{"id":"https://openalex.org/W2153963140","doi":"https://doi.org/10.1109/ispass.2013.6557173","title":"Characterizing scalar opportunities in GPGPU applications","display_name":"Characterizing scalar opportunities in GPGPU applications","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2153963140","doi":"https://doi.org/10.1109/ispass.2013.6557173","mag":"2153963140"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2013.6557173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2013.6557173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","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/A5011432420","display_name":"Zhongliang Chen","orcid":"https://orcid.org/0000-0002-8881-2294"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongliang Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061128237","display_name":"David Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036463155","display_name":"Norman Rubin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Norman Rubin","raw_affiliation_strings":["NVIDIA Corporation, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2202,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88468825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"234"},"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":0.9994000196456909,"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":0.9991999864578247,"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":0.9160099029541016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.855491042137146},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8236780166625977},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.6328766345977783},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6037518382072449},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.5968992710113525},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5501811504364014},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5460025668144226},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.474464476108551},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4279051423072815},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.28091681003570557},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1646726429462433},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13380175828933716}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9160099029541016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855491042137146},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8236780166625977},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.6328766345977783},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6037518382072449},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.5968992710113525},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5501811504364014},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5460025668144226},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.474464476108551},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4279051423072815},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.28091681003570557},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1646726429462433},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13380175828933716},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass.2013.6557173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2013.6557173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W762076161","https://openalex.org/W1482635212","https://openalex.org/W1485193134","https://openalex.org/W1979527452","https://openalex.org/W1994316441","https://openalex.org/W2033597569","https://openalex.org/W2124556751","https://openalex.org/W2128046183","https://openalex.org/W6622283136","https://openalex.org/W6629005405"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W99277194","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759"],"abstract_inverted_index":{"General":[0],"Purpose":[1],"computing":[2],"with":[3,99],"Graphics":[4],"Processing":[5],"Units":[6],"(GPGPU)":[7],"has":[8],"gained":[9],"widespread":[10],"adoption":[11],"in":[12,237],"both":[13],"the":[14,43,48,52,64,81,109,128,132,154,159,177,181,191,199,220,231,238],"high":[15],"performance":[16],"and":[17,130,183,233],"general":[18],"purpose":[19],"communities.":[20],"In":[21,141],"most":[22],"GPU":[23,35,208],"computation,":[24],"execution":[25,36],"exploits":[26],"a":[27,84,124,147,205],"Single":[28],"Instruction":[29],"Multiple":[30],"Data":[31],"(SIMD)":[32],"model.":[33],"However,":[34],"typically":[37],"pays":[38],"little":[39],"attention":[40],"to":[41,75,87,117,137,157,174],"whether":[42],"data":[44,112,179],"operated":[45],"upon":[46,119],"by":[47,78,180],"SIMD":[49,57,103,134,170],"units":[50,135,203,215],"is":[51],"same":[53,65,110,178],"or":[54],"different.":[55],"When":[56],"computation":[58,86],"operates":[59],"on":[60,108,176,204,230],"multiple":[61,88],"copies":[62],"of":[63,83,127,149,168,190,201,219,240],"data,":[66,129],"redundant":[67],"computations":[68],"are":[69,97,106,172,216],"generated.":[70],"It":[71],"provides":[72],"an":[73],"opportunity":[74],"improve":[76],"efficiency":[77],"just":[79],"broadcasting":[80],"results":[82,211,239],"single":[85,125],"outputs.":[89],"To":[90],"better":[91],"serve":[92],"those":[93],"operations,":[94],"modern":[95],"GPUs":[96],"armed":[98],"scalar":[100,120,162,202,214],"units.":[101],"Then":[102],"instructions":[104,171],"that":[105,166,213],"operating":[107],"input":[111],"operands":[113],"will":[114],"be":[115],"directed":[116],"execute":[118,138],"units,":[121],"requiring":[122],"only":[123],"copy":[126],"leaving":[131],"data-parallel":[133],"available":[136],"non-scalar":[139],"operations.":[140],"this":[142],"paper,":[143],"we":[144],"first":[145],"characterize":[146],"number":[148],"CUDA":[150],"programs":[151],"taken":[152],"from":[153],"NVIDIA":[155],"SDK":[156],"quantify":[158],"potential":[160],"for":[161,188],"execution.":[163,195],"We":[164,196],"observe":[165],"38%":[167],"static":[169],"recognized":[173],"operate":[175],"compiler,":[182],"their":[184,225],"dynamic":[185,193],"occurences":[186],"account":[187],"34%":[189],"total":[192],"instruction":[194],"then":[197],"evaluate":[198],"impact":[200],"heterogeneous":[206],"scalar-vector":[207],"architecture.":[209],"Our":[210],"show":[212],"utilized":[217],"51%":[218],"time":[221],"during":[222],"execution,":[223],"though":[224],"use":[226],"places":[227],"additional":[228],"pressure":[229],"interconnect":[232],"memory,":[234],"as":[235],"shown":[236],"our":[241],"study.":[242]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}