{"id":"https://openalex.org/W2794243109","doi":"https://doi.org/10.1145/3173162.3173171","title":"In-Memory Data Parallel Processor","display_name":"In-Memory Data Parallel Processor","publication_year":2018,"publication_date":"2018-03-19","ids":{"openalex":"https://openalex.org/W2794243109","doi":"https://doi.org/10.1145/3173162.3173171","mag":"2794243109"},"language":"en","primary_location":{"id":"doi:10.1145/3173162.3173171","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3173162.3173171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058871698","display_name":"Daichi Fujiki","orcid":"https://orcid.org/0000-0001-7949-0417"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daichi Fujiki","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002075773","display_name":"Scott Mahlke","orcid":"https://orcid.org/0000-0002-0438-0616"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Mahlke","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027544576","display_name":"Reetuparna Das","orcid":"https://orcid.org/0000-0002-5894-8342"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reetuparna Das","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":108,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/computer-science","display_name":"Computer science","score":0.8792867660522461},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7549378871917725},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7506618499755859},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5248130559921265},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.44563862681388855},{"id":"https://openalex.org/keywords/memory-map","display_name":"Memory map","score":0.44298475980758667},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.4390898048877716},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4373261630535126},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.41953301429748535},{"id":"https://openalex.org/keywords/in-memory-processing","display_name":"In-Memory Processing","score":0.4172939956188202},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3992467522621155},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.38495147228240967},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3613709509372711},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.17946681380271912},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.17596176266670227},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15263229608535767},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.11016926169395447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8792867660522461},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7549378871917725},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7506618499755859},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5248130559921265},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.44563862681388855},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.44298475980758667},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.4390898048877716},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4373261630535126},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.41953301429748535},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.4172939956188202},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3992467522621155},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.38495147228240967},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3613709509372711},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.17946681380271912},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.17596176266670227},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15263229608535767},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.11016926169395447},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.0},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3173162.3173171","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3173162.3173171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G339059864","display_name":"CAREER:  In-Situ Compute Memories for Accelerating Data Parallel Applications","funder_award_id":"1652294","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1975237352","https://openalex.org/W1981943579","https://openalex.org/W2013435193","https://openalex.org/W2021425055","https://openalex.org/W2043548159"],"related_works":["https://openalex.org/W254684032","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W1959889508","https://openalex.org/W2186451538","https://openalex.org/W4381884576","https://openalex.org/W2247651031","https://openalex.org/W233533876","https://openalex.org/W120214571","https://openalex.org/W1848192231"],"abstract_inverted_index":{"Recent":[0],"developments":[1],"in":[2,76,101],"Non-Volatile":[3],"Memories":[4],"(NVMs)":[5],"have":[6,26],"opened":[7],"up":[8],"a":[9,52,119,124,140,145,155,159],"new":[10],"horizon":[11],"for":[12,87,130,144,158],"in-memory":[13,54,66,115,132],"computing.":[14],"Despite":[15],"the":[16,35,64,88,98,102,106],"significant":[17],"performance":[18],"gain":[19],"offered":[20],"by":[21,50,104],"computational":[22],"NVMs,":[23],"previous":[24],"works":[25],"relied":[27],"on":[28],"manual":[29],"mapping":[30],"of":[31,63,108,147,161],"specialized":[32],"kernels":[33],"to":[34,41,96],"memory":[36,89],"arrays,":[37],"making":[38],"it":[39],"infeasible":[40],"execute":[42],"more":[43],"general":[44],"workloads.":[45],"We":[46],"combat":[47],"this":[48],"problem":[49],"proposing":[51],"programmable":[53],"processor":[55,67],"architecture":[56],"and":[57,74,110,127,151],"data-parallel":[58],"programming":[59,93],"framework.":[60],"The":[61,91],"efficiency":[62],"proposed":[65,92],"comes":[68],"from":[69,149],"two":[70],"sources:":[71],"massive":[72],"parallelism":[73,100],"reduction":[75],"data":[77],"movement.":[78],"A":[79],"compact":[80],"instruction":[81],"set":[82,146,160],"provides":[83],"generalized":[84],"computation":[85],"capabilities":[86],"array.":[90],"framework":[94,121],"seeks":[95],"leverage":[97],"underlying":[99],"hardware":[103],"merging":[105],"concepts":[107],"data-flow":[109],"vector":[111],"processing.":[112],"To":[113],"facilitate":[114],"programming,":[116],"we":[117],"develop":[118],"compilation":[120],"that":[122],"takes":[123],"TensorFlow":[125],"input":[126],"generates":[128],"code":[129],"our":[131],"processor.":[133],"Our":[134],"results":[135],"demonstrate":[136],"7.5x":[137],"speedup":[138,153],"over":[139,154],"multi-core":[141],"CPU":[142],"server":[143],"applications":[148],"Parsec":[150],"763x":[152],"server-class":[156],"GPU":[157],"Rodinia":[162],"benchmarks.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}