{"id":"https://openalex.org/W2294933397","doi":"https://doi.org/10.1109/pact.2015.32","title":"Throttling Automatic Vectorization: When Less is More","display_name":"Throttling Automatic Vectorization: When Less is More","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2294933397","doi":"https://doi.org/10.1109/pact.2015.32","mag":"2294933397"},"language":"en","primary_location":{"id":"doi:10.1109/pact.2015.32","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2015.32","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Parallel Architecture and Compilation (PACT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041672444","display_name":"Vasileios Porpodas","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Vasileios Porpodas","raw_affiliation_strings":["Computer Laboratory, University of Cambridge"],"affiliations":[{"raw_affiliation_string":"Computer Laboratory, University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047443783","display_name":"Timothy M. Jones","orcid":"https://orcid.org/0000-0002-4114-7661"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Timothy M. Jones","raw_affiliation_strings":["Computer Laboratory, University of Cambridge"],"affiliations":[{"raw_affiliation_string":"Computer Laboratory, University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041672444"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":4.2878,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94498661,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"432","last_page":"444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9966999888420105,"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/simd","display_name":"SIMD","score":0.8791321516036987},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8533621430397034},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.7973319292068481},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7490266561508179},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7393447160720825},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5006022453308105},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.43016231060028076},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3593935966491699},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.28209537267684937},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22217214107513428}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8791321516036987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8533621430397034},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7973319292068481},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7490266561508179},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7393447160720825},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5006022453308105},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.43016231060028076},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3593935966491699},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28209537267684937},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22217214107513428}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pact.2015.32","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2015.32","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on Parallel Architecture and Compilation (PACT)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.727.8384","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.727.8384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cl.cam.ac.uk/%7Evp331/papers/tslp_pact2015.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G3661743248","display_name":null,"funder_award_id":"EP/K026399/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7609657460","display_name":null,"funder_award_id":"EP/J016284/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W196281274","https://openalex.org/W1488308073","https://openalex.org/W1533942910","https://openalex.org/W1966324811","https://openalex.org/W1966691503","https://openalex.org/W1975594295","https://openalex.org/W2011393414","https://openalex.org/W2013156670","https://openalex.org/W2038328339","https://openalex.org/W2043555680","https://openalex.org/W2047937237","https://openalex.org/W2054103475","https://openalex.org/W2079834329","https://openalex.org/W2090268225","https://openalex.org/W2099404643","https://openalex.org/W2104378884","https://openalex.org/W2111394443","https://openalex.org/W2112121929","https://openalex.org/W2112482891","https://openalex.org/W2118031182","https://openalex.org/W2121176848","https://openalex.org/W2122060420","https://openalex.org/W2124273985","https://openalex.org/W2127324789","https://openalex.org/W2135736783","https://openalex.org/W2144481293","https://openalex.org/W2153185479","https://openalex.org/W2155503253","https://openalex.org/W2167639788","https://openalex.org/W3016220765","https://openalex.org/W3145750999","https://openalex.org/W4235055160","https://openalex.org/W4246166885","https://openalex.org/W4255465399","https://openalex.org/W6632112944","https://openalex.org/W6670344032"],"related_works":["https://openalex.org/W32529763","https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W3024308452","https://openalex.org/W4244894488","https://openalex.org/W4285390450","https://openalex.org/W2979513934","https://openalex.org/W2111180768","https://openalex.org/W2366442643","https://openalex.org/W2787898679"],"abstract_inverted_index":{"SIMD":[0,35],"vectors":[1,84],"are":[2],"widely":[3],"adopted":[4],"in":[5,71,227],"modern":[6],"general":[7],"purpose":[8],"processors":[9],"as":[10],"they":[11],"can":[12],"boost":[13],"performance":[14,203],"and":[15,37,45,68,88,223],"energy":[16],"efficiency":[17],"for":[18,27,110],"certain":[19],"applications.":[20],"Compiler-based":[21],"automatic":[22,60],"vectorization":[23,52,61,132,179,189],"is":[24,54,69,106,120,129,195],"one":[25],"approach":[26],"generating":[28],"codethat":[29],"makes":[30],"efficient":[31],"use":[32],"of":[33,41,59,153,207],"the":[34,39,55,90,111,123,135,150,155,183,228],"units,":[36],"has":[38,115],"benefit":[40],"avoiding":[42],"hand":[43],"development":[44],"platform-specific":[46],"optimizations.":[47],"The":[48,75,145],"Superword-Level":[49],"Parallelism":[50],"(SLP)":[51],"algorithm":[53,78,180],"most":[56],"well-known":[57],"implementation":[58],"when":[62],"starting":[63,85],"from":[64,86,140],"straight-line":[65],"scalar":[66,81,141],"code,":[67],"implemented":[70],"several":[72],"major":[73],"compilers.":[74],"existing":[76],"SLP":[77,175,218],"greedily":[79],"packs":[80],"instructions":[82],"into":[83,143],"stores":[87],"traversing":[89],"data":[91,139],"dependence":[92],"graph":[93,113,124,156,185],"upwards":[94],"until":[95],"it":[96],"reaches":[97],"loads":[98],"or":[99],"non-vectorizable":[100],"instructions.":[101],"Choosing":[102],"whether":[103],"to":[104,131,134,137,168,186,190,217,225],"vectorize":[105],"a":[107,177,205],"one-off":[108],"decision":[109,146],"whole":[112],"that":[114,128,181,200],"been":[116],"generated.":[117],"This,":[118],"however,":[119],"sub-optimal":[121],"because":[122],"may":[125],"contain":[126],"code":[127],"harmful":[130,160],"due":[133],"need":[136],"move":[138],"registers":[142],"vectors.":[144],"does":[147],"not":[148],"consider":[149],"potential":[151],"benefits":[152],"throttling":[154],"by":[157,172,219],"removing":[158],"this":[159,163,170,194],"code.":[161],"In":[162],"work":[164],"we":[165],"propose":[166],"asolution":[167],"overcome":[169],"limitation":[171],"introducing":[173],"Throttled":[174],"(TSLP),":[176],"novel":[178],"finds":[182],"optimal":[184],"vectorize,":[187],"forcing":[188],"stop":[191],"earlier":[192],"whenever":[193],"beneficial.":[196],"Our":[197],"experiments":[198],"show":[199],"TSLP":[201],"improves":[202],"across":[204],"number":[206],"kernels":[208],"extractedfrom":[209],"widely-used":[210],"benchmark":[211],"suites,":[212],"decreasing":[213],"execution":[214],"time":[215],"compared":[216],"9%":[220],"on":[221],"average":[222],"up":[224],"14%":[226],"best":[229],"case.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}