Parallel On-Demand Hierarchy Construction on Contemporary GPUs

J 2016

Parallel On-Demand Hierarchy Construction on Contemporary GPUs

VINKLER, Marek, Vlastimil HAVRAN, Jiří BITTNER a Jiří SOCHOR

Základní údaje

Originální název

Parallel On-Demand Hierarchy Construction on Contemporary GPUs

Autoři

VINKLER, Marek (203 Česká republika, garant, domácí), Vlastimil HAVRAN (203 Česká republika), Jiří BITTNER (203 Česká republika) a Jiří SOCHOR (203 Česká republika, domácí)

Vydání

IEEE Transactions on Visualization and Computer Graphics, USA, IEEE, 2016, 1077-2626

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Impakt faktor

Impact factor: 2.840

Kód RIV

RIV/00216224:14330/16:00089132

Organizační jednotka

Fakulta informatiky

DOI

http://dx.doi.org/10.1109/TVCG.2015.2465898

UT WoS

000377475200010

Klíčová slova anglicky

ray tracing; GPU; bounding volume hierarchies; kd-trees; lazy build

Štítky

best1

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 27. 4. 2017 05:44, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

We present the first parallel on-demand spatial hierarchy construction algorithm targeting ray tracing on many-core processors such as GPUs. The method performs simultaneous ray traversal and spatial hierarchy construction focused on the parts of the data structure being traversed. The method is based on a versatile framework built around a task pool and runs entirely on the GPU. We show that the on-demand construction can improve rendering times compared to full hierarchy construction. We evaluate our method on both object (BVH) and space (kd-tree) subdivision data structures and compare them mutually. The on-demand method is particularly beneficial for rendering large scenes with high occlusion. We also present SAH kd-tree builder that outperforms previous state-of-the-art builders running on the GPU.

Citovat

VINKLER, Marek, Vlastimil HAVRAN, Jiří BITTNER a Jiří SOCHOR. Parallel On-Demand Hierarchy Construction on Contemporary GPUs. IEEE Transactions on Visualization and Computer Graphics. USA: IEEE, 2016, roč. 22, č. 7, s. 1886-1898. ISSN 1077-2626. Dostupné z: https://dx.doi.org/10.1109/TVCG.2015.2465898.

@article{1314762,
   author = {Vinkler, Marek and Havran, Vlastimil and Bittner, Jiří and Sochor, Jiří},
   article_location = {USA},
   article_number = {7},
   doi = {http://dx.doi.org/10.1109/TVCG.2015.2465898},
   keywords = {ray tracing; GPU; bounding volume hierarchies; kd-trees; lazy build},
   language = {eng},
   issn = {1077-2626},
   journal = {IEEE Transactions on Visualization and Computer Graphics},
   title = {Parallel On-Demand Hierarchy Construction on Contemporary GPUs},
   volume = {22},
   year = {2016}
}

TY  - JOUR
ID  - 1314762
AU  - Vinkler, Marek - Havran, Vlastimil - Bittner, Jiří - Sochor, Jiří
PY  - 2016
TI  - Parallel On-Demand Hierarchy Construction on Contemporary GPUs
JF  - IEEE Transactions on Visualization and Computer Graphics
VL  - 22
IS  - 7
SP  - 1886-1898
EP  - 1886-1898
PB  - IEEE
SN  - 10772626
KW  - ray tracing
KW  - GPU
KW  - bounding volume hierarchies
KW  - kd-trees
KW  - lazy build
N2  - We present the first parallel on-demand spatial hierarchy construction algorithm targeting ray tracing on many-core processors such as GPUs. The method performs simultaneous ray traversal and spatial hierarchy construction focused on the parts of the data structure being traversed. The method is based on a versatile framework built around a task pool and runs entirely on the GPU. We show that the on-demand construction can improve rendering times compared to full hierarchy construction. We evaluate our method on both object (BVH) and space (kd-tree) subdivision data structures and compare them mutually. The on-demand method is particularly beneficial for rendering large scenes with high occlusion. We also present SAH kd-tree builder that outperforms previous state-of-the-art builders running on the GPU.
ER  -

VINKLER, Marek, Vlastimil HAVRAN, Jiří BITTNER a Jiří SOCHOR. Parallel On-Demand Hierarchy Construction on Contemporary GPUs. \textit{IEEE Transactions on Visualization and Computer Graphics}. USA: IEEE, 2016, roč.~22, č.~7, s.~1886-1898. ISSN~1077-2626. Dostupné z: https://dx.doi.org/10.1109/TVCG.2015.2465898.

Podrobný výpis o publikaci