schliessen

Filtern

 

Bibliotheken

Coherent Photon Mapping on the Intel MIC Architecture

Photon mapping is a global illumination algorithm which is composed of two steps: photon tracing and photon searching. During photon searching step, each shading point needs to search the photon-tree to find k-neighbouring photons for reflected radiance estimation. As the number of shading points an... Full description

Journal Title: Journal of computer science and technology 2015, Vol.30 (3), p.519-527
Main Author: 康春萌 王璐 王佩 徐延宁 孟祥旭
Format: Electronic Article Electronic Article
Language: English
Subjects:
MIC
R&D
Publisher: New York: Springer US
ID: ISSN: 1000-9000
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: cdi_wanfang_journals_jsjkxjsxb_e201503009
title: Coherent Photon Mapping on the Intel MIC Architecture
format: Article
creator:
  • 康春萌 王璐 王佩 徐延宁 孟祥旭
subjects:
  • Algorithms
  • Analysis
  • Artificial Intelligence
  • Clusters
  • Computer Science
  • Computer simulation
  • Data Structures and Information Theory
  • general
  • Illumination
  • Image processing systems
  • Information Systems Applications (incl.Internet)
  • Light
  • Mapping
  • MIC
  • Multiprocessing
  • Parallel processing
  • Photons
  • R&D
  • Radiance
  • Regular Paper
  • Research & development
  • Searching
  • Shading
  • Software Engineering
  • Studies
  • Theory of Computation
  • 单指令多数据
  • 搜索算法
  • 英特尔
ispartof: Journal of computer science and technology, 2015, Vol.30 (3), p.519-527
description: Photon mapping is a global illumination algorithm which is composed of two steps: photon tracing and photon searching. During photon searching step, each shading point needs to search the photon-tree to find k-neighbouring photons for reflected radiance estimation. As the number of shading points and the size of photon-tree are dramatically large, the photon searching step is time consuming. We propose a parallel photon searching algorithm by using radiance estimation approach for coherent shading points on the Intel Many Integrated Core (MIC) Architecture. In order to efficiently use single instruction multiple data (SIMD) units, shading points are clustered by similarity first (every cluster contains 16 shading-points), and an initial neighbouring scope is searched from the photon-tree for each cluster. Then we use 16-wide SIMD units by performing k-NN searching from the initial neighbouring scope for those 16 shading-points in a cluster in parallel. We use the method to simulate some global illumination scenes on Intel Xeon processors and Intel Xeon Phi^TM coprocessors. The comparison results with existing photon mapping techniques indicate that our method gives significant improvement in speed with the same accuracy.
language: eng
source:
identifier: ISSN: 1000-9000
fulltext: no_fulltext
issn:
  • 1000-9000
  • 1860-4749
url: Link


@attributes
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
RANK2.2626605
LOCALfalse
PrimoNMBib
record
control
sourceidwanfang_jour_proqu
recordidTN_cdi_wanfang_journals_jsjkxjsxb_e201503009
sourceformatXML
sourcesystemPC
galeidA412447239
cqvip_id664786615
wanfj_idjsjkxjsxb_e201503009
sourcerecordidjsjkxjsxb_e201503009
originalsourceidFETCH-LOGICAL-c3109-2aba8731ba476bd57e89cd7bc5b22f4b8fb203d4d3faf5fa5c8e90890128b4500
addsrcrecordideNp9kU1r3DAQhkVpoemmP6A30156qJORrC8fl6UfCwntITkLSZb8Ua-0kbw0_ffV4hBKD0UwGobnfWeGQegdhisMIK4zxk0LNWBWY0ZJjV-gCyw51FTQ9mXJAaBuS3iN3uQ8ATQCKL1AbBcHl1xYqh9DXGKobvXxOIa-KukyuGofFjdXt_tdtU12GBdnl1Nyl-iV13N2b5_-Dbr_8vlu962--f51v9ve1LbB0NZEGy1Fg42mgpuOCSdb2wljmSHEUyO9IdB0tGu89sxrZqVrQbaAiTSUAWzQp9X3lw5eh15N8ZRC6aimPP18nPKjUY6UpaEBaAv-ccWPKT6cXF7UYczWzbMOLp6ywgIwcC6JLOiHf9Bna8yFFMWS8UJdrVSvZ6fG4OOStC2vc4fRxuD8WOpbigmlgjTnCfAqsCnmnJxXxzQedPqtMKjzodR6KFVmVudDleIGkVWTCxt6l_4a5T-i90-Nhhj6h6J77sQ5FZLzssEf5BOdyw
sourcetypeAggregation Database
isCDItrue
recordtypearticle
pqid1678715056
display
typearticle
titleCoherent Photon Mapping on the Intel MIC Architecture
creator康春萌 王璐 王佩 徐延宁 孟祥旭
creatorcontrib康春萌 王璐 王佩 徐延宁 孟祥旭
descriptionPhoton mapping is a global illumination algorithm which is composed of two steps: photon tracing and photon searching. During photon searching step, each shading point needs to search the photon-tree to find k-neighbouring photons for reflected radiance estimation. As the number of shading points and the size of photon-tree are dramatically large, the photon searching step is time consuming. We propose a parallel photon searching algorithm by using radiance estimation approach for coherent shading points on the Intel Many Integrated Core (MIC) Architecture. In order to efficiently use single instruction multiple data (SIMD) units, shading points are clustered by similarity first (every cluster contains 16 shading-points), and an initial neighbouring scope is searched from the photon-tree for each cluster. Then we use 16-wide SIMD units by performing k-NN searching from the initial neighbouring scope for those 16 shading-points in a cluster in parallel. We use the method to simulate some global illumination scenes on Intel Xeon processors and Intel Xeon Phi^TM coprocessors. The comparison results with existing photon mapping techniques indicate that our method gives significant improvement in speed with the same accuracy.
identifier
0ISSN: 1000-9000
1EISSN: 1860-4749
2DOI: 10.1007/s11390-015-1542-1
languageeng
publisherNew York: Springer US
subjectAlgorithms ; Analysis ; Artificial Intelligence ; Clusters ; Computer Science ; Computer simulation ; Data Structures and Information Theory ; general ; Illumination ; Image processing systems ; Information Systems Applications (incl.Internet) ; Light ; Mapping ; MIC ; Multiprocessing ; Parallel processing ; Photons ; R&D ; Radiance ; Regular Paper ; Research & development ; Searching ; Shading ; Software Engineering ; Studies ; Theory of Computation ; 单指令多数据 ; 搜索算法 ; 英特尔
ispartofJournal of computer science and technology, 2015, Vol.30 (3), p.519-527
rights
0Springer Science+Business Media New York 2015
1COPYRIGHT 2015 Springer
2Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
lds50peer_reviewed
citesFETCH-LOGICAL-c3109-2aba8731ba476bd57e89cd7bc5b22f4b8fb203d4d3faf5fa5c8e90890128b4500
links
openurl$$Topenurl_article
thumbnail$$Uhttp://image.cqvip.com/vip1000/qk/85226X/85226X.jpg
search
creatorcontrib康春萌 王璐 王佩 徐延宁 孟祥旭
title
0Coherent Photon Mapping on the Intel MIC Architecture
1Journal of computer science and technology
addtitle
0J. Comput. Sci. Technol
1Journal of Computer Science and Technology
descriptionPhoton mapping is a global illumination algorithm which is composed of two steps: photon tracing and photon searching. During photon searching step, each shading point needs to search the photon-tree to find k-neighbouring photons for reflected radiance estimation. As the number of shading points and the size of photon-tree are dramatically large, the photon searching step is time consuming. We propose a parallel photon searching algorithm by using radiance estimation approach for coherent shading points on the Intel Many Integrated Core (MIC) Architecture. In order to efficiently use single instruction multiple data (SIMD) units, shading points are clustered by similarity first (every cluster contains 16 shading-points), and an initial neighbouring scope is searched from the photon-tree for each cluster. Then we use 16-wide SIMD units by performing k-NN searching from the initial neighbouring scope for those 16 shading-points in a cluster in parallel. We use the method to simulate some global illumination scenes on Intel Xeon processors and Intel Xeon Phi^TM coprocessors. The comparison results with existing photon mapping techniques indicate that our method gives significant improvement in speed with the same accuracy.
subject
0Algorithms
1Analysis
2Artificial Intelligence
3Clusters
4Computer Science
5Computer simulation
6Data Structures and Information Theory
7general
8Illumination
9Image processing systems
10Information Systems Applications (incl.Internet)
11Light
12Mapping
13MIC
14Multiprocessing
15Parallel processing
16Photons
17R&D
18Radiance
19Regular Paper
20Research & development
21Searching
22Shading
23Software Engineering
24Studies
25Theory of Computation
26单指令多数据
27搜索算法
28英特尔
issn
01000-9000
11860-4749
fulltextfalse
rsrctypearticle
creationdate2015
recordtypearticle
recordideNp9kU1r3DAQhkVpoemmP6A30156qJORrC8fl6UfCwntITkLSZb8Ua-0kbw0_ffV4hBKD0UwGobnfWeGQegdhisMIK4zxk0LNWBWY0ZJjV-gCyw51FTQ9mXJAaBuS3iN3uQ8ATQCKL1AbBcHl1xYqh9DXGKobvXxOIa-KukyuGofFjdXt_tdtU12GBdnl1Nyl-iV13N2b5_-Dbr_8vlu962--f51v9ve1LbB0NZEGy1Fg42mgpuOCSdb2wljmSHEUyO9IdB0tGu89sxrZqVrQbaAiTSUAWzQp9X3lw5eh15N8ZRC6aimPP18nPKjUY6UpaEBaAv-ccWPKT6cXF7UYczWzbMOLp6ywgIwcC6JLOiHf9Bna8yFFMWS8UJdrVSvZ6fG4OOStC2vc4fRxuD8WOpbigmlgjTnCfAqsCnmnJxXxzQedPqtMKjzodR6KFVmVudDleIGkVWTCxt6l_4a5T-i90-Nhhj6h6J77sQ5FZLzssEf5BOdyw
startdate2015
enddate2015
creator康春萌 王璐 王佩 徐延宁 孟祥旭
general
0Springer US
1Springer
2Springer Nature B.V
3School of Computer Science and Technology, Shandong University, Jinan 250101, China%Engineering Research Center of Digital Media Technology, Ministry of Education, Jinan 250101, China
scope
02RA
192L
2CQIGP
3W92
4~WA
5AAYXX
6CITATION
7BSHEE
83V.
97SC
107WY
117WZ
127XB
1387Z
148AL
158FD
168FE
178FG
188FK
198FL
20ABUWG
21ARAPS
22AZQEC
23BENPR
24BEZIV
25BGLVJ
26DWQXO
27FRNLG
28F~G
29GNUQQ
30HCIFZ
31JQ2
32K60
33K6~
34K7-
35L.-
36L7M
37L~C
38L~D
39M0C
40M0N
41P5Z
42P62
43PQBIZ
44PQBZA
45PQEST
46PQQKQ
47PQUKI
48PRINS
49PYYUZ
50Q9U
517SP
522B.
534A8
5492I
5593N
56PSX
57TCJ
sort
creationdate2015
titleCoherent Photon Mapping on the Intel MIC Architecture
author康春萌 王璐 王佩 徐延宁 孟祥旭
facets
frbrtype5
frbrgroupidcdi_FETCH-LOGICAL-c3109-2aba8731ba476bd57e89cd7bc5b22f4b8fb203d4d3faf5fa5c8e90890128b4500
rsrctypearticles
prefilterarticles
languageeng
creationdate2015
topic
0Algorithms
1Analysis
2Artificial Intelligence
3Clusters
4Computer Science
5Computer simulation
6Data Structures and Information Theory
7general
8Illumination
9Image processing systems
10Information Systems Applications (incl.Internet)
11Light
12Mapping
13MIC
14Multiprocessing
15Parallel processing
16Photons
17R&D
18Radiance
19Regular Paper
20Research & development
21Searching
22Shading
23Software Engineering
24Studies
25Theory of Computation
26单指令多数据
27搜索算法
28英特尔
toplevelpeer_reviewed
creatorcontrib康春萌 王璐 王佩 徐延宁 孟祥旭
collection
0中文科技期刊数据库
1中文科技期刊数据库-CALIS站点
2中文科技期刊数据库-7.0平台
3中文科技期刊数据库-工程技术
4中文科技期刊数据库- 镜像站点
5CrossRef
6Academic OneFile (A&I only)
7ProQuest Central (Corporate)
8Computer and Information Systems Abstracts
9ABI/INFORM Collection
10ABI/INFORM Global (PDF only)
11ProQuest Central (purchase pre-March 2016)
12ABI/INFORM Global (Alumni Edition)
13Computing Database (Alumni Edition)
14Technology Research Database
15ProQuest SciTech Collection
16ProQuest Technology Collection
17ProQuest Central (Alumni) (purchase pre-March 2016)
18ABI/INFORM Collection (Alumni Edition)
19ProQuest Central (Alumni Edition)
20Advanced Technologies & Aerospace Collection
21ProQuest Central Essentials
22ProQuest Central
23Business Premium Collection
24Technology Collection
25ProQuest Central Korea
26Business Premium Collection (Alumni)
27ABI/INFORM Global (Corporate)
28ProQuest Central Student
29SciTech Premium Collection
30ProQuest Computer Science Collection
31ProQuest Business Collection (Alumni Edition)
32ProQuest Business Collection
33Computer Science Database
34ABI/INFORM Professional Advanced
35Advanced Technologies Database with Aerospace
36Computer and Information Systems Abstracts – Academic
37Computer and Information Systems Abstracts Professional
38ABI/INFORM Global
39Computing Database
40Advanced Technologies & Aerospace Database
41ProQuest Advanced Technologies & Aerospace Collection
42ProQuest One Business
43ProQuest One Business (Alumni)
44ProQuest One Academic Eastern Edition
45ProQuest One Academic
46ProQuest One Academic UKI Edition
47ProQuest Central China
48ABI/INFORM Collection China
49ProQuest Central Basic
50Electronics & Communications Abstracts
51Wanfang Data Journals - Hong Kong
52WANFANG Data Centre
53Wanfang Data Journals
54万方数据期刊 - 香港版
55China Online Journals (COJ)
56China Online Journals (COJ)
jtitleJournal of computer science and technology
delivery
delcategoryRemote Search Resource
fulltextno_fulltext
addata
au康春萌 王璐 王佩 徐延宁 孟祥旭
formatjournal
genrearticle
ristypeJOUR
atitleCoherent Photon Mapping on the Intel MIC Architecture
jtitleJournal of computer science and technology
stitleJ. Comput. Sci. Technol
addtitleJournal of Computer Science and Technology
date2015
risdate2015
volume30
issue3
spage519
epage527
pages519-527
issn1000-9000
eissn1860-4749
notes
0Chun-Meng Kang, Lu Wang, Pei Wang, Yan-Ning Xu, Xiang-Xu Meng ( 1School of Computer Science and Technology, Shandong University, Jinan 250101, China 2Engineering Research Center of Digital Media Technology, Ministry of Education, Jinan 250101, China 3Software College, Shandong University, Jinan 250101, China)
111-2296/TP
2Photon mapping is a global illumination algorithm which is composed of two steps: photon tracing and photon searching. During photon searching step, each shading point needs to search the photon-tree to find k-neighbouring photons for reflected radiance estimation. As the number of shading points and the size of photon-tree are dramatically large, the photon searching step is time consuming. We propose a parallel photon searching algorithm by using radiance estimation approach for coherent shading points on the Intel Many Integrated Core (MIC) Architecture. In order to efficiently use single instruction multiple data (SIMD) units, shading points are clustered by similarity first (every cluster contains 16 shading-points), and an initial neighbouring scope is searched from the photon-tree for each cluster. Then we use 16-wide SIMD units by performing k-NN searching from the initial neighbouring scope for those 16 shading-points in a cluster in parallel. We use the method to simulate some global illumination scenes on Intel Xeon processors and Intel Xeon Phi^TM coprocessors. The comparison results with existing photon mapping techniques indicate that our method gives significant improvement in speed with the same accuracy.
3photon mapping, parallel processing, SIMD
abstractPhoton mapping is a global illumination algorithm which is composed of two steps: photon tracing and photon searching. During photon searching step, each shading point needs to search the photon-tree to find k-neighbouring photons for reflected radiance estimation. As the number of shading points and the size of photon-tree are dramatically large, the photon searching step is time consuming. We propose a parallel photon searching algorithm by using radiance estimation approach for coherent shading points on the Intel Many Integrated Core (MIC) Architecture. In order to efficiently use single instruction multiple data (SIMD) units, shading points are clustered by similarity first (every cluster contains 16 shading-points), and an initial neighbouring scope is searched from the photon-tree for each cluster. Then we use 16-wide SIMD units by performing k-NN searching from the initial neighbouring scope for those 16 shading-points in a cluster in parallel. We use the method to simulate some global illumination scenes on Intel Xeon processors and Intel Xeon Phi^TM coprocessors. The comparison results with existing photon mapping techniques indicate that our method gives significant improvement in speed with the same accuracy.
copNew York
pubSpringer US
doi10.1007/s11390-015-1542-1