LonestarGPU

LonestarGPU is a collection of widely-used real-world applications that exhibit irregular behavior.
This work is done in collaboration with Texas State University, San Marcos, USA

IMPORTANT: LonestarGPU 2.0 fixes bugs in DMR, SP, and MST from version 1.02 and contains newer and faster implementations. You are strongly encouraged to upgrade to version 2.0.

Requirements

Download

Installation, Building and Running

tar jxf lonestargpu-2.0.tar.bz2 cd lonestargpu-2.0/ less README

Although LSG 2.0 does not run directly on GPGPGU-sim v3.2.1, you may want to read how to get LSG 2.0 running on GPGPU-sim.

Changelog

2014-01-14 LonestarGPU<lonestar@ices.utexas.edu> * Version 2.0 * New implementations of BFS, SSSP, DMR, MST and SP * Faster versions of BFS and SSSP using Merrill's strategy * PTA now verifies correctly * All the new implementations produce output for easy verification * DMR features new code to automatically perform minimal number of data-transfers * New maintainer (Sreepathi Pai <sreepai@ices.utexas.edu>) 2013-09-03 LonestarGPU<lonestar@ices.utexas.edu> * version 1.02 * Breadth-First Search bug fix on computing amount of work per thread. * Barnes-Hut uses diameter instead of radius. * Delaunay Mesh Refinement bug fix about reading input * Minimum Spanning Tree uses union-find * Header fix for MAC and FreeBSD * Update to CudaSM2Cores 2013-02-01 LonestarGPU<lonestar@ices.utexas.edu> * version 1.0 * uses common code base * Barnes Hut: bug fix, additional optimizations, and Kepler support added * Points-to Analysis: 4.x compatibility * inputs can be downloaded with "make inputs" 2013-01-16 LonestarGPU <lonestar@ices.utexas.edu> * version 0.9 * added Breadth-First Search * added Barnes-Hut N-Body Simulation * added Delaunay Mesh Refinement * added Minimum Spanning Tree * added Points-to Analysis * added Single-Source Shortest Paths * added Survey Propagation

Related publication

If you find this software useful in academic work, please acknowledge LonestarGPU and cite the following publication:
  A Quantitative Study of Irregular Programs on GPUs
  Martin Burtscher, Rupesh Nasre, Keshav Pingali
  IEEE International Symposium on Workload Characterization (IISWC) 2012

License

This software is released under the terms of the University of Texas at Austin Research License, which makes this software available without charge to anyone for academic, research, experimental, or personal use. For all other uses, please contact the University of Texas at Austin's Office of Technology Commercialization.

Galois, a framework to exploit amorphous data-parallelism in irregular
programs.

Copyright (C) 2014, The University of Texas at Austin. All rights
reserved.  UNIVERSITY EXPRESSLY DISCLAIMS ANY AND ALL WARRANTIES
CONCERNING THIS SOFTWARE AND DOCUMENTATION, INCLUDING ANY WARRANTIES OF
MERCHANTABILITY, FITNESS FOR ANY PARTICULAR PURPOSE, NON-INFRINGEMENT
AND WARRANTIES OF PERFORMANCE, AND ANY WARRANTY THAT MIGHT OTHERWISE
ARISE FROM COURSE OF DEALING OR USAGE OF TRADE.  NO WARRANTY IS
EITHER EXPRESS OR IMPLIED WITH RESPECT TO THE USE OF THE SOFTWARE OR
DOCUMENTATION. Under no circumstances shall University be liable for
incidental, special, indirect, direct or consequential damages or loss
of profits, interruption of business, or related expenses which may
arise from use of Software or Documentation, including but not limited
to those resulting from defects in Software and/or Documentation,
or loss or inaccuracy of data of any kind.

Note that LonestarGPU 2.0 also includes code from NVIDIA. Please see the individual files for license information.