All Projects → AutomataLab → Tigr

AutomataLab / Tigr

Licence: MIT license
Transforming Graphs for Efficient Irregular Graph Processing on GPUs

Programming Languages

Cuda
1817 projects
C++
36643 projects - #6 most used programming language
Makefile
30231 projects

Projects that are alternatives of or similar to Tigr

awesome-dynamic-graphs
A collection of resources on dynamic/streaming/temporal/evolving graph processing systems, databases, data structures, datasets, and related academic and industrial work
Stars: ✭ 89 (+161.76%)
Mutual labels:  graph-processing, graph-analytics
graphi
🌠 An interactive network analysis & visualization tool
Stars: ✭ 20 (-41.18%)
Mutual labels:  graph-processing, graph-analytics
SuiteSparseGraphBLAS.jl
Sparse, General Linear Algebra for Graphs!
Stars: ✭ 79 (+132.35%)
Mutual labels:  graph-analytics
PowerWalk
Personalized PageRank (PPR) on GraphLab PowerGraph
Stars: ✭ 14 (-58.82%)
Mutual labels:  graph-processing
Krill
An efficient concurrent graph processing system
Stars: ✭ 33 (-2.94%)
Mutual labels:  graph-processing
dxram
A distributed in-memory key-value storage for billions of small objects.
Stars: ✭ 25 (-26.47%)
Mutual labels:  graph-processing
Gephi
Gephi - The Open Graph Viz Platform
Stars: ✭ 4,552 (+13288.24%)
Mutual labels:  graph-analytics
v6d
vineyard (v6d): an in-memory immutable data manager. (Project under CNCF)
Stars: ✭ 557 (+1538.24%)
Mutual labels:  graph-analytics
Graphs.jl
An optimized graphs package for the Julia programming language
Stars: ✭ 197 (+479.41%)
Mutual labels:  graph-analytics
LightGraphs.jl
An optimized graphs package for the Julia programming language
Stars: ✭ 680 (+1900%)
Mutual labels:  graph-analytics
graphsurge
Graphs analytics on collections of views!
Stars: ✭ 22 (-35.29%)
Mutual labels:  graph-analytics
pgx-samples
Applications using Parallel Graph AnalytiX (PGX) from Oracle Labs
Stars: ✭ 39 (+14.71%)
Mutual labels:  graph-analytics
GraphScope
🔨 🍇 💻 🚀 GraphScope: A One-Stop Large-Scale Graph Computing System from Alibaba 来自阿里巴巴的一站式大规模图计算系统 图分析 图查询 图机器学习
Stars: ✭ 1,899 (+5485.29%)
Mutual labels:  graph-analytics
scarf
Toolkit for highly memory efficient analysis of single-cell RNA-Seq, scATAC-Seq and CITE-Seq data. Analyze atlas scale datasets with millions of cells on laptop.
Stars: ✭ 54 (+58.82%)
Mutual labels:  graph-analytics
gardenia
GARDENIA: Graph Analytics Repository for Designing Efficient Next-generation Accelerators
Stars: ✭ 22 (-35.29%)
Mutual labels:  graph-analytics
Subway
Out-of-GPU-Memory Graph Processing with Minimal Data Transfer
Stars: ✭ 30 (-11.76%)
Mutual labels:  graph-transformation
kaliningraph
🕸️ Graphs, finite fields and discrete dynamical systems in Kotlin
Stars: ✭ 62 (+82.35%)
Mutual labels:  graph-transformation
swap
A Solver for the Wavelength Assignment Problem (RWA) in WDM networks
Stars: ✭ 27 (-20.59%)
Mutual labels:  graph-transformation

Tigr

Tigr is a lightweight graph transformation and processing framework for GPU platforms.

In real-world graphs, the high irregularity of degree distribution acts as a major barrier to their efficient processing on GPU architectures. Tigr addresses the irregularity issue at its origin by transforming irregular graphs into more regular ones, meanwhile preserving the same results as running on the original graphs.

Compilation

To compile Tigr, just run make in the root directory.

Running applications in Tigr

The applications take the input graph as input as well as some optional arguments. For example:

$ ./sssp --input path-to-input-graph
$ ./sssp --input path-to-input-graph --source 10

Input graph format

Input graphs should be in form of plain text files, containing the list of the edges of the graph. Each line is corresponding to an edge and is of the following form:

V1  V2  W

It specifies that there is an edge from node V1 to node V2 with weight W. The Wight value is optional and if it is omitted, it is set to 1. The node-ids can start from 0 or 1. It ignores any line starting with a character rather than a number.

Graphs in this format can be found in many public graph repositories, such as SNAP's. There are some graph datasets ready to download in datasets folder. To download, just run make in each folder.

Publications:

[ASPLOS'18] Amir Nodehi, Junqiao Qiu, Zhijia Zhao. Tigr: Transforming Irregular Graphs for GPU-Friendly Graph Processing. In Proceedings of The 23th International Conference on Architectural Support for Programming Languages and Operating Systems, Williamsburg, VA, 2018. 15 pages

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].