{"id":"https://openalex.org/W1973806083","doi":"https://doi.org/10.1145/2567938","title":"HARP","display_name":"HARP","publication_year":2014,"publication_date":"2014-03-01","ids":{"openalex":"https://openalex.org/W1973806083","doi":"https://doi.org/10.1145/2567938","mag":"1973806083"},"language":"en","primary_location":{"id":"doi:10.1145/2567938","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2567938","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-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/A5049161926","display_name":"Ahmad Lashgar","orcid":"https://orcid.org/0000-0003-4838-8895"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ahmad Lashgar","raw_affiliation_strings":["University of Tehran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091782280","display_name":"Ahmad Khonsari","orcid":"https://orcid.org/0000-0002-8669-4001"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ahmad Khonsari","raw_affiliation_strings":["University of Tehran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000153604","display_name":"Amirali Baniasadi","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amirali Baniasadi","raw_affiliation_strings":["University of Victoria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6302,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67700963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"13","issue":"3s","first_page":"1","last_page":"25"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8551108837127686},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7953940629959106},{"id":"https://openalex.org/keywords/harp","display_name":"HARP","score":0.7887409925460815},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7202194929122925},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6860728859901428},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6545674800872803},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6519078016281128},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5304915904998779},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.44831612706184387},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2287975251674652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8551108837127686},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7953940629959106},{"id":"https://openalex.org/C2776030095","wikidata":"https://www.wikidata.org/wiki/Q5628954","display_name":"HARP","level":2,"score":0.7887409925460815},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7202194929122925},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6860728859901428},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6545674800872803},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6519078016281128},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5304915904998779},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44831612706184387},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2287975251674652},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2567938","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2567938","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1496940124","https://openalex.org/W1968902482","https://openalex.org/W1979527452","https://openalex.org/W2002950519","https://openalex.org/W2040469876","https://openalex.org/W2063186542","https://openalex.org/W2080592089","https://openalex.org/W2081373884","https://openalex.org/W2090584832","https://openalex.org/W2107333973","https://openalex.org/W2110195531","https://openalex.org/W2125979435","https://openalex.org/W2135947393","https://openalex.org/W2142444503","https://openalex.org/W2148443481","https://openalex.org/W2155503253","https://openalex.org/W2155568054","https://openalex.org/W2156540297","https://openalex.org/W2156831150","https://openalex.org/W2160428323","https://openalex.org/W2168921806","https://openalex.org/W2169880332","https://openalex.org/W2273348289","https://openalex.org/W2273440736","https://openalex.org/W2942827234","https://openalex.org/W3013490664","https://openalex.org/W3152438252","https://openalex.org/W4248073216"],"related_works":["https://openalex.org/W2091083843","https://openalex.org/W424580262","https://openalex.org/W2597835809","https://openalex.org/W4300904561","https://openalex.org/W619121476","https://openalex.org/W2807944126","https://openalex.org/W4248186805","https://openalex.org/W2099629705","https://openalex.org/W1966837078","https://openalex.org/W2136725475"],"abstract_inverted_index":{"SIMT":[0],"accelerators":[1],"are":[2,46],"equipped":[3],"with":[4,158],"thousands":[5],"of":[6,72,148,178,183],"computational":[7],"resources.":[8],"Conventional":[9],"accelerators,":[10],"however,":[11],"fail":[12],"to":[13,19,51,78,93,107,136,162],"fully":[14],"utilize":[15],"available":[16,92],"resources":[17],"due":[18,50],"branch":[20,52],"and":[21,35,58,75,110,131,160,197],"memory":[22],"divergences.":[23,53],"This":[24,54,83],"underutilization":[25,34,40,64],"is":[26,76],"manifested":[27],"in":[28,60,101,113],"two":[29],"underlying":[30],"inefficiencies:":[31],"pipeline":[32,36,69,80],"width":[33,109],"depth":[37,111],"underutilization.":[38],"Width":[39],"occurs":[41],"when":[42,67],"SIMD":[43,61,196],"execution":[44],"units":[45],"not":[47],"entirely":[48],"utilized":[49],"affects":[55],"lane":[56],"activity":[57],"results":[59],"inefficiency.":[62],"Depth":[63],"takes":[65],"place":[66],"the":[68,94,154,181],"runs":[70],"out":[71],"active":[73],"threads":[74,91,122],"forced":[77],"leave":[79],"stages":[81],"idle.":[82],"work":[84],"addresses":[85],"both":[86],"inefficiencies":[87],"by":[88],"harnessing":[89],"inactive":[90,119],"pipeline.":[95],"We":[96,115,152],"introduce":[97],"Harnessing":[98],"inActive":[99],"thReads":[100],"many-core":[102],"Processors":[103],"(or":[104],"simply":[105],"HARP)":[106],"improve":[108],"utilization":[112],"accelerators.":[114],"show":[116,169],"how":[117],"using":[118],"yet":[120],"ready":[121],"can":[123],"enhance":[124],"performance.":[125],"Moreover,":[126],"we":[127,142,168],"investigate":[128],"implementation":[129],"details":[130],"study":[132],"microarchitectural":[133,149],"changes":[134],"needed":[135],"build":[137],"a":[138,146],"HARP-enhanced":[139],"accelerator.":[140],"Furthermore,":[141],"evaluate":[143],"HARP":[144,159,171,191],"under":[145,194],"variety":[147],"design":[150],"points.":[151],"measure":[153],"area":[155,185],"overhead":[156],"associated":[157],"compare":[161],"conventional":[163],"alternatives.":[164],"Under":[165],"Fermi-like":[166],"GPUs,":[167],"that":[170,190],"provides":[172],"10%":[173],"speedup":[174],"on":[175],"average":[176],"(maximum":[177],"1.6X)":[179],"at":[180],"cost":[182],"3.5%":[184],"overhead.":[186],"Our":[187],"analysis":[188],"shows":[189],"performs":[192],"better":[193],"narrower":[195],"shorter":[198],"pipelines.":[199]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}