Out-of-core sort-first parallel rendering for cluster-based tiled displays

Wagner T. Corrêa, James T. Klosowski, Cláudio T. Silva

Research output: Contribution to journalArticle

Abstract

We present a sort-first parallel system for out-of-core rendering of large models on cluster-based tiled displays. The system renders high-resolution images of large models at interactive frame rates using off-the-shelf PCs with small memory. Given a model, we use an out-of-core preprocessing algorithm to build an on-disk hierarchical representation for the model. At run time, each PC renders the image for a display tile, using an out-of-core rendering approach that employs multiple threads to overlap rendering, visibility computation, and disk operations. The system can operate in approximate mode for real-time rendering, or in conservative mode for rendering with guaranteed accuracy. Running our system in approximate mode on a cluster of 16 PCs each with 512 MB of main memory, we are able to render 12-megapixel images of a 13-million-triangle model with 99.3% of accuracy at 10.8 frames per second. Rendering such a large model at high resolutions and interactive frame rates would typically require expensive high-end graphics hardware. Our results show that a cluster of inexpensive PCs is an attractive alternative to those high-end systems.

Original languageEnglish (US)
Pages (from-to)325-338
Number of pages14
JournalParallel Computing
Volume29
Issue number3
DOIs
StatePublished - Mar 2003

Fingerprint

Rendering
Sort
Display
Display devices
High Resolution
Model
Data storage equipment
Graphics Hardware
Parallel Systems
Tile
Image resolution
Visibility
Thread
Preprocessing
Overlap
Triangle
Real-time
Hardware
Alternatives

Keywords

  • Cluster of PCs
  • Out-of-core rendering
  • Parallel rendering

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Out-of-core sort-first parallel rendering for cluster-based tiled displays. / Corrêa, Wagner T.; Klosowski, James T.; Silva, Cláudio T.

In: Parallel Computing, Vol. 29, No. 3, 03.2003, p. 325-338.

Research output: Contribution to journalArticle

Corrêa, Wagner T. ; Klosowski, James T. ; Silva, Cláudio T. / Out-of-core sort-first parallel rendering for cluster-based tiled displays. In: Parallel Computing. 2003 ; Vol. 29, No. 3. pp. 325-338.
@article{5b1ac971d8184eecb4b8e1b5d141d383,
title = "Out-of-core sort-first parallel rendering for cluster-based tiled displays",
abstract = "We present a sort-first parallel system for out-of-core rendering of large models on cluster-based tiled displays. The system renders high-resolution images of large models at interactive frame rates using off-the-shelf PCs with small memory. Given a model, we use an out-of-core preprocessing algorithm to build an on-disk hierarchical representation for the model. At run time, each PC renders the image for a display tile, using an out-of-core rendering approach that employs multiple threads to overlap rendering, visibility computation, and disk operations. The system can operate in approximate mode for real-time rendering, or in conservative mode for rendering with guaranteed accuracy. Running our system in approximate mode on a cluster of 16 PCs each with 512 MB of main memory, we are able to render 12-megapixel images of a 13-million-triangle model with 99.3{\%} of accuracy at 10.8 frames per second. Rendering such a large model at high resolutions and interactive frame rates would typically require expensive high-end graphics hardware. Our results show that a cluster of inexpensive PCs is an attractive alternative to those high-end systems.",
keywords = "Cluster of PCs, Out-of-core rendering, Parallel rendering",
author = "Corr{\^e}a, {Wagner T.} and Klosowski, {James T.} and Silva, {Cl{\'a}udio T.}",
year = "2003",
month = "3",
doi = "10.1016/S0167-8191(02)00249-1",
language = "English (US)",
volume = "29",
pages = "325--338",
journal = "Parallel Computing",
issn = "0167-8191",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Out-of-core sort-first parallel rendering for cluster-based tiled displays

AU - Corrêa, Wagner T.

AU - Klosowski, James T.

AU - Silva, Cláudio T.

PY - 2003/3

Y1 - 2003/3

N2 - We present a sort-first parallel system for out-of-core rendering of large models on cluster-based tiled displays. The system renders high-resolution images of large models at interactive frame rates using off-the-shelf PCs with small memory. Given a model, we use an out-of-core preprocessing algorithm to build an on-disk hierarchical representation for the model. At run time, each PC renders the image for a display tile, using an out-of-core rendering approach that employs multiple threads to overlap rendering, visibility computation, and disk operations. The system can operate in approximate mode for real-time rendering, or in conservative mode for rendering with guaranteed accuracy. Running our system in approximate mode on a cluster of 16 PCs each with 512 MB of main memory, we are able to render 12-megapixel images of a 13-million-triangle model with 99.3% of accuracy at 10.8 frames per second. Rendering such a large model at high resolutions and interactive frame rates would typically require expensive high-end graphics hardware. Our results show that a cluster of inexpensive PCs is an attractive alternative to those high-end systems.

AB - We present a sort-first parallel system for out-of-core rendering of large models on cluster-based tiled displays. The system renders high-resolution images of large models at interactive frame rates using off-the-shelf PCs with small memory. Given a model, we use an out-of-core preprocessing algorithm to build an on-disk hierarchical representation for the model. At run time, each PC renders the image for a display tile, using an out-of-core rendering approach that employs multiple threads to overlap rendering, visibility computation, and disk operations. The system can operate in approximate mode for real-time rendering, or in conservative mode for rendering with guaranteed accuracy. Running our system in approximate mode on a cluster of 16 PCs each with 512 MB of main memory, we are able to render 12-megapixel images of a 13-million-triangle model with 99.3% of accuracy at 10.8 frames per second. Rendering such a large model at high resolutions and interactive frame rates would typically require expensive high-end graphics hardware. Our results show that a cluster of inexpensive PCs is an attractive alternative to those high-end systems.

KW - Cluster of PCs

KW - Out-of-core rendering

KW - Parallel rendering

UR - http://www.scopus.com/inward/record.url?scp=0037363022&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037363022&partnerID=8YFLogxK

U2 - 10.1016/S0167-8191(02)00249-1

DO - 10.1016/S0167-8191(02)00249-1

M3 - Article

AN - SCOPUS:0037363022

VL - 29

SP - 325

EP - 338

JO - Parallel Computing

JF - Parallel Computing

SN - 0167-8191

IS - 3

ER -