{"id":"https://openalex.org/W1935559531","doi":"https://doi.org/10.1177/1094342016668978","title":"An improved parallelism scheme for deterministic discrete ordinates transport","display_name":"An improved parallelism scheme for deterministic discrete ordinates transport","publication_year":2016,"publication_date":"2016-09-18","ids":{"openalex":"https://openalex.org/W1935559531","doi":"https://doi.org/10.1177/1094342016668978","mag":"1935559531"},"language":"en","primary_location":{"id":"doi:10.1177/1094342016668978","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1094342016668978","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1094342016668978","source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://journals.sagepub.com/doi/pdf/10.1177/1094342016668978","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047958284","display_name":"Tom Deakin","orcid":"https://orcid.org/0000-0002-6439-4171"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Tom Deakin","raw_affiliation_strings":["Department of Computer Science, University of Bristol, Bristol, UK","#N# 1Department of Computer Science, University of Bristol, Bristol, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"#N# 1Department of Computer Science, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020200003","display_name":"Simon McIntosh\u2010Smith","orcid":"https://orcid.org/0000-0002-5312-0378"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon McIntosh-Smith","raw_affiliation_strings":["Department of Computer Science, University of Bristol, Bristol, UK","Microelectronics"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]},{"raw_affiliation_string":"Microelectronics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028117617","display_name":"Matt Martineau","orcid":null},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matt Martineau","raw_affiliation_strings":["Department of Computer Science, University of Bristol, Bristol, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bristol, Bristol, UK","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005778020","display_name":"Wayne Gaudin","orcid":null},"institutions":[{"id":"https://openalex.org/I2802201010","display_name":"Atomic Weapons Establishment","ror":"https://ror.org/02gv4h649","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2802201010"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wayne Gaudin","raw_affiliation_strings":["High Performance Computing, UK Atomic Weapons Establishment, Aldermaston, UK","2High Performance Computing, UK Atomic Weapons Establishment, Aldermaston, UK"],"affiliations":[{"raw_affiliation_string":"High Performance Computing, UK Atomic Weapons Establishment, Aldermaston, UK","institution_ids":["https://openalex.org/I2802201010"]},{"raw_affiliation_string":"2High Performance Computing, UK Atomic Weapons Establishment, Aldermaston, UK","institution_ids":["https://openalex.org/I2802201010"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047958284"],"corresponding_institution_ids":["https://openalex.org/I36234482"],"apc_list":null,"apc_paid":null,"fwci":1.9301,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84205204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"32","issue":"4","first_page":"555","last_page":"569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8884847164154053},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8332719802856445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8166013956069946},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6658564805984497},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6654598116874695},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5777119994163513},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4619147777557373},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.45652735233306885},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4562245011329651},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4370502233505249},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.4190073013305664},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41169098019599915},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.3894844055175781},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3699341416358948},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08755072951316833}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8884847164154053},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8332719802856445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166013956069946},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6658564805984497},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6654598116874695},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5777119994163513},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4619147777557373},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.45652735233306885},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4562245011329651},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4370502233505249},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.4190073013305664},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41169098019599915},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3894844055175781},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3699341416358948},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08755072951316833},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/1094342016668978","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1094342016668978","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1094342016668978","source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:research-information.bris.ac.uk:openaire/2c460898-05ab-42cb-9f35-e249bf40780c","is_oa":true,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/2c460898-05ab-42cb-9f35-e249bf40780c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Deakin, T, McIntosh-Smith, S, Martineau, M & Gaudin, W 2018, 'An Improved Parallelism Scheme for Deterministic Discrete Ordinates Transport', International Journal of High Performance Computing Applications, vol. 32, no. 4, pp. 555-569. https://doi.org/10.1177/1094342016668978","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:research-information.bris.ac.uk:publications/2c460898-05ab-42cb-9f35-e249bf40780c","is_oa":true,"landing_page_url":null,"pdf_url":"https://research-information.bris.ac.uk/en/publications/2c460898-05ab-42cb-9f35-e249bf40780c","source":{"id":"https://openalex.org/S4306400895","display_name":"Bristol Research (University of Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I36234482","host_organization_name":"University of Bristol","host_organization_lineage":["https://openalex.org/I36234482"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.1177/1094342016668978","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1094342016668978","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1094342016668978","source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320360","display_name":"University of Bristol","ror":"https://ror.org/0524sp257"},{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1935559531.pdf","grobid_xml":"https://content.openalex.org/works/W1935559531.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1520966093","https://openalex.org/W1549057003","https://openalex.org/W1592795936","https://openalex.org/W1955124277","https://openalex.org/W2002555321","https://openalex.org/W2014555481","https://openalex.org/W2077828271","https://openalex.org/W2112121929","https://openalex.org/W2114124085","https://openalex.org/W2117689653","https://openalex.org/W2146331174","https://openalex.org/W2172331116","https://openalex.org/W2284274288","https://openalex.org/W2304564885","https://openalex.org/W2346028389","https://openalex.org/W2534432699","https://openalex.org/W2971869340","https://openalex.org/W2992161528","https://openalex.org/W4298156632"],"related_works":["https://openalex.org/W2739740241","https://openalex.org/W1974923383","https://openalex.org/W2085105049","https://openalex.org/W2475524688","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2981664121","https://openalex.org/W2796552083","https://openalex.org/W2949197156"],"abstract_inverted_index":{"In":[0],"this":[1,143,153],"paper":[2],"we":[3],"demonstrate":[4,57,167],"techniques":[5],"for":[6,47,88,120,150],"increasing":[7],"the":[8,35,48,61,70,79,121,131,135,140,168,179],"node-level":[9],"parallelism":[10],"of":[11,34,38,69,96,104,145,152],"a":[12,21,31,66,85,102,110,116],"deterministic":[13],"discrete":[14],"ordinates":[15],"neutral":[16],"particle":[17],"transport":[18,72,122],"algorithm":[19,73,81,99],"on":[20,109,170],"structured":[22],"mesh":[23],"to":[24,50,78,82,106,115,126,130,159,178],"exploit":[25],"many-core":[26,111],"technologies.":[27],"Transport":[28],"calculations":[29],"form":[30],"large":[32],"part":[33],"computational":[36],"workload":[37],"physical":[39],"simulations":[40,49],"and":[41,124,166],"so":[42],"good":[43],"performance":[44,169],"is":[45],"vital":[46],"complete":[51],"in":[52,134,163],"reasonable":[53],"time.":[54],"We":[55,91,155],"will":[56],"our":[58,97,161],"approach":[59],"utilizing":[60],"SNAP":[62],"mini-app,":[63],"which":[64,100],"gives":[65],"simplified":[67],"implementation":[68,95],"full":[71],"but":[74],"remains":[75],"similar":[76],"enough":[77],"real":[80],"act":[83],"as":[84],"useful":[86],"proxy":[87],"research":[89],"purposes.":[90],"present":[92],"an":[93,171],"OpenCL":[94],"improved":[98],"achieves":[101],"speedup":[103,146],"up":[105,125],"2.5":[107],"\u00d7":[108,128],"GPGPU":[112],"device":[113],"compared":[114,129,177],"state-of-the-art":[117],"multi-core":[118,132],"node":[119],"sweep,":[123],"4":[127],"CPUs":[133],"largest":[136],"GPU":[137],"enabled":[138],"supercomputer;":[139],"first":[141],"time":[142],"scale":[144],"has":[147],"been":[148],"achieved":[149],"algorithms":[151],"class.":[154],"then":[156],"discuss":[157],"ways":[158],"express":[160],"scheme":[162],"OpenMP":[164],"4.0":[165],"Intel":[172],"Knights":[173],"Corner":[174],"Xeon":[175],"Phi":[176],"original":[180],"scheme.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}