{"id":"https://openalex.org/W2412759392","doi":"https://doi.org/10.1109/ispass.2016.7482073","title":"Analyzing the energy-efficiency of sparse matrix multiplication on heterogeneous systems: A comparative study of GPU, Xeon Phi and FPGA","display_name":"Analyzing the energy-efficiency of sparse matrix multiplication on heterogeneous systems: A comparative study of GPU, Xeon Phi and FPGA","publication_year":2016,"publication_date":"2016-04-01","ids":{"openalex":"https://openalex.org/W2412759392","doi":"https://doi.org/10.1109/ispass.2016.7482073","mag":"2412759392"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2016.7482073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2016.7482073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5036729583","display_name":"Heiner Giefers","orcid":"https://orcid.org/0000-0002-5811-6386"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Heiner Giefers","raw_affiliation_strings":["IBM Research - Zurich, Ruschlikon, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research - Zurich, Ruschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024778597","display_name":"Peter Staar","orcid":"https://orcid.org/0000-0002-8088-0823"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Peter Staar","raw_affiliation_strings":["IBM Research - Zurich, Ruschlikon, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research - Zurich, Ruschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110940665","display_name":"Costas Bekas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Costas Bekas","raw_affiliation_strings":["IBM Research - Zurich, Ruschlikon, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research - Zurich, Ruschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001983294","display_name":"Christoph Hagleitner","orcid":"https://orcid.org/0000-0002-6815-7835"},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christoph Hagleitner","raw_affiliation_strings":["IBM Research - Zurich, Ruschlikon, Switzerland"],"affiliations":[{"raw_affiliation_string":"IBM Research - Zurich, Ruschlikon, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036729583"],"corresponding_institution_ids":["https://openalex.org/I4210126328"],"apc_list":null,"apc_paid":null,"fwci":2.8894,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.90330533,"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":"46","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9970999956130981,"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":0.8011214733123779},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7202379703521729},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.6764266490936279},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6478772163391113},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6323736906051636},{"id":"https://openalex.org/keywords/pci-express","display_name":"PCI Express","score":0.6094692349433899},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5807554125785828},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5208921432495117},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.49039793014526367},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.45646679401397705},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.45339372754096985},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.33791837096214294},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2712743282318115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011214733123779},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7202379703521729},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6764266490936279},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6478772163391113},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6323736906051636},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.6094692349433899},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5807554125785828},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5208921432495117},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.49039793014526367},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.45646679401397705},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.45339372754096985},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33791837096214294},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2712743282318115},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass.2016.7482073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2016.7482073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1520679476","https://openalex.org/W1578462120","https://openalex.org/W1776498962","https://openalex.org/W1968432902","https://openalex.org/W1975116854","https://openalex.org/W1977661221","https://openalex.org/W1987840949","https://openalex.org/W1988593113","https://openalex.org/W1997113918","https://openalex.org/W2022020111","https://openalex.org/W2023047131","https://openalex.org/W2023930909","https://openalex.org/W2029531463","https://openalex.org/W2034919323","https://openalex.org/W2035080386","https://openalex.org/W2041872229","https://openalex.org/W2054592134","https://openalex.org/W2054882590","https://openalex.org/W2059117794","https://openalex.org/W2080592089","https://openalex.org/W2088866486","https://openalex.org/W2095230296","https://openalex.org/W2100415730","https://openalex.org/W2101511474","https://openalex.org/W2106111377","https://openalex.org/W2108540054","https://openalex.org/W2110195531","https://openalex.org/W2113921339","https://openalex.org/W2114226921","https://openalex.org/W2121082877","https://openalex.org/W2128539477","https://openalex.org/W2133156997","https://openalex.org/W2134807578","https://openalex.org/W2135120170","https://openalex.org/W2137708693","https://openalex.org/W2142769604","https://openalex.org/W2145055833","https://openalex.org/W2149234156","https://openalex.org/W2154590891","https://openalex.org/W2154991996","https://openalex.org/W2155470578","https://openalex.org/W2162283062","https://openalex.org/W2167868137","https://openalex.org/W2343695530","https://openalex.org/W2474119684","https://openalex.org/W2486056921","https://openalex.org/W2533651815","https://openalex.org/W4206600176","https://openalex.org/W4240739471","https://openalex.org/W4245121088","https://openalex.org/W4256629673","https://openalex.org/W6631228652","https://openalex.org/W6638245406","https://openalex.org/W6678286823","https://openalex.org/W6682848092","https://openalex.org/W6684509964","https://openalex.org/W6720547715","https://openalex.org/W6722751131"],"related_works":["https://openalex.org/W1974923383","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2475524688","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2032784242","https://openalex.org/W1981810806","https://openalex.org/W2279642117"],"abstract_inverted_index":{"Hardware":[0],"accelerators":[1,26,57,112,188],"have":[2],"evolved":[3],"as":[4],"the":[5,11,28,38,50,64,78,107,122,125,149,160,165,175,192],"most":[6],"prominent":[7],"vehicle":[8],"to":[9,36,89,105,120,199],"meet":[10],"demanding":[12],"performance":[13,194],"and":[14,53,102,158,173,195,201],"energy-efficiency":[15,54,157],"constraints":[16],"of":[17,24,55,71,80,110,128,148,156,186],"modern":[18,115],"computer":[19],"systems.":[20,117],"The":[21],"prevalent":[22],"type":[23],"hardware":[25,111],"in":[27,86,114,154],"high-performance":[29],"computing":[30],"domain":[31],"are":[32,85],"PCIe":[33],"attached":[34],"co-processors":[35,104],"which":[37,84,137],"CPU":[39],"can":[40,189],"offload":[41],"compute":[42],"intensive":[43],"tasks.":[44],"In":[45,118],"this":[46],"paper,":[47],"we":[48,131,144],"analyze":[49],"performance,":[51],"power,":[52],"such":[56],"for":[58,66,136],"sparse":[59,67,167],"matrix":[60,68,168],"multiplication":[61],"kernels.":[62],"Improving":[63],"efficiency":[65,177,196],"operations":[69],"is":[70],"eminent":[72],"importance":[73],"since":[74],"they":[75],"work":[76],"at":[77],"core":[79],"graph":[81],"analytics":[82],"algorithms":[83],"turn":[87],"key":[88],"many":[90],"big":[91],"data":[92,170],"knowledge":[93],"discovery":[94],"workloads.":[95],"Our":[96],"study":[97],"involves":[98],"GPU,":[99],"Xeon":[100],"Phi,":[101],"FPGA":[103],"embrace":[106],"vast":[108],"majority":[109],"applied":[113,176],"HPC":[116],"order":[119],"compare":[121],"devices":[123,151],"on":[124,164,174],"same":[126],"level":[127],"implementation":[129],"quality":[130],"apply":[132],"vendor":[133],"optimized":[134],"libraries":[135],"published":[138],"results":[139],"exist.":[140],"From":[141],"our":[142],"experiments":[143],"deduce":[145],"that":[146,159,182],"none":[147],"compared":[150],"generally":[152],"dominates":[153],"terms":[155],"optimal":[161],"solutions":[162],"depends":[163],"actual":[166],"data,":[169],"transfer":[171],"requirements":[172],"metric.":[178],"We":[179],"also":[180],"show":[181],"a":[183],"combined":[184],"use":[185],"multiple":[187],"further":[190],"improve":[191],"system's":[193],"by":[197],"up":[198],"11%":[200],"18%,":[202],"respectively.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}