A parallel pipelined renderer for time-varying volume data

Tzi Cier Chiueh, Kwan-Liu Ma

Research output: Contribution to conferencePaper

8 Citations (Scopus)

Abstract

This paper presents a strategy for efficiently rendering time-varying volume data on a distributed-memory parallel computer. Visualizing time-varying volume data take both large storage space and long computation time. Instead of employing all processors to render one volume at a time, a pipelined rendering approach partitions processors into groups so that multiple volumes can be rendered concurrently. The overall rendering time is greatly minimized because rendering is overlapped with I/O required to load the volume data sets. Moreover, parallelization overhead may be reduced as a result of partitioning the processors. We modify an existing parallel volume renderer to exploit various levels of rendering parallelism and to study how the partitioning of processors may lead to optimal rendering performance. We find that two factors affecting the overall execution time are resource utilization efficiency and pipeline startup latency. The optimal partitioning configuration is the one that balances these two factors. Tests on Intel Paragon computers show that in general optimal partitionings do exist for a given rendering task and result in 40-50% saving in overall rendering time.

Original languageEnglish (US)
Pages9-15
Number of pages7
DOIs
StatePublished - Jan 1 1997
Externally publishedYes
Event3rd International Symposium on Parallel Architectures, Algorithms, and Networks, I-SPAN 1997 - Taipei, Taiwan, Province of China
Duration: Dec 18 1997Dec 20 1997

Other

Other3rd International Symposium on Parallel Architectures, Algorithms, and Networks, I-SPAN 1997
CountryTaiwan, Province of China
CityTaipei
Period12/18/9712/20/97

Fingerprint

Plant startup
Pipelines
Data storage equipment

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Safety, Risk, Reliability and Quality

Cite this

Chiueh, T. C., & Ma, K-L. (1997). A parallel pipelined renderer for time-varying volume data. 9-15. Paper presented at 3rd International Symposium on Parallel Architectures, Algorithms, and Networks, I-SPAN 1997, Taipei, Taiwan, Province of China. https://doi.org/10.1109/ISPAN.1997.645046

A parallel pipelined renderer for time-varying volume data. / Chiueh, Tzi Cier; Ma, Kwan-Liu.

1997. 9-15 Paper presented at 3rd International Symposium on Parallel Architectures, Algorithms, and Networks, I-SPAN 1997, Taipei, Taiwan, Province of China.

Research output: Contribution to conferencePaper

Chiueh, TC & Ma, K-L 1997, 'A parallel pipelined renderer for time-varying volume data' Paper presented at 3rd International Symposium on Parallel Architectures, Algorithms, and Networks, I-SPAN 1997, Taipei, Taiwan, Province of China, 12/18/97 - 12/20/97, pp. 9-15. https://doi.org/10.1109/ISPAN.1997.645046
Chiueh TC, Ma K-L. A parallel pipelined renderer for time-varying volume data. 1997. Paper presented at 3rd International Symposium on Parallel Architectures, Algorithms, and Networks, I-SPAN 1997, Taipei, Taiwan, Province of China. https://doi.org/10.1109/ISPAN.1997.645046
Chiueh, Tzi Cier ; Ma, Kwan-Liu. / A parallel pipelined renderer for time-varying volume data. Paper presented at 3rd International Symposium on Parallel Architectures, Algorithms, and Networks, I-SPAN 1997, Taipei, Taiwan, Province of China.7 p.
@conference{38b6703b430d44e781e60f5c6732d5d7,
title = "A parallel pipelined renderer for time-varying volume data",
abstract = "This paper presents a strategy for efficiently rendering time-varying volume data on a distributed-memory parallel computer. Visualizing time-varying volume data take both large storage space and long computation time. Instead of employing all processors to render one volume at a time, a pipelined rendering approach partitions processors into groups so that multiple volumes can be rendered concurrently. The overall rendering time is greatly minimized because rendering is overlapped with I/O required to load the volume data sets. Moreover, parallelization overhead may be reduced as a result of partitioning the processors. We modify an existing parallel volume renderer to exploit various levels of rendering parallelism and to study how the partitioning of processors may lead to optimal rendering performance. We find that two factors affecting the overall execution time are resource utilization efficiency and pipeline startup latency. The optimal partitioning configuration is the one that balances these two factors. Tests on Intel Paragon computers show that in general optimal partitionings do exist for a given rendering task and result in 40-50{\%} saving in overall rendering time.",
author = "Chiueh, {Tzi Cier} and Kwan-Liu Ma",
year = "1997",
month = "1",
day = "1",
doi = "10.1109/ISPAN.1997.645046",
language = "English (US)",
pages = "9--15",
note = "3rd International Symposium on Parallel Architectures, Algorithms, and Networks, I-SPAN 1997 ; Conference date: 18-12-1997 Through 20-12-1997",

}

TY - CONF

T1 - A parallel pipelined renderer for time-varying volume data

AU - Chiueh, Tzi Cier

AU - Ma, Kwan-Liu

PY - 1997/1/1

Y1 - 1997/1/1

N2 - This paper presents a strategy for efficiently rendering time-varying volume data on a distributed-memory parallel computer. Visualizing time-varying volume data take both large storage space and long computation time. Instead of employing all processors to render one volume at a time, a pipelined rendering approach partitions processors into groups so that multiple volumes can be rendered concurrently. The overall rendering time is greatly minimized because rendering is overlapped with I/O required to load the volume data sets. Moreover, parallelization overhead may be reduced as a result of partitioning the processors. We modify an existing parallel volume renderer to exploit various levels of rendering parallelism and to study how the partitioning of processors may lead to optimal rendering performance. We find that two factors affecting the overall execution time are resource utilization efficiency and pipeline startup latency. The optimal partitioning configuration is the one that balances these two factors. Tests on Intel Paragon computers show that in general optimal partitionings do exist for a given rendering task and result in 40-50% saving in overall rendering time.

AB - This paper presents a strategy for efficiently rendering time-varying volume data on a distributed-memory parallel computer. Visualizing time-varying volume data take both large storage space and long computation time. Instead of employing all processors to render one volume at a time, a pipelined rendering approach partitions processors into groups so that multiple volumes can be rendered concurrently. The overall rendering time is greatly minimized because rendering is overlapped with I/O required to load the volume data sets. Moreover, parallelization overhead may be reduced as a result of partitioning the processors. We modify an existing parallel volume renderer to exploit various levels of rendering parallelism and to study how the partitioning of processors may lead to optimal rendering performance. We find that two factors affecting the overall execution time are resource utilization efficiency and pipeline startup latency. The optimal partitioning configuration is the one that balances these two factors. Tests on Intel Paragon computers show that in general optimal partitionings do exist for a given rendering task and result in 40-50% saving in overall rendering time.

UR - http://www.scopus.com/inward/record.url?scp=84862961852&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862961852&partnerID=8YFLogxK

U2 - 10.1109/ISPAN.1997.645046

DO - 10.1109/ISPAN.1997.645046

M3 - Paper

SP - 9

EP - 15

ER -