Load balancing strategies for ray tracing on parallel processors

Tong Yee Lee, C. S. Raghavendra, John B. Nicholas

研究成果: Paper

摘要

Ray tracing is one of the computer graphics techniques used to render high quality images. Unfortunately, ray tracing complex scenes can require large amounts of CPU time, making the technique impractical for everyday use. Since the ray tracing calculations that determine the values of individual pixels are independent, this appears to be an easy problem to parallelize and parallel algorithms have been proposed. However, pixel computation times can vary significantly, and naive attempts at parallelization give poor speedup due to load imbalance between the processors. The key to achieving high parallel efficiency is to ensure that the computational load is evenly balanced. In this paper, we propose two new load balancing schemes and evaluate the performance of ours for ray tracing on parallel processors. We term both new methods Local Distributed Control (LDC) and Global Distributed Control (GDC). Our new strategies are complementary: GDC performs well for high computational complexity images and LDC works well for low computational complexity images.

原文English
頁面177-181
頁數5
出版狀態Published - 1995 一月 1
事件Proceedings of the 1994 IEEE Region 10's 9th Annual International Conference (TENCON'94). Part 1 (of 2) - Singapore, Singapore
持續時間: 1994 八月 221994 八月 26

Other

OtherProceedings of the 1994 IEEE Region 10's 9th Annual International Conference (TENCON'94). Part 1 (of 2)
城市Singapore, Singapore
期間94-08-2294-08-26

指紋

Ray tracing
Resource allocation
Computational complexity
Pixels
Computer graphics
Parallel algorithms
Image quality
Program processors

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

引用此文

Lee, T. Y., Raghavendra, C. S., & Nicholas, J. B. (1995). Load balancing strategies for ray tracing on parallel processors. 177-181. 論文發表於 Proceedings of the 1994 IEEE Region 10's 9th Annual International Conference (TENCON'94). Part 1 (of 2), Singapore, Singapore, .
Lee, Tong Yee ; Raghavendra, C. S. ; Nicholas, John B. / Load balancing strategies for ray tracing on parallel processors. 論文發表於 Proceedings of the 1994 IEEE Region 10's 9th Annual International Conference (TENCON'94). Part 1 (of 2), Singapore, Singapore, .5 p.
@conference{0d826d4ea5d842c8a924777b6fe30182,
title = "Load balancing strategies for ray tracing on parallel processors",
abstract = "Ray tracing is one of the computer graphics techniques used to render high quality images. Unfortunately, ray tracing complex scenes can require large amounts of CPU time, making the technique impractical for everyday use. Since the ray tracing calculations that determine the values of individual pixels are independent, this appears to be an easy problem to parallelize and parallel algorithms have been proposed. However, pixel computation times can vary significantly, and naive attempts at parallelization give poor speedup due to load imbalance between the processors. The key to achieving high parallel efficiency is to ensure that the computational load is evenly balanced. In this paper, we propose two new load balancing schemes and evaluate the performance of ours for ray tracing on parallel processors. We term both new methods Local Distributed Control (LDC) and Global Distributed Control (GDC). Our new strategies are complementary: GDC performs well for high computational complexity images and LDC works well for low computational complexity images.",
author = "Lee, {Tong Yee} and Raghavendra, {C. S.} and Nicholas, {John B.}",
year = "1995",
month = "1",
day = "1",
language = "English",
pages = "177--181",
note = "Proceedings of the 1994 IEEE Region 10's 9th Annual International Conference (TENCON'94). Part 1 (of 2) ; Conference date: 22-08-1994 Through 26-08-1994",

}

Lee, TY, Raghavendra, CS & Nicholas, JB 1995, 'Load balancing strategies for ray tracing on parallel processors', 論文發表於 Proceedings of the 1994 IEEE Region 10's 9th Annual International Conference (TENCON'94). Part 1 (of 2), Singapore, Singapore, 94-08-22 - 94-08-26 頁 177-181.

Load balancing strategies for ray tracing on parallel processors. / Lee, Tong Yee; Raghavendra, C. S.; Nicholas, John B.

1995. 177-181 論文發表於 Proceedings of the 1994 IEEE Region 10's 9th Annual International Conference (TENCON'94). Part 1 (of 2), Singapore, Singapore, .

研究成果: Paper

TY - CONF

T1 - Load balancing strategies for ray tracing on parallel processors

AU - Lee, Tong Yee

AU - Raghavendra, C. S.

AU - Nicholas, John B.

PY - 1995/1/1

Y1 - 1995/1/1

N2 - Ray tracing is one of the computer graphics techniques used to render high quality images. Unfortunately, ray tracing complex scenes can require large amounts of CPU time, making the technique impractical for everyday use. Since the ray tracing calculations that determine the values of individual pixels are independent, this appears to be an easy problem to parallelize and parallel algorithms have been proposed. However, pixel computation times can vary significantly, and naive attempts at parallelization give poor speedup due to load imbalance between the processors. The key to achieving high parallel efficiency is to ensure that the computational load is evenly balanced. In this paper, we propose two new load balancing schemes and evaluate the performance of ours for ray tracing on parallel processors. We term both new methods Local Distributed Control (LDC) and Global Distributed Control (GDC). Our new strategies are complementary: GDC performs well for high computational complexity images and LDC works well for low computational complexity images.

AB - Ray tracing is one of the computer graphics techniques used to render high quality images. Unfortunately, ray tracing complex scenes can require large amounts of CPU time, making the technique impractical for everyday use. Since the ray tracing calculations that determine the values of individual pixels are independent, this appears to be an easy problem to parallelize and parallel algorithms have been proposed. However, pixel computation times can vary significantly, and naive attempts at parallelization give poor speedup due to load imbalance between the processors. The key to achieving high parallel efficiency is to ensure that the computational load is evenly balanced. In this paper, we propose two new load balancing schemes and evaluate the performance of ours for ray tracing on parallel processors. We term both new methods Local Distributed Control (LDC) and Global Distributed Control (GDC). Our new strategies are complementary: GDC performs well for high computational complexity images and LDC works well for low computational complexity images.

UR - http://www.scopus.com/inward/record.url?scp=0029208239&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029208239&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029208239

SP - 177

EP - 181

ER -

Lee TY, Raghavendra CS, Nicholas JB. Load balancing strategies for ray tracing on parallel processors. 1995. 論文發表於 Proceedings of the 1994 IEEE Region 10's 9th Annual International Conference (TENCON'94). Part 1 (of 2), Singapore, Singapore, .