DMTCP (Distributed MultiThreaded Checkpointing) transparently checkpoints a single-host or distributed computation in user-space -- with no modifications to user code or to the O/S. It works on most Linux applications, including HPC (e.g. SLURM/MPI, InfiniBand), 3D graphics, Python, Matlab, R, GUI desktops, etc. It is robust and widely used (on Sourceforge since 2007).
- distributed computation
- 3D graphics
Be the first to post a review of Distributed MultiThreaded Checkpointing!