Performance studies of the parallel VIM code
- Argonne National Lab., IL (United States). Reactor Analysis Div.
In this paper, the authors evaluate the performance of the parallel version of the VIM Monte Carlo code on the IBM SPx at the High Performance Computing Research Facility at ANL. Three test problems with contrasting computational characteristics were used to assess effects in performance. A statistical method for estimating the inefficiencies due to load imbalance and communication is also introduced. VIM is a large scale continuous energy Monte Carlo radiation transport program and was parallelized using history partitioning, the master/worker approach, and p4 message passing library. Dynamic load balancing is accomplished when the master processor assigns chunks of histories to workers that have completed a previously assigned task, accommodating variations in the lengths of histories, processor speeds, and worker loads. At the end of each batch (generation), the fission sites and tallies are sent from each worker to the master process, contributing to the parallel inefficiency. All communications are between master and workers, and are serial. The SPx is a scalable 128-node parallel supercomputer with high-performance Omega switches of 63 {micro}sec latency and 35 MBytes/sec bandwidth. For uniform and reproducible performance, they used only the 120 identical regular processors (IBM RS/6000) and excluded the remaining eight planet nodes, which may be loaded by other`s jobs.
- Research Organization:
- Argonne National Lab., IL (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- W-31109-ENG-38
- OSTI ID:
- 231699
- Report Number(s):
- ANL/RA/SUMM--88954; CONF-9606116--35-Summ.; ON: DE96010813
- Country of Publication:
- United States
- Language:
- English
Similar Records
Load Balancing and Scalability of a Subgrid Orography Scheme in a Global Climate Model
Distributed multitasking ITS with PVM