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.
- NVIDIA GPU with compute capability 2.0 or above
- CUDA 5.5
- NVIDIA CUB 1.2.0+
- A modern Linux distribution
Related publicationIf 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
This software is released under the BSD-3-clause license.
Galois, a framework to exploit amorphous data-parallelism in irregular programs. Copyright (C) 2018, 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.