A dynamic parallel volume rendering computation mode based on cluster

Authors:
Weifang Nie;Jizhou Sun;Jing Jin;Xiaotu Li;Jie Yang;Jiawan Zhang
Affiliations:
IBM New Technology Center, Tianjin University, Tianjin, P.R.China;IBM New Technology Center, Tianjin University, Tianjin, P.R.China;IBM New Technology Center, Tianjin University, Tianjin, P.R.China;IBM New Technology Center, Tianjin University, Tianjin, P.R.China;IBM New Technology Center, Tianjin University, Tianjin, P.R.China;IBM New Technology Center, Tianjin University, Tianjin, P.R.China
Venue:
ICCSA'05 Proceedings of the 2005 international conference on Computational Science and Its Applications - Volume Part III
Year:
2005

Citing 3
Cited 0

PVM: Parallel virtual machine: a users' guide and tutorial for networked parallel computing

PVM: Parallel virtual machine: a users' guide and tutorial for networked parallel computing
Parallel programming: techniques and applications using networked workstations and parallel computers

Parallel programming: techniques and applications using networked workstations and parallel computers
Building a Linux Hpc Cluster With Xcat

Building a Linux Hpc Cluster With Xcat

Quantified Score

Hi-index	0.00

Visualization

Abstract

Based on cluster, a dynamic parallel mode–the MSGD (Master-Slave-Gleaner-Dynamic) mode is presented in this paper. Combining the load balancing with the MSG (Master-Slave-Gleane) mode, this mode brings in a load balancing strategy–task pool, which can coordinate the workload of each node effectively. A volume rendering algorithm called Splatting is used to test the performance of this mode on IBM Cluster1350. The results prove that this mode can effectively increase the total calculation speed and improve the global load balance. In addition this mode has good scalability and is suitable for various parallel volume rendering algorithms with large-scale data volume.