T&I Engine: Traversal and Intersection Engine for Hardware Accelerated Ray Tracing

Jae Ho Nah, Jeong Soo Park, Jin Woo Kim, Yun Hye Jung, Tack-Don Han, Chanmin Park, Woo Chan Park

Research output: Contribution to journalArticle

Abstract

Ray tracing naturally supports high-quality global illumination effects, but it is computationally costly. Traversal and intersection operations dominate the computation of ray tracing. To accelerate these two operations, we propose a hardware architecture integrating three novel approaches. First, we present an ordered depth-first layout and a traversal architecture using this layout to reduce the required memory bandwidth. Second, we propose a three-phase ray-triangle intersection architecture that takes advantage of early exit. Third, we propose a latency hiding architecture defined as the ray accumulation unit. Cycle-accurate simulation results indicate our architecture can achieve interactive distributed ray tracing.

Original languageEnglish
Pages (from-to)1-10
Number of pages10
JournalACM Transactions on Graphics
Volume30
Issue number6
DOIs
Publication statusPublished - 2011 Dec 1

Fingerprint

Ray tracing
Engines
Hardware
Lighting
Bandwidth
Data storage equipment

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design

Cite this

Nah, Jae Ho ; Park, Jeong Soo ; Kim, Jin Woo ; Jung, Yun Hye ; Han, Tack-Don ; Park, Chanmin ; Park, Woo Chan. / T&I Engine : Traversal and Intersection Engine for Hardware Accelerated Ray Tracing. In: ACM Transactions on Graphics. 2011 ; Vol. 30, No. 6. pp. 1-10.
@article{f31026f861514ace8404beddd6a856b6,
title = "T&I Engine: Traversal and Intersection Engine for Hardware Accelerated Ray Tracing",
abstract = "Ray tracing naturally supports high-quality global illumination effects, but it is computationally costly. Traversal and intersection operations dominate the computation of ray tracing. To accelerate these two operations, we propose a hardware architecture integrating three novel approaches. First, we present an ordered depth-first layout and a traversal architecture using this layout to reduce the required memory bandwidth. Second, we propose a three-phase ray-triangle intersection architecture that takes advantage of early exit. Third, we propose a latency hiding architecture defined as the ray accumulation unit. Cycle-accurate simulation results indicate our architecture can achieve interactive distributed ray tracing.",
author = "Nah, {Jae Ho} and Park, {Jeong Soo} and Kim, {Jin Woo} and Jung, {Yun Hye} and Tack-Don Han and Chanmin Park and Park, {Woo Chan}",
year = "2011",
month = "12",
day = "1",
doi = "10.1145/2070781.2024194",
language = "English",
volume = "30",
pages = "1--10",
journal = "ACM Transactions on Graphics",
issn = "0730-0301",
publisher = "Association for Computing Machinery (ACM)",
number = "6",

}

T&I Engine : Traversal and Intersection Engine for Hardware Accelerated Ray Tracing. / Nah, Jae Ho; Park, Jeong Soo; Kim, Jin Woo; Jung, Yun Hye; Han, Tack-Don; Park, Chanmin; Park, Woo Chan.

In: ACM Transactions on Graphics, Vol. 30, No. 6, 01.12.2011, p. 1-10.

Research output: Contribution to journalArticle

TY - JOUR

T1 - T&I Engine

T2 - Traversal and Intersection Engine for Hardware Accelerated Ray Tracing

AU - Nah, Jae Ho

AU - Park, Jeong Soo

AU - Kim, Jin Woo

AU - Jung, Yun Hye

AU - Han, Tack-Don

AU - Park, Chanmin

AU - Park, Woo Chan

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Ray tracing naturally supports high-quality global illumination effects, but it is computationally costly. Traversal and intersection operations dominate the computation of ray tracing. To accelerate these two operations, we propose a hardware architecture integrating three novel approaches. First, we present an ordered depth-first layout and a traversal architecture using this layout to reduce the required memory bandwidth. Second, we propose a three-phase ray-triangle intersection architecture that takes advantage of early exit. Third, we propose a latency hiding architecture defined as the ray accumulation unit. Cycle-accurate simulation results indicate our architecture can achieve interactive distributed ray tracing.

AB - Ray tracing naturally supports high-quality global illumination effects, but it is computationally costly. Traversal and intersection operations dominate the computation of ray tracing. To accelerate these two operations, we propose a hardware architecture integrating three novel approaches. First, we present an ordered depth-first layout and a traversal architecture using this layout to reduce the required memory bandwidth. Second, we propose a three-phase ray-triangle intersection architecture that takes advantage of early exit. Third, we propose a latency hiding architecture defined as the ray accumulation unit. Cycle-accurate simulation results indicate our architecture can achieve interactive distributed ray tracing.

UR - http://www.scopus.com/inward/record.url?scp=85024262757&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024262757&partnerID=8YFLogxK

U2 - 10.1145/2070781.2024194

DO - 10.1145/2070781.2024194

M3 - Article

AN - SCOPUS:85024262757

VL - 30

SP - 1

EP - 10

JO - ACM Transactions on Graphics

JF - ACM Transactions on Graphics

SN - 0730-0301

IS - 6

ER -