01-2015)

Identifiers

  • HAL Id : hal-01102877 , version 1

Cite

Roman Iakymchuk, David Defour, Caroline Collange, Stef Graillat. Reproducible and Accurate Matrix Multiplication for GPU Accelerators. 2015. ⟨hal-01102877⟩
820 View
1015 Download

Share

Gmail Facebook Twitter LinkedIn More