{"id":"https://openalex.org/W7116366342","doi":"https://doi.org/10.1145/3754598.3754651","title":"AMPED: Accelerating MTTKRP for Billion-Scale Sparse Tensor Decomposition on Multiple GPUs","display_name":"AMPED: Accelerating MTTKRP for Billion-Scale Sparse Tensor Decomposition on Multiple GPUs","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116366342","doi":"https://doi.org/10.1145/3754598.3754651"},"language":null,"primary_location":{"id":"doi:10.1145/3754598.3754651","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3754598.3754651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","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/A5036985229","display_name":"Sasindu Wijeratne","orcid":"https://orcid.org/0000-0002-5538-2988"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sasindu Wijeratne","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-5538-2988","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042560222","display_name":"Rajgopal Kannan","orcid":"https://orcid.org/0000-0001-8736-3012"},"institutions":[{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajgopal Kannan","raw_affiliation_strings":["DEVCOM Army Research Office, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0001-8736-3012","affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Office, Los Angeles, USA","institution_ids":["https://openalex.org/I2802705668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120921940","display_name":"Viktor Prasanna","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor Prasanna","raw_affiliation_strings":["University of Southern California, LOS ANGELES, USA"],"raw_orcid":"https://orcid.org/0000-0002-1609-8589","affiliations":[{"raw_affiliation_string":"University of Southern California, LOS ANGELES, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036985229"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63339071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"208","last_page":"217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9617000222206116,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9617000222206116,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.006800000090152025,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.004100000020116568,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7746999859809875},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6212999820709229},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5853999853134155},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.5838000178337097},{"id":"https://openalex.org/keywords/tensor-decomposition","display_name":"Tensor decomposition","score":0.506600022315979},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5011000037193298},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4700999855995178},{"id":"https://openalex.org/keywords/tensor-product","display_name":"Tensor product","score":0.44609999656677246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771000266075134},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7746999859809875},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.760200023651123},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.5838000178337097},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.506600022315979},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5011000037193298},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4724000096321106},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4203000068664551},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.39800000190734863},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.32280001044273376},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.25220000743865967},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3754598.3754651","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3754598.3754651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2024165284","https://openalex.org/W2114973222","https://openalex.org/W2119412403","https://openalex.org/W2532592438","https://openalex.org/W2903901007","https://openalex.org/W2964104075","https://openalex.org/W2971508019","https://openalex.org/W2982471955","https://openalex.org/W2986686333","https://openalex.org/W3005990752","https://openalex.org/W3016735325","https://openalex.org/W3090480494","https://openalex.org/W3131137184","https://openalex.org/W3200075413","https://openalex.org/W3201632862","https://openalex.org/W4225391771","https://openalex.org/W4250981202","https://openalex.org/W4282975603","https://openalex.org/W4285609561","https://openalex.org/W4289533782","https://openalex.org/W4308968707","https://openalex.org/W4319870531","https://openalex.org/W4388483325","https://openalex.org/W4396944764","https://openalex.org/W4399343569","https://openalex.org/W4404133484"],"related_works":[],"abstract_inverted_index":{"Matricized":[0],"Tensor":[1],"Times":[2],"Khatri-Rao":[3],"Product":[4],"(MTTKRP)":[5],"is":[6],"the":[7,56,64],"computational":[8],"bottleneck":[9],"in":[10,104],"sparse":[11,16,51],"tensor":[12],"decomposition.":[13],"As":[14],"real-world":[15,93],"tensors":[17],"grow":[18],"to":[19,46,84],"billions":[20],"of":[21,58,69],"nonzeros,":[22],"they":[23],"increasingly":[24],"demand":[25],"higher":[26],"memory":[27,65],"capacity":[28],"and":[29,66,87],"compute":[30],"throughput":[31],"from":[32],"hardware":[33],"accelerators.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"present":[39],"AMPED,":[40],"a":[41,59,74,79,98,116],"multi-GPU":[42],"parallel":[43],"algorithm":[44],"designed":[45],"accelerate":[47],"MTTKRP":[48],"on":[49,115],"billion-scale":[50,94],"tensors.":[52],"AMPED":[53,96],"scales":[54],"beyond":[55],"limits":[57],"single":[60,117],"GPU,":[61],"meeting":[62],"both":[63],"performance":[67],"requirements":[68],"large-scale":[70],"workloads.":[71],"We":[72],"introduce":[73],"partitioning":[75],"strategy":[76],"combined":[77],"with":[78],"dynamic":[80],"load":[81],"balancing":[82],"scheme":[83],"distribute":[85],"computation":[86],"minimize":[88],"GPU":[89,110],"idle":[90],"time.":[91],"On":[92],"tensors,":[95],"achieves":[97],"5.1":[99],"\u00d7":[100],"geometric":[101],"mean":[102],"speedup":[103],"total":[105],"execution":[106],"time":[107],"over":[108],"state-of-the-art":[109],"baselines":[111],"using":[112],"4":[113],"GPUs":[114],"CPU":[118],"node.":[119]},"counts_by_year":[],"updated_date":"2025-12-21T02:06:08.432651","created_date":"2025-12-21T00:00:00"}