{"id":"https://openalex.org/W7204759077","doi":"https://doi.org/10.5281/zenodo.22197587","title":"OpenNUMA : Open Source Neural Unified Memory Allocator","display_name":"OpenNUMA : Open Source Neural Unified Memory Allocator","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204759077","doi":"https://doi.org/10.5281/zenodo.22197587"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22197587","doi":"https://doi.org/10.5281/zenodo.22197587","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22197587","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"volume":null,"type":"software","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22197587","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141204278","display_name":"Md. Muminul Islam","orcid":"https://orcid.org/0009-0003-5463-8771","observed_orcids":["https://orcid.org/0009-0003-5463-8771"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Islam, Md. Muminul","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0009-0003-5463-8771","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5141204278"],"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":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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/memory-allocators","display_name":"memory allocators","score":0.6650000214576721},{"id":"https://openalex.org/keywords/integrated-gpu","display_name":"integrated GPU","score":0.9100000262260437},{"id":"https://openalex.org/keywords/cpu-gpu-data-transfer","display_name":"CPU-GPU data transfer","score":0.703000009059906},{"id":"https://openalex.org/keywords/memory-pooling","display_name":"memory pooling","score":0.753000020980835},{"id":"https://openalex.org/keywords/thread-safety","display_name":"thread safety","score":0.5839999914169312},{"id":"https://openalex.org/keywords/memory-management","display_name":"memory management","score":0.40799999237060547}],"concepts":[{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.9128999710083008},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467000126838684},{"id":"https://openalex.org/C95203288","wikidata":"https://www.wikidata.org/wiki/Q221682","display_name":"Semaphore","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46459999680519104},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.4239000082015991},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C34339311","wikidata":"https://www.wikidata.org/wiki/Q1050390","display_name":"C dynamic memory allocation","level":4,"score":0.36390000581741333},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.3303999900817871},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.3140999972820282},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C7042729","wikidata":"https://www.wikidata.org/wiki/Q2289219","display_name":"SPMD","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C124343487","wikidata":"https://www.wikidata.org/wiki/Q1046373","display_name":"Critical section","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22197587","doi":"https://doi.org/10.5281/zenodo.22197587","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22197587","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},{"id":"doi:10.5281/zenodo.22197588","doi":"https://doi.org/10.5281/zenodo.22197588","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22197588","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22197587","doi":"https://doi.org/10.5281/zenodo.22197587","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22197587","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7206207062","https://openalex.org/W4394712068","https://openalex.org/W6885101983","https://openalex.org/W4379518600","https://openalex.org/W4403815862","https://openalex.org/W2270772303","https://openalex.org/W7099804453","https://openalex.org/W4406164050","https://openalex.org/W2984365163","https://openalex.org/W2520424219"],"abstract_inverted_index":{"Neural":[0,61],"network":[1],"and":[2,90,96,107,129,146,177,191,215,240],"machine-learning":[3],"workloads":[4,43,109,179],"commonly":[5],"rely":[6],"on":[7,83],"dedicated":[8],"GPUs":[9,18],"with":[10,16],"tensor":[11,142,144,147,221],"cores,":[12],"While":[13],"existing":[14,34],"systems":[15,37],"integrated":[17,40],"(iGPUs)may":[19],"have":[20],"unused":[21],"computing":[22],"power.":[23],"This":[24,120],"study":[25,80],"investigates":[26],"whether":[27],"a":[28,66,101,155],"custom":[29,67],"memory":[30,56,123],"allocator":[31,68,212,231],"can":[32,203,213],"enable":[33],"or":[35],"older":[36],"to":[38,76,110,181,197,206],"utilize":[39],"GPUsfor":[41],"such":[42,211],"without":[44],"requiring":[45],"hardware-level":[46],"modification.":[47],"The":[48,184],"proposed":[49,75],"method":[50],"does":[51],"not":[52,224],"require":[53],"unified":[54],"virtual":[55],"mappings.":[57],"OpenNUMA":[58,74,99,139,187,209],"(Open":[59],"Source":[60],"Unified":[62,92],"Memory":[63,94],"Allocator)":[64],"is":[65,188],"developed":[69],"for":[70,175,192],"these":[71],"tasks.":[72],"Although":[73,200],"platform-independent,":[77],"in":[78,158],"this":[79],"it":[81],"relies":[82],"PyTorch":[84,230],"XPU":[85],"backend,":[86],"Intel":[87],"oneAPI":[88],"SYCL":[89],"Shared":[91,93],"(USM),":[95],"Microsoft":[97],"Windows.":[98],"provides":[100],"memory-management":[102],"layer":[103],"that":[104],"allows":[105],"CPU":[106],"iGPU":[108,141,176],"access":[111,222],"shared":[112,220],"system-memory":[113],"allocations":[114],"through":[115,149,227],"the":[116,201,228],"parent":[117],"application":[118],"interface.":[119],"prototype":[121],"implements":[122],"pooling,":[124],"allocation":[125],"tracking,":[126,128],"deallocation":[127],"thread":[130],"safety":[131],"using":[132],"mutex":[133],"locking.":[134],"Feasibility":[135],"testing":[136,153,170],"successfully":[137],"shows":[138,210],"initialization,":[140],"allocation,":[143],"operations,":[145],"aliasing":[148],"PyTorch.":[150],"CPUto-iGPU":[151],"transfer":[152,159,163],"achieved":[154],"34.076%":[156],"reduction":[157],"time,":[160],"while":[161],"iGPU-to-CPU":[162],"time":[164],"increased":[165],"by":[166],"5.258%.":[167],"General":[168],"workload":[169],"showed":[171],"minimal":[172],"performance":[173,185],"differences":[174],"neural-network":[178],"compared":[180,196],"default":[182,198],"allocator.":[183,199],"of":[186],"nearly":[189],"identical":[190],"some":[193],"cases":[194],"improved":[195,238],"results":[202],"vary":[204],"due":[205],"different":[207],"systems,":[208],"exist":[214],"perform":[216],"effectively.":[217],"However,":[218],"CPU-iGPU":[219],"could":[223],"be":[225],"verified":[226],"current":[229],"interface.Future":[232],"work":[233],"will":[234],"investigate":[235],"memory-release":[236],"mechanisms,":[237],"synchronization,":[239],"queue":[241],"tracking.":[242]},"counts_by_year":[],"updated_date":"2026-10-09T09:14:12.587421","created_date":"2026-09-01T00:00:00"}