{"id":"https://openalex.org/W2946049946","doi":"https://doi.org/10.1145/3316781.3317810","title":"Efficient GPU NVRAM Persistence with Helper Warps","display_name":"Efficient GPU NVRAM Persistence with Helper Warps","publication_year":2019,"publication_date":"2019-05-23","ids":{"openalex":"https://openalex.org/W2946049946","doi":"https://doi.org/10.1145/3316781.3317810","mag":"2946049946"},"language":"en","primary_location":{"id":"doi:10.1145/3316781.3317810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3316781.3317810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Design Automation Conference 2019","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/A5012107181","display_name":"Sui Chen","orcid":"https://orcid.org/0000-0001-7251-7760"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sui Chen","raw_affiliation_strings":["Louisiana State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana State University","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007287914","display_name":"Faen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210141904","display_name":"EduInnovation","ror":"https://ror.org/03s3qsz11","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210141904"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Faen Zhang","raw_affiliation_strings":["Ainnovation Technology Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ainnovation Technology Ltd","institution_ids":["https://openalex.org/I4210141904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349498","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0001-8623-8682"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["SKLCA, Institute of Computing Technology, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SKLCA, Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101893942","display_name":"Lu Peng","orcid":"https://orcid.org/0000-0003-3545-286X"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Peng","raw_affiliation_strings":["Louisiana State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Louisiana State University","institution_ids":["https://openalex.org/I121820613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983999729156494,"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":0.8128154277801514},{"id":"https://openalex.org/keywords/non-volatile-random-access-memory","display_name":"Non-volatile random-access memory","score":0.77051842212677},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5854432582855225},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5623272061347961},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4997553825378418},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.42388859391212463},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4166591763496399},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3545583486557007},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2665777802467346},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23286816477775574},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.20837032794952393},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.17336681485176086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128154277801514},{"id":"https://openalex.org/C34172316","wikidata":"https://www.wikidata.org/wiki/Q499024","display_name":"Non-volatile random-access memory","level":5,"score":0.77051842212677},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5854432582855225},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5623272061347961},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4997553825378418},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.42388859391212463},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4166591763496399},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3545583486557007},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2665777802467346},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23286816477775574},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.20837032794952393},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.17336681485176086},{"id":"https://openalex.org/C87907426","wikidata":"https://www.wikidata.org/wiki/Q6815755","display_name":"Memory refresh","level":4,"score":0.0},{"id":"https://openalex.org/C92855701","wikidata":"https://www.wikidata.org/wiki/Q5830907","display_name":"Computer memory","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3316781.3317810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3316781.3317810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Design Automation Conference 2019","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":19,"referenced_works":["https://openalex.org/W2005887179","https://openalex.org/W2018384083","https://openalex.org/W2113751407","https://openalex.org/W2134158653","https://openalex.org/W2138218143","https://openalex.org/W2150662965","https://openalex.org/W2170666978","https://openalex.org/W2335340700","https://openalex.org/W2545744347","https://openalex.org/W2593354228","https://openalex.org/W2610308442","https://openalex.org/W2611473431","https://openalex.org/W2612252783","https://openalex.org/W2626705819","https://openalex.org/W2728001126","https://openalex.org/W2742513757","https://openalex.org/W2934889147","https://openalex.org/W4238433345","https://openalex.org/W4244155122"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2891987081","https://openalex.org/W2097990792","https://openalex.org/W2169710001","https://openalex.org/W2542548909","https://openalex.org/W2110995678"],"abstract_inverted_index":{"Non-volatile":[0],"Random-Access":[1],"Memories":[2],"(NVRAM)":[3],"have":[4],"emerged":[5],"in":[6,136],"recent":[7],"years":[8],"to":[9,61,84,121],"bridge":[10],"the":[11,15,24,89,96],"performance":[12],"gap":[13],"between":[14],"main":[16],"memory":[17],"and":[18,107,115,118],"external":[19],"storage":[20],"devices.":[21],"To":[22,75],"utilize":[23],"non-volatility":[25],"of":[26,52,63,88,92,98,105,112,134],"NVRAMs,":[27],"programs":[28],"should":[29],"allow":[30],"durable":[31],"stores,":[32],"meaning":[33],"consistency":[34],"must":[35],"be":[36],"maintained":[37],"during":[38],"a":[39,103],"power":[40],"loss":[41],"event.":[42],"GPUs":[43],"are":[44],"designed":[45],"with":[46,55],"high":[47,50,131],"throughput,":[48],"leveraging":[49],"degrees":[51],"parallelism.":[53],"However,":[54],"lower":[56],"NVRAM":[57,66,127],"write":[58],"bandwidths":[59],"compared":[60],"that":[62],"DRAMs,":[64],"using":[65,81],"as":[67,130,132],"is":[68,119],"may":[69],"yield":[70],"suboptimal":[71],"overall":[72],"system":[73],"performance.":[74],"address":[76],"this":[77],"problem,":[78],"we":[79],"propose":[80],"Helper":[82],"Warps":[83],"move":[85],"persistence":[86],"out":[87],"critical":[90],"path":[91],"transaction":[93],"execution,":[94],"alleviating":[95],"impact":[97],"latencies.":[99],"Our":[100],"mechanism":[101],"achieves":[102],"speedup":[104],"4.4":[106],"1.5":[108],"under":[109],"bandwidth":[110,128],"limits":[111],"1.6":[113],"GB/s":[114,117,135],"12":[116],"projected":[120],"maintain":[122],"speed":[123],"advantage":[124],"even":[125],"when":[126],"gets":[129],"hundreds":[133],"certain":[137],"cases.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}