We propose a novel compositing pipeline and a dynamic load balancing technique for volume rendering which utilizes a two-layered group structure to achieve effective and scalable load balancing. The technique enables each process to render data from non-contiguous regions of the volume with minimal impact on the total render time. We demonstrate the effectiveness of the proposed technique by performing a set of experiments on a modern GPU cluster. The experiments show that using the technique results in up to a 35.7% lower worst-case memory usage as compared to a dynamic k-d tree load balancing technique, whilst simultaneously achieving similar or higher render performance. The proposed technique was also able to lower the amount of transferred data during the load balancing stage by up to 72.2%. The technique has the potential to be used in many scenarios where other dynamic load balancing techniques have proved to be inadequate, such as during large-scale visualization.
Marcus WALLDEN
Osaka University
Stefano MARKIDIS
KTH Royal University of Technology
Masao OKITA
Osaka University
Fumihiko INO
Osaka University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Marcus WALLDEN, Stefano MARKIDIS, Masao OKITA, Fumihiko INO, "Memory Efficient Load Balancing for Distributed Large-Scale Volume Rendering Using a Two-Layered Group Structure" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 12, pp. 2306-2316, December 2019, doi: 10.1587/transinf.2019PAP0003.
Abstract: We propose a novel compositing pipeline and a dynamic load balancing technique for volume rendering which utilizes a two-layered group structure to achieve effective and scalable load balancing. The technique enables each process to render data from non-contiguous regions of the volume with minimal impact on the total render time. We demonstrate the effectiveness of the proposed technique by performing a set of experiments on a modern GPU cluster. The experiments show that using the technique results in up to a 35.7% lower worst-case memory usage as compared to a dynamic k-d tree load balancing technique, whilst simultaneously achieving similar or higher render performance. The proposed technique was also able to lower the amount of transferred data during the load balancing stage by up to 72.2%. The technique has the potential to be used in many scenarios where other dynamic load balancing techniques have proved to be inadequate, such as during large-scale visualization.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019PAP0003/_p
Copy
@ARTICLE{e102-d_12_2306,
author={Marcus WALLDEN, Stefano MARKIDIS, Masao OKITA, Fumihiko INO, },
journal={IEICE TRANSACTIONS on Information},
title={Memory Efficient Load Balancing for Distributed Large-Scale Volume Rendering Using a Two-Layered Group Structure},
year={2019},
volume={E102-D},
number={12},
pages={2306-2316},
abstract={We propose a novel compositing pipeline and a dynamic load balancing technique for volume rendering which utilizes a two-layered group structure to achieve effective and scalable load balancing. The technique enables each process to render data from non-contiguous regions of the volume with minimal impact on the total render time. We demonstrate the effectiveness of the proposed technique by performing a set of experiments on a modern GPU cluster. The experiments show that using the technique results in up to a 35.7% lower worst-case memory usage as compared to a dynamic k-d tree load balancing technique, whilst simultaneously achieving similar or higher render performance. The proposed technique was also able to lower the amount of transferred data during the load balancing stage by up to 72.2%. The technique has the potential to be used in many scenarios where other dynamic load balancing techniques have proved to be inadequate, such as during large-scale visualization.},
keywords={},
doi={10.1587/transinf.2019PAP0003},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - Memory Efficient Load Balancing for Distributed Large-Scale Volume Rendering Using a Two-Layered Group Structure
T2 - IEICE TRANSACTIONS on Information
SP - 2306
EP - 2316
AU - Marcus WALLDEN
AU - Stefano MARKIDIS
AU - Masao OKITA
AU - Fumihiko INO
PY - 2019
DO - 10.1587/transinf.2019PAP0003
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2019
AB - We propose a novel compositing pipeline and a dynamic load balancing technique for volume rendering which utilizes a two-layered group structure to achieve effective and scalable load balancing. The technique enables each process to render data from non-contiguous regions of the volume with minimal impact on the total render time. We demonstrate the effectiveness of the proposed technique by performing a set of experiments on a modern GPU cluster. The experiments show that using the technique results in up to a 35.7% lower worst-case memory usage as compared to a dynamic k-d tree load balancing technique, whilst simultaneously achieving similar or higher render performance. The proposed technique was also able to lower the amount of transferred data during the load balancing stage by up to 72.2%. The technique has the potential to be used in many scenarios where other dynamic load balancing techniques have proved to be inadequate, such as during large-scale visualization.
ER -