Heterogeneous Intelligent Accelerator Experiment Platform for Ship Information Infrastructure

This paper combined the requirement easily use demand of ship information infrastructure in the scenarios of heterogeneous artificial intelligent (AI) accelerators in the ship user system, and established a benchmark for heterogeneous intelligent accelerator for ship information infrastructure. In order to achieve the benchmark test of multiple AI accelerators in parallel area in ship information infrastructure and improve the convenience and intuitiveness of heterogeneous task management, an experiment platform for heterogeneous AI accelerators based on container technology was designed in this paper. This experiment platform implemented resource management, dataset management, model management, synchronization testing, models evaluation, and operation of multiple servers in the cluster, through which the ship users could view heterogeneous resource status and task execution progress at one glance.

Authors

Institutions

Publication Details

Published
2024-12-02
DOI
https://doi.org/10.1109/swc62898.2024.00240
Primary Topic
Advanced Sensor and Control Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Heterogeneous Intelligent Accelerator Experiment Platform for Ship Information Infrastructure

Wanhai Xu, Kai Huang, Song Da, Chen Ma
Advanced Sensor and Control Systems
article

Heterogeneous Intelligent Accelerator Experiment Platform for Ship Information Infrastructure

Wanhai Xu, Kai Huang, Song Da, Chen Ma
article en

Abstract

This paper combined the requirement easily use demand of ship information infrastructure in the scenarios of heterogeneous artificial intelligent (AI) accelerators in the ship user system, and established a benchmark for heterogeneous intelligent accelerator for ship information infrastructure. In order to achieve the benchmark test of multiple AI accelerators in parallel area in ship information infrastructure and improve the convenience and intuitiveness of heterogeneous task management, an experiment platform for heterogeneous AI accelerators based on container technology was designed in this paper. This experiment platform implemented resource management, dataset management, model management, synchronization testing, models evaluation, and operation of multiple servers in the cluster, through which the ship users could view heterogeneous resource status and task execution progress at one glance.

Tianjin University (CN)
Industry, innovation and infrastructure
Openalex Percentile: Top 64%
Advanced Sensor and Control Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.