{"id":"https://openalex.org/W4390188367","doi":"https://doi.org/10.1109/hpec58863.2023.10363624","title":"Optimizing Compression Schemes for Parallel Sparse Tensor Algebra","display_name":"Optimizing Compression Schemes for Parallel Sparse Tensor Algebra","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4390188367","doi":"https://doi.org/10.1109/hpec58863.2023.10363624"},"language":"en","primary_location":{"id":"doi:10.1109/hpec58863.2023.10363624","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/hpec58863.2023.10363624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5101649586","display_name":"Helen Xu","orcid":"https://orcid.org/0000-0003-2232-3305"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Helen Xu","raw_affiliation_strings":["Lawrence Berkeley National Laboratory"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018454153","display_name":"Tao B. Schardl","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao B. Schardl","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009910914","display_name":"Michael Pellauer","orcid":"https://orcid.org/0000-0002-5305-4307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Pellauer","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024384625","display_name":"Joel Emer","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joel S. Emer","raw_affiliation_strings":["NVIDIA/MIT"],"affiliations":[{"raw_affiliation_string":"NVIDIA/MIT","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101649586"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19378141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T12303","display_name":"Tensor decomposition and applications","score":0.9969000220298767,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.6907727718353271},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.6539642810821533},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6371597647666931},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5986710786819458},{"id":"https://openalex.org/keywords/uncompressed-video","display_name":"Uncompressed video","score":0.5691612362861633},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49694016575813293},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.49283599853515625},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.46684110164642334},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44568243622779846},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.445048987865448},{"id":"https://openalex.org/keywords/tensor-algebra","display_name":"Tensor algebra","score":0.4431447684764862},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4145064949989319},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.3715035319328308},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.361295223236084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20066124200820923},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19989076256752014},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08623114228248596},{"id":"https://openalex.org/keywords/algebra-representation","display_name":"Algebra representation","score":0.08164548873901367},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.06640273332595825},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.06443995237350464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6907727718353271},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.6539642810821533},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6371597647666931},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5986710786819458},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.5691612362861633},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49694016575813293},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.49283599853515625},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.46684110164642334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44568243622779846},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.445048987865448},{"id":"https://openalex.org/C1680195","wikidata":"https://www.wikidata.org/wiki/Q2296021","display_name":"Tensor algebra","level":5,"score":0.4431447684764862},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4145064949989319},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.3715035319328308},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.361295223236084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20066124200820923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19989076256752014},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08623114228248596},{"id":"https://openalex.org/C14394260","wikidata":"https://www.wikidata.org/wiki/Q4723980","display_name":"Algebra representation","level":3,"score":0.08164548873901367},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.06640273332595825},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.06443995237350464},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0},{"id":"https://openalex.org/C100376341","wikidata":"https://www.wikidata.org/wiki/Q649977","display_name":"Jordan algebra","level":4,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec58863.2023.10363624","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/hpec58863.2023.10363624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","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":29,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1515135833","https://openalex.org/W1543897857","https://openalex.org/W1950330800","https://openalex.org/W1965551736","https://openalex.org/W1975116854","https://openalex.org/W1978979183","https://openalex.org/W1988311079","https://openalex.org/W2027851979","https://openalex.org/W2029108714","https://openalex.org/W2035080386","https://openalex.org/W2072806558","https://openalex.org/W2084296319","https://openalex.org/W2098602979","https://openalex.org/W2111667319","https://openalex.org/W2115215129","https://openalex.org/W2146530035","https://openalex.org/W2590246587","https://openalex.org/W2621280964","https://openalex.org/W2898123186","https://openalex.org/W2953212265","https://openalex.org/W2996480042","https://openalex.org/W3099706321","https://openalex.org/W3105671561","https://openalex.org/W3121402054","https://openalex.org/W4220886130","https://openalex.org/W4238995617","https://openalex.org/W4246166885","https://openalex.org/W6966426965"],"related_works":["https://openalex.org/W4244492201","https://openalex.org/W2165546027","https://openalex.org/W2112348346","https://openalex.org/W59193195","https://openalex.org/W1835670156","https://openalex.org/W4296405127","https://openalex.org/W3169240678","https://openalex.org/W4381050447","https://openalex.org/W3217141622","https://openalex.org/W2982469657"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"compression":[3,17,59,90],"techniques":[4,60],"for":[5,36,75],"parallel":[6],"in-memory":[7],"sparse":[8,67,76],"tensor":[9,77],"algebra.":[10,78],"We":[11,56],"find":[12],"that":[13,40,89],"applying":[14],"simple":[15],"existing":[16],"schemes":[18],"can":[19,41],"lead":[20],"to":[21,53,95],"performance":[22,51],"loss":[23],"in":[24],"some":[25],"cases.":[26],"To":[27],"resolve":[28],"this":[29],"issue,":[30],"we":[31],"introduce":[32],"an":[33],"optimized":[34],"algorithm":[35,105],"processing":[37],"compressed":[38],"inputs":[39],"improve":[42],"both":[43],"the":[44,50,58,92,97],"space":[45,93],"usage":[46],"as":[47,49],"well":[48],"compared":[52],"uncompressed":[54],"inputs.":[55],"implement":[57],"on":[61],"top":[62],"of":[63,66],"a":[64,73,80],"suite":[65],"matrix":[68],"algorithms":[69],"generated":[70],"by":[71,99],"taco,":[72],"compiler":[74],"On":[79],"machine":[81],"with":[82],"48":[83],"hyperthreads,":[84],"our":[85],"empirical":[86],"evaluation":[87],"shows":[88],"reduces":[91],"needed":[94],"store":[96],"matrices":[98],"over":[100],"2":[101],"x":[102],"without":[103],"sacrificing":[104],"performance.":[106]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}