Parallel Programming: Techniques and Applications Using Networked Workstations and Parallel Computers (2nd Edition)
| Hi-index | 0.00 |
Electron tomography allows structure determination of complex biological specimens. The tomographic reconstruction algorithms require an extensive use of computational resources and considerable processing time to compute high resolution 3D reconstructions. High performance computing (HPC) turns out to be essential to cope with these demands. We propose and evaluate different HPC strategies based on the well-known master/slave paradigm for tomographic reconstruction. Our results demonstrate that there is an underlying problem to tackle, if the performance is to be further improved: the access to the shared file system. On the other hand, it has been shown that it is possible to find out the optimal size of the tasks distributed by the master, specially for large datasets.