RAO-SS: A Prototype of Run-time Auto-tuning Facility for Sparse Direct Solvers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Katagiri, Takahiro, Ishii, Yoshinori, Honda, Hiroki
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910573226098688
author Katagiri, Takahiro
Ishii, Yoshinori
Honda, Hiroki
author_facet Katagiri, Takahiro
Ishii, Yoshinori
Honda, Hiroki
contents In this paper, a run-time auto-tuning method for performance parameters according to input matrices is proposed. RAO-SS (Run-time Auto-tuning Optimizer for Sparse Solvers), which is a prototype of auto-tuning software using the proposed method, is also evaluated. The RAO-SS is implemented with the Autopilot, which is middle-ware to support run-time auto-tuning with fuzzy logic function. The target numerical library is the SuperLU, which is a sparse direct solver for linear equations. The result indicated that: (1) the speedup factors of 1.2 for average and 3.6 for maximum to default executions were obtained; (2) the software overhead of the Autopilot can be ignored in RAO-SS.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11880
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RAO-SS: A Prototype of Run-time Auto-tuning Facility for Sparse Direct Solvers
Katagiri, Takahiro
Ishii, Yoshinori
Honda, Hiroki
Mathematical Software
Performance
In this paper, a run-time auto-tuning method for performance parameters according to input matrices is proposed. RAO-SS (Run-time Auto-tuning Optimizer for Sparse Solvers), which is a prototype of auto-tuning software using the proposed method, is also evaluated. The RAO-SS is implemented with the Autopilot, which is middle-ware to support run-time auto-tuning with fuzzy logic function. The target numerical library is the SuperLU, which is a sparse direct solver for linear equations. The result indicated that: (1) the speedup factors of 1.2 for average and 3.6 for maximum to default executions were obtained; (2) the software overhead of the Autopilot can be ignored in RAO-SS.
title RAO-SS: A Prototype of Run-time Auto-tuning Facility for Sparse Direct Solvers
topic Mathematical Software
Performance
url https://arxiv.org/abs/2408.11880