{"id":"https://openalex.org/W4254284875","doi":"https://doi.org/10.1109/isca.2014.6853233","title":"STAG: Spintronic-Tape Architecture for GPGPU cache hierarchies","display_name":"STAG: Spintronic-Tape Architecture for GPGPU cache hierarchies","publication_year":2014,"publication_date":"2014-06-01","ids":{"openalex":"https://openalex.org/W4254284875","doi":"https://doi.org/10.1109/isca.2014.6853233"},"language":"en","primary_location":{"id":"doi:10.1109/isca.2014.6853233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isca.2014.6853233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 ACM/IEEE 41st International Symposium on Computer Architecture (ISCA)","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/A5045219356","display_name":"Rangharajan Venkatesan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rangharajan Venkatesan","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033127135","display_name":"Shankar Ganesh Ramasubramanian","orcid":"https://orcid.org/0000-0003-3938-9052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shankar Ganesh Ramasubramanian","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010094713","display_name":"Swagath Venkataramani","orcid":"https://orcid.org/0000-0002-0470-6364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swagath Venkataramani","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031161187","display_name":"Kaushik Roy","orcid":"https://orcid.org/0000-0002-0735-9695"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaushik Roy","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065766721","display_name":"Anand Raghunathan","orcid":"https://orcid.org/0000-0002-4624-564X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anand Raghunathan","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0964,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.94220442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"320","issue":null,"first_page":"253","last_page":"264"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774822115898132},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6695621609687805},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5800175666809082},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5493167042732239},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5283463597297668},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4933132231235504},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1886948049068451},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.07930630445480347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774822115898132},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6695621609687805},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5800175666809082},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5493167042732239},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5283463597297668},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4933132231235504},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1886948049068451},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.07930630445480347},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isca.2014.6853233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isca.2014.6853233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 ACM/IEEE 41st International Symposium on Computer Architecture (ISCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1968480751","https://openalex.org/W1971543343","https://openalex.org/W1979527452","https://openalex.org/W1981443800","https://openalex.org/W2005242923","https://openalex.org/W2005522813","https://openalex.org/W2011443263","https://openalex.org/W2018384083","https://openalex.org/W2020572638","https://openalex.org/W2029083842","https://openalex.org/W2033188264","https://openalex.org/W2034097727","https://openalex.org/W2047379549","https://openalex.org/W2048588974","https://openalex.org/W2064977311","https://openalex.org/W2065558271","https://openalex.org/W2072656003","https://openalex.org/W2078760460","https://openalex.org/W2080592089","https://openalex.org/W2084007230","https://openalex.org/W2097823832","https://openalex.org/W2102449048","https://openalex.org/W2135393827","https://openalex.org/W2155551886","https://openalex.org/W2273440736","https://openalex.org/W2578507560","https://openalex.org/W3139006581","https://openalex.org/W4240165677","https://openalex.org/W4254159549","https://openalex.org/W6635732093","https://openalex.org/W6653237175","https://openalex.org/W6684763460","https://openalex.org/W6694513646"],"related_works":["https://openalex.org/W2505380084","https://openalex.org/W4400333498","https://openalex.org/W2086739451","https://openalex.org/W3183233360","https://openalex.org/W2073137634","https://openalex.org/W2808906329","https://openalex.org/W22188748","https://openalex.org/W2152099439","https://openalex.org/W1980160788","https://openalex.org/W2038503502"],"abstract_inverted_index":{"General-purpose":[0],"Graphics":[1],"Processing":[2],"Units":[3],"(GPGPUs)":[4],"are":[5,167,214,229],"widely":[6],"used":[7],"for":[8,41,196],"executing":[9],"massively":[10],"parallel":[11,176],"workloads":[12],"from":[13,241],"various":[14],"application":[15],"domains.":[16],"Feeding":[17],"data":[18],"to":[19,22,98,143,188,210,231],"the":[20,34,81,103,145,150,161,190,211,242],"hundreds":[21],"thousands":[23],"of":[24,83,129,172,193,239],"cores":[25],"that":[26,102,138,183,222],"current":[27],"GPGPUs":[28],"integrate":[29],"places":[30],"great":[31],"demands":[32],"on":[33,217],"memory":[35,62,147],"hierarchy,":[36,153],"fueling":[37],"an":[38],"ever-increasing":[39],"demand":[40],"on-chip":[42],"memory.":[43],"In":[44],"this":[45,94,123],"work,":[46],"we":[47],"propose":[48],"STAG,":[49],"a":[50,59,84,90,99,127,134,155,164,170,201,225,232,236],"high":[51],"density,":[52],"energy-efficient":[53],"GPGPU":[54,151],"cache":[55,136,152,165,213],"hierarchy":[56],"design":[57],"using":[58],"new":[60],"spintronic":[61],"technology":[63],"called":[64],"Domain":[65],"Wall":[66],"Memory":[67],"(DWM).":[68],"DWMs":[69],"inherently":[70],"offer":[71],"unprecedented":[72],"benefits":[73,251],"in":[74,80,114,159,163,207,252],"density":[75],"by":[76,109],"storing":[77],"multiple":[78],"bits":[79,104,162],"domains":[82],"ferromagnetic":[85],"nanowire,":[86],"which":[87,160,208],"logically":[88],"resembles":[89],"bit-serial":[91],"tape.":[92],"However,":[93],"structure":[95],"also":[96],"leads":[97],"unique":[100],"challenge":[101],"must":[105],"be":[106],"sequentially":[107],"accessed":[108],"performing":[110],"\u201cshift\u201d":[111],"operations,":[112],"resulting":[113],"variable":[115],"and":[116,199,220,245,257,261,266],"potentially":[117],"higher":[118],"access":[119],"latencies.":[120],"To":[121],"address":[122],"challenge,":[124],"STAG":[125,248],"utilizes":[126],"number":[128,192],"architectural":[130],"techniques":[131],":":[132],"(i)":[133],"hybrid":[135],"organization":[137],"employs":[139],"different":[140,146],"DWM":[141,173,186,212],"bit-cells":[142],"realize":[144],"arrays":[148,187],"within":[149],"(ii)":[154],"clustered,":[156],"bit-interleaved":[157],"organization,":[158],"block":[166],"spread":[168],"across":[169],"cluster":[171],"tapes,":[174],"allowing":[175],"access,":[177],"(iii)":[178],"tape":[179],"head":[180],"management":[181],"policies":[182],"predictively":[184],"configure":[185],"reduce":[189],"expected":[191],"shift":[194,202,227],"operations":[195],"subsequent":[197],"accesses,":[198],"(iv)":[200],"aware":[203],"promotion":[204],"buffer":[205],"(SaPB),":[206],"accesses":[209],"predicted":[215],"based":[216],"intra-warp":[218],"locality,":[219],"locations":[221],"would":[223],"incur":[224],"large":[226],"penalty":[228],"promoted":[230],"smaller":[233],"buffer.":[234],"Over":[235],"wide":[237],"range":[238],"benchmarks":[240],"Rodinia,":[243],"ISPASS":[244],"Parboil":[246],"suites,":[247],"achieves":[249],"significant":[250],"performance":[253],"(12.1%":[254],"over":[255,259,264,268],"SRAM":[256,265],"5.8%":[258],"STT-MRAM)":[260],"energy":[262],"(3.3X":[263],"2.6X":[267],"STT-MRAM).":[269]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}