On the Scalability of the GPUexplore Explicit-State Model Checker

@inproceedings{Cassee2017OnTS,
  title={On the Scalability of the GPUexplore Explicit-State Model Checker},
  author={Nathan Cassee and Thomas Neele and Anton Wijs},
  booktitle={GaM@ETAPS},
  year={2017}
}
The use of graphics processors (GPUs) is a promising approach to speed up model checking to such an extent that it becomes feasible to instantly verify software systems during development. GPUexplore is an explicit-state model checker that runs all its computations on the GPU. Over the years it has been extended with various techniques, and the possibilities to further improve its performance have been continuously investigated. In this paper, we discuss how the hash table of the tool works… 

Figures and Tables from this paper

Analysing the Performance of GPU Hash Tables for State Space Exploration

This paper experimentally compares two different hash tables optimised for the GPU, one being the GPUEXPLORE hash table, and the other using Cuckoo hashing, to analyse the applicability of the two hash tables for state space exploration and concludes that Cuckoos hashing is three times faster than GPUEX PLORE hashing for random data and five to nine times faster for non-random data.

Swarm model checking on the GPU

A comprehensive performance analysis of Grapple focused on various design parameters, including the size of the visited-state queue structure, implementation of guard statements, and nondeterministic exploration order shows thatGrapple performs favorably compared to the SPIN swarm and a prior non-swarm GPU implementation.

Parallel computational tree logic model‐checking on pushdown systems

A parallel framework based on the Compute Unified Device Architecture and the corresponding parallel algorithms to solve the emptiness problem of ABPDSs are proposed and an encouraging performance speedup is indicated.

Swarm model checking on the GPU

A comprehensive performance analysis of Grapple focused on various design parameters, including the size of the visited-state queue structure, implementation of guard statements, and nondeterministic exploration order shows thatGrapple performs favorably compared to the SPIN swarm and a prior non-swarm GPU implementation.

Efficient Parallel CTL Model-Checking for Pushdown Systems

  • Xinyu ChenHansheng WeiXin YeLi HaoYanhong HuangJianqi Shi
  • Computer Science
    2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA/IUCC/BDCloud/SocialCom/SustainCom)
  • 2018
A partitioned alternatingmulti automaton is proposed, which is a parallel extension of the alternating multi automaton (AMA) to represent the infinite set of configurations for the alternating Pushdown System and it is demonstrated how the emptiness analysis can be conducted in parallel based on a partitioned rotating automaton.

References

SHOWING 1-10 OF 37 REFERENCES

GPUexplore: Many-Core On-the-Fly State Space Exploration Using GPUs

This paper discusses the possible approaches involving related work, and proposes an alternative, using a new hash table approach for GPUs, which shows significant speed-ups compared to the established sequential counterparts.

GPUexplore 2.0: Unleashing GPU Explicit-State Model Checking

A new version of the GPU model checker, GPUexplore, running on state-of-the-art hardware can be more than 100 times faster than a sequential implementation for large models and is on average eight times faster compared to the previous version of this tool running on the same hardware.

Many-core on-the-fly model checking of safety properties using GPUs

  • Anton WijsD. Bosnacki
  • Computer Science
    International Journal on Software Tools for Technology Transfer
  • 2015
This work presents techniques to perform graph generation and exploration using general purpose graphics processors (GPUs) and shows how the exploration technique can be extended to detect deadlocks and check safety properties on-the-fly.

GPU Accelerated On-the-Fly Reachability Checking

This paper proposes an approach, named GPURC, to utilize the Graphics Processing Units (GPUs) to speed up the reachability verification and develops a BFS-based state space generation algorithm in GPUs that makes full use of the GPU memory hierarchy and the latest dynamic parallelism feature in CUDA to achieve a high parallelism.

Towards a GPGPU-parallel SPIN model checker

This work shows how the 2012 multicore CPU-parallel state-space exploration algorithm of the SPIN model checker can be re-engineered to take advantage of the unique parallel-processing capabilities of the GPGPU architecture, and demonstrates how to overcome the non-trivial design obstacles presented by this task.

Partial-Order Reduction for GPU Model Checking

This work proposes novel parallel algorithms for three practical approaches to partial-order reduction for on-the-fly explicit-state model checking using GPUs, and shows that the implementation achieves a reduction similar to or better than the state-of- the-art techniques for CPUs.

Analysing the Performance of GPU Hash Tables for State Space Exploration

This paper experimentally compares two different hash tables optimised for the GPU, one being the GPUEXPLORE hash table, and the other using Cuckoo hashing, to analyse the applicability of the two hash tables for state space exploration and concludes that Cuckoos hashing is three times faster than GPUEX PLORE hashing for random data and five to nine times faster for non-random data.

Efficient Explicit-State Model Checking on General Purpose Graphics Processors

This work parallelizes the breadth-first layered construction of the state space graph by executing complex operations on the graphics processing unit (GPU) to accelerate state space exploration for explicit-state model checking.

BFS-Based Model Checking of Linear-Time Properties with an Application on GPUs

This paper considers how a model checker that completely runs on a GPU can be extended to efficiently verify whether finite-state concurrent systems satisfy liveness properties, and exploits the fact that the state space is the product of the behaviour of several parallel automata.

GPU Accelerated Strong and Branching Bisimilarity Checking

A novel way to check strong bisimilarity on general-purpose graphics processing units GPUs is presented, and it is shown experimentally that an implementation of it for CUDA-enabled GPUs is competitive with other parallel techniques that run either on a GPU or use message-passing on a multi-core system.