{"id":"https://openalex.org/W7139966203","doi":"https://doi.org/10.48550/arxiv.2603.18690","title":"TurboMem: High-Performance Lock-Free Memory Pool with Transparent Huge Page Auto-Merging for DPDK","display_name":"TurboMem: High-Performance Lock-Free Memory Pool with Transparent Huge Page Auto-Merging for DPDK","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7139966203","doi":"https://doi.org/10.48550/arxiv.2603.18690"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.18690","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18690","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.18690","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130230915","display_name":"Junyi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Junyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5130230915"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8880000114440918,"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":0.8880000114440918,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.028999999165534973,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.023900000378489494,"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/translation-lookaside-buffer","display_name":"Translation lookaside buffer","score":0.9534000158309937},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7009000182151794},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6013000011444092},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5623999834060669},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5440999865531921},{"id":"https://openalex.org/keywords/page","display_name":"Page","score":0.5400000214576721},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4684000015258789},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.4503999948501587}],"concepts":[{"id":"https://openalex.org/C116007543","wikidata":"https://www.wikidata.org/wiki/Q1071403","display_name":"Translation lookaside buffer","level":4,"score":0.9534000158309937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8432999849319458},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7009000182151794},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5796999931335449},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5623999834060669},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5440999865531921},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5425999760627747},{"id":"https://openalex.org/C33925742","wikidata":"https://www.wikidata.org/wiki/Q361698","display_name":"Page","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4684000015258789},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4050999879837036},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.36039999127388},{"id":"https://openalex.org/C191015642","wikidata":"https://www.wikidata.org/wiki/Q1132459","display_name":"Fragmentation (computing)","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C174839445","wikidata":"https://www.wikidata.org/wiki/Q1134386","display_name":"Lock (firearm)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.2824999988079071},{"id":"https://openalex.org/C177950962","wikidata":"https://www.wikidata.org/wiki/Q10997658","display_name":"Non-volatile memory","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.18690","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18690","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.18690","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18690","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"High-speed":[0],"packet":[1,20,176],"processing":[2],"on":[3,9,38,165,246],"multicore":[4],"CPUs":[5],"places":[6],"extreme":[7],"demands":[8],"memory":[10,17,72,96],"allocators.":[11],"In":[12],"systems":[13],"like":[14],"DPDK,":[15],"fixed-size":[16],"pools":[18,125],"back":[19],"buffers":[21],"(mbufs)":[22],"to":[23,85,126,180,189,235],"avoid":[24],"costly":[25],"dynamic":[26],"allocation.":[27],"However,":[28],"even":[29],"DPDK's":[30],"optimized":[31],"mempool":[32,193],"faces":[33],"scalability":[34],"limits:":[35],"lock":[36],"contention":[37],"the":[39,134],"shared":[40],"ring,":[41],"cache-coherence":[42],"ping-pong":[43],"between":[44],"cores,":[45],"and":[46,82,87,111,148,155,213,239,258],"heavy":[47],"TLB":[48,76,184,242],"pressure":[49],"from":[50,158],"thousands":[51],"of":[52,136],"small":[53],"pages.":[54,197],"To":[55],"mitigate":[56],"these":[57,100],"issues,":[58],"DPDK":[59,192],"typically":[60],"uses":[61],"explicit":[62,195],"huge":[63,137,196,208],"pages":[64,129,138,209],"(2":[65],"MB":[66,128],"or":[67],"1":[68],"GB)":[69],"for":[70],"its":[71,159],"pools.":[73],"This":[74],"reduces":[75],"misses":[77,185],"but":[78],"requires":[79],"manual":[80,140],"configuration":[81],"can":[83,204],"lead":[84],"fragmentation":[86],"inflexibility.":[88],"We":[89,142],"propose":[90],"TurboMem,":[91],"a":[92,104,166,190,263],"novel":[93],"C++":[94,216],"template-based":[95],"pool":[97],"that":[98,173,201,214],"addresses":[99],"challenges.":[101],"TurboMem":[102,132,174],"combines":[103],"fully":[105],"lock-free":[106,217],"design":[107],"(using":[108],"atomic":[109],"stacks":[110],"per-core":[112],"local":[113,160],"caches)":[114],"with":[115,194],"Transparent":[116],"Huge":[117],"Page":[118],"(THP)":[119],"auto":[120],"merging.":[121],"By":[122],"automatically":[123],"promoting":[124],"2":[127],"via":[130],"madvise(MADV_HUGEPAGE),":[131],"achieves":[133],"benefits":[135],"without":[139],"setup.":[141],"also":[143],"enforce":[144],"strict":[145],"NUMA":[146],"locality":[147],"CPU":[149],"affinity,":[150],"so":[151],"each":[152],"core":[153],"allocates":[154],"frees":[156],"objects":[157],"node.":[161],"Using":[162],"Intel":[163,253],"VTune":[164,254],"single-socket":[167],"100":[168],"Gbps":[169],"testbed,":[170],"we":[171],"show":[172],"boosts":[175],"throughput":[177,238],"by":[178,186],"up":[179],"28%":[181,236],"while":[182],"reducing":[183],"41%":[187,240],"compared":[188],"standard":[191],"These":[198],"results":[199],"demonstrate":[200],"THP":[202],"auto-merging":[203],"outperform":[205],"manually":[206],"reserved":[207],"in":[210,222,230,262],"low-fragmentation":[211],"scenarios,":[212],"modern":[215],"programming":[218],"yields":[219],"practical":[220],"gains":[221],"data-plane":[223],"software.":[224],"Note:":[225],"The":[226],"performance":[227],"claims":[228],"reported":[229],"this":[231],"preliminary":[232],"version":[233],"(up":[234],"higher":[237],"fewer":[241],"misses)":[243],"are":[244,255],"based":[245],"mock":[247],"benchmarks.":[248],"Comprehensive":[249],"real-system":[250],"evaluations":[251],"using":[252],"currently":[256],"underway":[257],"will":[259],"be":[260],"presented":[261],"future":[264],"revision.":[265]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-21T00:00:00"}