Distributed terascale volume visualization using distributed shared virtual memory

Johanna Beyer*, Markus Hadwiger, Jens Schneider, Won Ki Jeong, Hanspeter Pfister

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

Table 1 illustrates the impact of different distribution unit sizes, different screen resolutions, and numbers of GPU nodes. We use two and four GPUs (NVIDIA Quadro 5000 with 2.5 GB memory) and a mouse cortex EM dataset (see Figure 2) of resolution 21,494 x 25,790 x 1,850 = 955GB. The size of the virtual distribution units significantly influences the data distribution between nodes. Small distribution units result in a high depth complexity for compositing. Large distribution units lead to a low utilization of GPUs, because in the worst case only a single distribution unit will be in view, which is rendered by only a single node. The choice of an optimal distribution unit size depends on three major factors: the output screen resolution, the block cache size on each node, and the number of nodes. Currently, we are working on optimizing the compositing step and network communication between nodes.

Original languageEnglish
Title of host publication1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Proceedings
Pages127-128
Number of pages2
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Providence, RI, United States
Duration: 23 Oct 201124 Oct 2011

Publication series

Name1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011 - Proceedings

Conference

Conference1st IEEE Symposium on Large-Scale Data Analysis and Visualization 2011, LDAV 2011
Country/TerritoryUnited States
CityProvidence, RI
Period23/10/1124/10/11

Fingerprint

Dive into the research topics of 'Distributed terascale volume visualization using distributed shared virtual memory'. Together they form a unique fingerprint.

Cite this