MPI-BugBench [[MBB24](#References)] is an benchmark suite to evaluate the classification quality of MPI correctness tools. It covers various error classes in MPI while incorporating a broad range of real-world MPI usage scenarios.
## Preparation
For simple reproduction, all workflows are executed within Docker containers.
MBB uses a generation infrastructure written in Python to generate all test codes and supports different test generation levels (for details, see our [paper](#References)).
To generate the test cases for a given generation level (1-5) run the following commands:
```
```
python3 MBB.py -c generate --level 2
python3 MBB.py -c generate --level 2
```
```
Or
or
```
```
cd /MBB
cd /MBB
tar -xf real_world_data.csv.tar.gz
tar -xf real_world_data.csv.tar.gz
...
@@ -31,15 +39,18 @@ python3 MBB.py -c run -x <parcoach|itac|must> -t <timeout in seconds> -l <logs o
...
@@ -31,15 +39,18 @@ python3 MBB.py -c run -x <parcoach|itac|must> -t <timeout in seconds> -l <logs o
If you see an error like "Waiting for cache lock: Could not get lock /var/lib/dpkg/lock-frontend. It is held by process 3509 (apt)"
## References
Try: apt clean
[MBB24] Tim Jammer, Emmanuelle Saillard, Simon Schwitanski, Joachim Jenke, Radjasouria Vinayagame, Alexander Hück, Christian Bischof. 2024. MPI-BugBench: A Framework for Assessing MPI Correctness Tools]. In EuroMPI'24, September 25-27, 2024, Perth, Australia. Springer.
And retry the command to run the tool: python3 MBI.py -x itac -c run