{"id":"https://openalex.org/W3012547936","doi":"https://doi.org/10.1109/iiswc47752.2019.9042134","title":"Optimizing Hyperplane Sweep Operations Using Asynchronous Multi-grain GPU Tasks","display_name":"Optimizing Hyperplane Sweep Operations Using Asynchronous Multi-grain GPU Tasks","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012547936","doi":"https://doi.org/10.1109/iiswc47752.2019.9042134","mag":"3012547936"},"language":"en","primary_location":{"id":"doi:10.1109/iiswc47752.2019.9042134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc47752.2019.9042134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Workload Characterization (IISWC)","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/A5073862711","display_name":"Anirudh Mohan Kaushik","orcid":"https://orcid.org/0000-0002-8347-0109"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Anirudh Mohan Kaushik","raw_affiliation_strings":["University of Waterloo,Department of ECE,Waterloo,Canada","Department of ECE, University of Waterloo, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo,Department of ECE,Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"Department of ECE, University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091417392","display_name":"Ashwin M. Aji","orcid":"https://orcid.org/0000-0002-5467-8357"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin M. Aji","raw_affiliation_strings":["Advanced Micro Devices, Inc.,AMD Research,USA","AMD Research, Advanced Micro Devices, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,AMD Research,USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"AMD Research, Advanced Micro Devices, Inc., USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104053500","display_name":"Muhammad Amber Hassaan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Amber Hassaan","raw_affiliation_strings":["Advanced Micro Devices, Inc.,AMD Research,USA","AMD Research, Advanced Micro Devices, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,AMD Research,USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"AMD Research, Advanced Micro Devices, Inc., USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020250502","display_name":"Noel Chalmers","orcid":"https://orcid.org/0000-0002-1293-7525"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noel Chalmers","raw_affiliation_strings":["Advanced Micro Devices, Inc.,AMD Research,USA","AMD Research, Advanced Micro Devices, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,AMD Research,USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"AMD Research, Advanced Micro Devices, Inc., USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076196719","display_name":"Noah Wolfe","orcid":"https://orcid.org/0000-0002-7935-421X"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noah Wolfe","raw_affiliation_strings":["Advanced Micro Devices, Inc.,AMD Research,USA","AMD Research, Advanced Micro Devices, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,AMD Research,USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"AMD Research, Advanced Micro Devices, Inc., USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080835775","display_name":"Scott Moe","orcid":"https://orcid.org/0009-0007-8500-5810"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Moe","raw_affiliation_strings":["Advanced Micro Devices, Inc.,AMD Research,USA","AMD Research, Advanced Micro Devices, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,AMD Research,USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"AMD Research, Advanced Micro Devices, Inc., USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024878606","display_name":"Sooraj Puthoor","orcid":"https://orcid.org/0000-0003-0285-5742"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sooraj Puthoor","raw_affiliation_strings":["Advanced Micro Devices, Inc.,AMD Research,USA","AMD Research, Advanced Micro Devices, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,AMD Research,USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"AMD Research, Advanced Micro Devices, Inc., USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077056823","display_name":"Bradford M. Beckmann","orcid":"https://orcid.org/0000-0002-5444-6521"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bradford M. Beckmann","raw_affiliation_strings":["Advanced Micro Devices, Inc.,AMD Research,USA","AMD Research, Advanced Micro Devices, Inc., USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc.,AMD Research,USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"AMD Research, Advanced Micro Devices, Inc., USA","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5073862711"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.2408,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54617793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"69"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.8297268152236938},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8113551139831543},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6490936875343323},{"id":"https://openalex.org/keywords/hyperplane","display_name":"Hyperplane","score":0.6116882562637329},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5955118536949158},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5585156083106995},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5225550532341003},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4836021959781647},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4638400673866272},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4213528037071228},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1569010317325592},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.13193228840827942},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07964080572128296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297268152236938},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8113551139831543},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6490936875343323},{"id":"https://openalex.org/C68693459","wikidata":"https://www.wikidata.org/wiki/Q657586","display_name":"Hyperplane","level":2,"score":0.6116882562637329},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5955118536949158},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5585156083106995},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5225550532341003},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4836021959781647},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4638400673866272},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4213528037071228},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1569010317325592},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.13193228840827942},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07964080572128296},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iiswc47752.2019.9042134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc47752.2019.9042134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Workload Characterization (IISWC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W181207963","https://openalex.org/W1974165977","https://openalex.org/W2022188979","https://openalex.org/W2049391017","https://openalex.org/W2061781302","https://openalex.org/W2088917948","https://openalex.org/W2104861744","https://openalex.org/W2165221050","https://openalex.org/W2322798958","https://openalex.org/W2337369872","https://openalex.org/W2340816002","https://openalex.org/W2576230297","https://openalex.org/W2582456645","https://openalex.org/W2734294625","https://openalex.org/W2788386530","https://openalex.org/W2788517652","https://openalex.org/W2795475040","https://openalex.org/W2885503917","https://openalex.org/W3010696258","https://openalex.org/W4205464437","https://openalex.org/W4233930397","https://openalex.org/W6607280473","https://openalex.org/W6703970976","https://openalex.org/W6732885202","https://openalex.org/W6753810136","https://openalex.org/W7006597792"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W2168758875","https://openalex.org/W4246549241","https://openalex.org/W2410733619","https://openalex.org/W2963483475","https://openalex.org/W1980160788","https://openalex.org/W641925902","https://openalex.org/W2149904643"],"abstract_inverted_index":{"General-Purpose":[0],"Graphics":[1],"Processing":[2],"Units":[3],"(GPGPUs)":[4],"are":[5,28],"employed":[6],"in":[7,48],"today's":[8],"fastest":[9],"supercomputers":[10],"to":[11,92],"accelerate":[12],"a":[13,100],"variety":[14],"of":[15,23],"scientific":[16],"compute":[17],"workloads.":[18],"These":[19],"workloads":[20],"typically":[21],"comprise":[22],"data-parallel":[24],"mathematical":[25,42],"kernels":[26],"that":[27,44,103,111],"well":[29],"suited":[30],"for":[31],"execution":[32],"on":[33],"GPUs.":[34],"The":[35],"hyperplane":[36,60],"sweep":[37,61,106],"operation":[38,76],"is":[39,45],"one":[40],"such":[41],"kernel":[43],"commonly":[46],"used":[47,64],"high-performance":[49],"computing.":[50],"In":[51],"this":[52,82],"paper,":[53],"we":[54,84,109],"characterize":[55],"the":[56,75,94,105,119],"conventional":[57],"bulk":[58,120],"synchronous":[59,121],"implementation":[62],"currently":[63],"by":[65,73,81],"GPUs":[66],"and":[67,89,108],"identify":[68],"significant":[69],"performance":[70],"improvement":[71],"potential":[72],"breaking":[74],"into":[77],"finer-grain":[78],"tasks.":[79],"Guided":[80],"characterization,":[83],"propose":[85],"multi-grain":[86],"task":[87],"decomposition":[88],"scheduling":[90],"techniques":[91],"optimize":[93],"operation.":[95],"We":[96],"use":[97],"KRIPKE":[98],"as":[99],"case":[101],"study":[102],"features":[104],"operation,":[107],"show":[110],"our":[112],"proposed":[113],"optimizations":[114],"achieve":[115],"41%":[116],"speedup":[117],"over":[118],"implementation.":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
