LeapGraph: A Fully External Graph Processing System on High-Speed SSD

As graphs exponentially grow nowadays, it becomes more and more challenging to hold large-scale graphs inside the memory of a single machine. To address this issue, fully external graph systems offer a promising solution of high scalability by keeping the large-scale graph in storage while loading a small part of the graph into memory for computation. However, the rapid evolution of storage technology presents a challenge for traditional fully external graph systems because they are unable to leverage these high-speed storage, thus severely limiting their performance. As a result, this work aims to present a fully external graph system, LeapGraph, developed for modern, high-speed storage with three main designs. Our preliminary evaluation with billion-scale graphs reveals the promising result of LeapGraph.

Authors

Institutions

Publication Details

Published
2024-08-21
DOI
https://doi.org/10.1109/nvmsa63038.2024.10693656
Primary Topic
Advanced Data Storage Technologies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

LeapGraph: A Fully External Graph Processing System on High-Speed SSD

Yuan-Hao Chang, Tsun-Yu Yang, Ming-Chang Yang
Advanced Data Storage Technologies
article

LeapGraph: A Fully External Graph Processing System on High-Speed SSD

Yuan-Hao Chang, Tsun-Yu Yang, Ming-Chang Yang
article en

Abstract

As graphs exponentially grow nowadays, it becomes more and more challenging to hold large-scale graphs inside the memory of a single machine. To address this issue, fully external graph systems offer a promising solution of high scalability by keeping the large-scale graph in storage while loading a small part of the graph into memory for computation. However, the rapid evolution of storage technology presents a challenge for traditional fully external graph systems because they are unable to leverage these high-speed storage, thus severely limiting their performance. As a result, this work aims to present a fully external graph system, LeapGraph, developed for modern, high-speed storage with three main designs. Our preliminary evaluation with billion-scale graphs reveals the promising result of LeapGraph.

Chinese University of Hong Kong (HK), Institute of Information Science, Academia Sinica (TW)
Affordable and clean energy
Openalex Percentile: Top 82%
Advanced Data Storage Technologies
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.