{"id":"https://openalex.org/W2156355519","doi":"https://doi.org/10.1145/2628071.2628072","title":"D <sup>2</sup> MA","display_name":"D <sup>2</sup> MA","publication_year":2014,"publication_date":"2014-08-21","ids":{"openalex":"https://openalex.org/W2156355519","doi":"https://doi.org/10.1145/2628071.2628072","mag":"2156355519"},"language":"en","primary_location":{"id":"doi:10.1145/2628071.2628072","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2628072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","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/A5065079006","display_name":"D. Anoushe Jamshidi","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"D. Anoushe Jamshidi","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"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/A5058642630","display_name":"Mehrzad Samadi","orcid":"https://orcid.org/0000-0002-3581-1255"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehrzad Samadi","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"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/A5002075773","display_name":"Scott Mahlke","orcid":"https://orcid.org/0000-0002-0438-0616"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","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"],"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":3,"corresponding_author_ids":["https://openalex.org/A5065079006"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":2.1453,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88034415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"431","last_page":"442"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9990000128746033,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8620544672012329},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.65413498878479},{"id":"https://openalex.org/keywords/shader","display_name":"Shader","score":0.5847952961921692},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4969532787799835},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4810221791267395},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.47287437319755554},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34470513463020325},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24369695782661438},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1993422508239746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8620544672012329},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.65413498878479},{"id":"https://openalex.org/C177681979","wikidata":"https://www.wikidata.org/wiki/Q633182","display_name":"Shader","level":3,"score":0.5847952961921692},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4969532787799835},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4810221791267395},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.47287437319755554},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34470513463020325},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24369695782661438},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1993422508239746},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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:10.1145/2628071.2628072","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2628072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7342013639","display_name":null,"funder_award_id":"CNS-0964478","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G7397408956","display_name":null,"funder_award_id":"SHF-1217917","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/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W56720343","https://openalex.org/W1567646530","https://openalex.org/W1979527452","https://openalex.org/W1983235612","https://openalex.org/W1989061323","https://openalex.org/W1994999558","https://openalex.org/W2024122052","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2049875313","https://openalex.org/W2061179133","https://openalex.org/W2078994750","https://openalex.org/W2080592089","https://openalex.org/W2084110734","https://openalex.org/W2088943630","https://openalex.org/W2090584832","https://openalex.org/W2096661534","https://openalex.org/W2109772848","https://openalex.org/W2140375692","https://openalex.org/W2142444503","https://openalex.org/W2166918318","https://openalex.org/W2998721384","https://openalex.org/W3003193617","https://openalex.org/W3138340923","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1997955449","https://openalex.org/W1505787035","https://openalex.org/W1997145140","https://openalex.org/W2372170743","https://openalex.org/W2462936459","https://openalex.org/W2117014006","https://openalex.org/W1558545464","https://openalex.org/W2131630752","https://openalex.org/W2060252920","https://openalex.org/W2105856903"],"abstract_inverted_index":{"To":[0,106],"achieve":[1,181],"high":[2,184],"performance":[3],"on":[4,34,99,197],"many-core":[5],"architectures":[6],"like":[7,29],"GPUs,":[8],"it":[9,20,53],"is":[10,21,117,171],"crucial":[11],"to":[12,23,38,77,92,94,130,157,173,180,192],"efficiently":[13,56],"utilize":[14],"the":[15,30,58,100,103,125,141,160,174,189],"available":[16,33,59],"memory":[17,32,60,156],"bandwidth.":[18],"Currently,":[19],"common":[22],"use":[24],"fast,":[25],"on-chip":[26,86],"scratchpad":[27],"memories,":[28],"shared":[31,161],"GPUs'":[35],"shader":[36,66],"cores,":[37],"buffer":[39,193],"data":[40,79,153,194],"for":[41,70,152],"computation.":[42],"This":[43],"buffering,":[44],"however,":[45],"has":[46],"some":[47],"sources":[48],"of":[49,102,120,127,132],"inefficiency":[50],"that":[51,123,170],"hinder":[52],"from":[54,65,140],"most":[55],"utilizing":[57],"resources.":[61],"These":[62,176],"issues":[63],"stem":[64],"resources":[67],"being":[68],"used":[69],"repeated,":[71],"regular":[72],"address":[73,107,138],"calculations,":[74],"a":[75,83,118,146,165],"need":[76],"shuffle":[78],"multiple":[80],"times":[81],"between":[82],"physically":[84],"unified":[85],"memory,":[87,162],"and":[88,149,163,187],"forcing":[89],"all":[90],"threads":[91],"synchronize":[93],"ensure":[95],"RAW":[96],"consistency":[97],"based":[98],"speed":[101],"slowest":[104],"threads.":[105,135],"these":[108],"inefficiencies,":[109],"we":[110],"propose":[111],"Data-Parallel":[112],"DMA,":[113],"or":[114],"D2MA.":[115],"D2MA":[116,136,179],"reimagination":[119],"traditional":[121],"DMA":[122,129],"addresses":[124],"challenges":[126],"extending":[128],"thousands":[131],"concurrently":[133],"executing":[134],"de-couples":[137],"generation":[139],"shader's":[142],"computational":[143],"resources,":[144],"provides":[145],"more":[147],"direct":[148],"efficient":[150],"path":[151],"in":[154],"global":[155],"travel":[158],"into":[159],"introduces":[164],"novel":[166],"dynamic":[167],"synchronization":[168],"scheme":[169],"transparent":[172],"programmer.":[175],"advancements":[177],"allow":[178],"speedups":[182],"as":[183,185],"2.29x,":[186],"reduces":[188],"average":[190],"time":[191],"by":[195],"81%":[196],"average.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
