{"id":"https://openalex.org/W1974048680","doi":"https://doi.org/10.1145/2568058.2568068","title":"Comparing the performance of different x86 SIMD instruction sets for a medical imaging application on modern multi- and manycore chips","display_name":"Comparing the performance of different x86 SIMD instruction sets for a medical imaging application on modern multi- and manycore chips","publication_year":2014,"publication_date":"2014-02-16","ids":{"openalex":"https://openalex.org/W1974048680","doi":"https://doi.org/10.1145/2568058.2568068","mag":"1974048680"},"language":"en","primary_location":{"id":"doi:10.1145/2568058.2568068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2568058.2568068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Workshop on Programming models for SIMD/Vector processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1401.7494","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058862418","display_name":"Johannes Hofmann","orcid":"https://orcid.org/0000-0002-0667-2452"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Hofmann","raw_affiliation_strings":["University Erlangen-Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039308392","display_name":"Jan Treibig","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Treibig","raw_affiliation_strings":["University Erlangen-Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["University Erlangen-Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["University Erlangen-Nuremberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Erlangen-Nuremberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10378","display_name":"Advanced MRI Techniques and Applications","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8693692684173584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8486581444740295},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.8300700187683105},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.776914119720459},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6105970144271851},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5955548286437988},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5841435194015503},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5427193641662598},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.4838780164718628},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.4275369942188263},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.41878047585487366},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4180380702018738},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32142049074172974},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.17359063029289246},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08598372340202332},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.08295139670372009},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0776309072971344}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8693692684173584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486581444740295},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.8300700187683105},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.776914119720459},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6105970144271851},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5955548286437988},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5841435194015503},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5427193641662598},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.4838780164718628},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.4275369942188263},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.41878047585487366},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4180380702018738},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32142049074172974},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.17359063029289246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08598372340202332},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.08295139670372009},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0776309072971344},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2568058.2568068","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2568058.2568068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Workshop on Programming models for SIMD/Vector processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1401.7494","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1401.7494","pdf_url":"https://arxiv.org/pdf/1401.7494","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.754.4129","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.754.4129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1401.7494.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1401.7494","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1401.7494","pdf_url":"https://arxiv.org/pdf/1401.7494","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1961751213","https://openalex.org/W1972015875","https://openalex.org/W1997448249","https://openalex.org/W2029570992","https://openalex.org/W2055844022","https://openalex.org/W2067635581","https://openalex.org/W2082344075","https://openalex.org/W2253316886","https://openalex.org/W2949679561","https://openalex.org/W3103104567","https://openalex.org/W4299563552"],"related_works":["https://openalex.org/W2129537883","https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W3024308452","https://openalex.org/W4244894488","https://openalex.org/W4285390450","https://openalex.org/W2366442643","https://openalex.org/W4225987401","https://openalex.org/W4236526691","https://openalex.org/W2003690377"],"abstract_inverted_index":{"Single":[0],"Instruction,":[1],"Multiple":[2],"Data":[3],"(SIMD)":[4],"vectorization":[5,64],"is":[6,16,60,111],"a":[7,50,61,70,75],"major":[8],"driver":[9],"of":[10,34,38,74,88],"performance":[11,21,87],"in":[12,53],"current":[13],"architectures,":[14],"and":[15,98,121],"mandatory":[17],"for":[18,63,134],"achieving":[19],"good":[20],"with":[22],"codes":[23],"that":[24],"are":[25],"limited":[26],"by":[27,47],"instruction":[28],"throughput.":[29],"We":[30,84],"investigate":[31],"the":[32,39,86,114],"efficiency":[33],"different":[35],"SIMD-vectorized":[36],"implementations":[37,102,130],"RabbitCT":[40,42],"benchmark.":[41],"performs":[43],"3D":[44],"image":[45,82],"reconstruction":[46],"back":[48],"projection,":[49],"vital":[51],"operation":[52],"computed":[54],"tomography":[55],"applications.":[56],"The":[57],"underlying":[58],"algorithm":[59],"challenge":[62],"because":[65],"it":[66],"consists,":[67],"apart":[68],"from":[69],"streaming":[71],"part,":[72],"also":[73],"bilinear":[76],"interpolation":[77],"requiring":[78],"scattered":[79],"access":[80],"to":[81],"data.":[83],"analyze":[85],"SSE":[89],"(128":[90],"bit),":[91,94,97],"AVX":[92],"(256":[93,96],"AVX2":[95],"IMCI":[99],"(512":[100],"bit)":[101],"on":[103,113,118],"recent":[104],"Intel":[105,119],"x86":[106],"systems.":[107],"A":[108],"special":[109],"emphasis":[110],"put":[112],"vector":[115],"gather":[116],"implementation":[117],"Haswell":[120],"Knights":[122],"Corner":[123],"microarchitectures.":[124],"Finally":[125],"we":[126],"discuss":[127],"why":[128],"GPU":[129],"perform":[131],"much":[132],"better":[133],"this":[135],"specific":[136],"algorithm.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}