{"id":"https://openalex.org/W4391985770","doi":"https://doi.org/10.1145/3627535.3638502","title":"Shared Memory-contention-aware Concurrent DNN Execution for Diversely Heterogeneous System-on-Chips","display_name":"Shared Memory-contention-aware Concurrent DNN Execution for Diversely Heterogeneous System-on-Chips","publication_year":2024,"publication_date":"2024-02-20","ids":{"openalex":"https://openalex.org/W4391985770","doi":"https://doi.org/10.1145/3627535.3638502"},"language":"en","primary_location":{"id":"doi:10.1145/3627535.3638502","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627535.3638502","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3627535.3638502","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066438526","display_name":"Ismet Dagli","orcid":"https://orcid.org/0000-0002-1460-6906"},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ismet Dagli","raw_affiliation_strings":["Computer Science Department, Colorado School of Mines, Golden, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-1460-6906","affiliations":[{"raw_affiliation_string":"Computer Science Department, Colorado School of Mines, Golden, United States of America","institution_ids":["https://openalex.org/I167576493"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080092881","display_name":"Mehmet E. Belviranl\u0131","orcid":"https://orcid.org/0000-0001-9434-9833"},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet E. Belviranli","raw_affiliation_strings":["Computer Science Department, Colorado School of Mines, Golden, USA"],"raw_orcid":"https://orcid.org/0000-0001-9434-9833","affiliations":[{"raw_affiliation_string":"Computer Science Department, Colorado School of Mines, Golden, USA","institution_ids":["https://openalex.org/I167576493"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066438526"],"corresponding_institution_ids":["https://openalex.org/I167576493"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"243","last_page":"256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9994999766349792,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9980000257492065,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9979000091552734,"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":0.8602780699729919},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5756968259811401},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5162465572357178},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4598868787288666},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37122321128845215},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3202802538871765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8602780699729919},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5756968259811401},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5162465572357178},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4598868787288666},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37122321128845215},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3202802538871765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627535.3638502","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627535.3638502","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627535.3638502","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627535.3638502","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1022177737","https://openalex.org/W1480909796","https://openalex.org/W2067523571","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2409247164","https://openalex.org/W2606126819","https://openalex.org/W2725660063","https://openalex.org/W2901994046","https://openalex.org/W2903666872","https://openalex.org/W2910338735","https://openalex.org/W2914062858","https://openalex.org/W2928598815","https://openalex.org/W2969388332","https://openalex.org/W2981207549","https://openalex.org/W3010466514","https://openalex.org/W3013780467","https://openalex.org/W3017948916","https://openalex.org/W3091023227","https://openalex.org/W3110144974","https://openalex.org/W3110931771","https://openalex.org/W3112293503","https://openalex.org/W3119892279","https://openalex.org/W3135807226","https://openalex.org/W3140854437","https://openalex.org/W3153174751","https://openalex.org/W3158233068","https://openalex.org/W3169512402","https://openalex.org/W3174529902","https://openalex.org/W3197899274","https://openalex.org/W3206210071","https://openalex.org/W3207730694","https://openalex.org/W3213988574","https://openalex.org/W4213249026","https://openalex.org/W4249932213","https://openalex.org/W4282970339","https://openalex.org/W4283709177","https://openalex.org/W4293023061","https://openalex.org/W4293025058","https://openalex.org/W4293704347","https://openalex.org/W4312121086","https://openalex.org/W4313423332","https://openalex.org/W4385835157"],"related_works":["https://openalex.org/W1837558792","https://openalex.org/W2098482419","https://openalex.org/W4254638342","https://openalex.org/W1982466989","https://openalex.org/W2070983336","https://openalex.org/W1853437450","https://openalex.org/W4384344236","https://openalex.org/W2465501459","https://openalex.org/W2033847453","https://openalex.org/W2995170196"],"abstract_inverted_index":{"Two":[0],"distinguishing":[1],"features":[2],"of":[3,87],"state-of-the-art":[4],"mobile":[5],"and":[6,24,47,74,103,120,139,143,149],"autonomous":[7],"systems":[8,43],"are:":[9],"1)":[10],"There":[11],"are":[12],"often":[13],"multiple":[14],"workloads,":[15],"mainly":[16],"deep":[17],"neural":[18],"network":[19],"(DNN)":[20],"inference,":[21],"running":[22],"concurrently":[23,78],"continuously.":[25],"2)":[26],"They":[27],"operate":[28],"on":[29,115],"shared":[30,99],"memory":[31,100,133],"System-on-Chips":[32],"(SoC)":[33],"that":[34,72,129],"embed":[35],"heterogeneous":[36],"accelerators":[37,88],"tailored":[38],"for":[39],"specific":[40],"operations.":[41],"State-of-the-art":[42],"lack":[44],"efficient":[45],"performance":[46],"resource":[48],"management":[49],"techniques":[50],"necessary":[51],"to":[52,83,108,137,147,153],"either":[53],"maximize":[54],"total":[55,141],"system":[56],"throughput":[57,144],"or":[58],"minimize":[59,132],"end-to-end":[60],"workload":[61],"latency.":[62],"In":[63],"this":[64],"work,":[65],"we":[66],"propose":[67],"HaX-CoNN,":[68],"a":[69,84],"novel":[70],"scheme":[71,93],"characterizes":[73],"maps":[75],"layers":[76],"in":[77],"executing":[79],"DNN":[80],"inference":[81],"workloads":[82],"diverse":[85],"set":[86],"within":[89],"an":[90],"SoC.":[91],"Our":[92,125],"uniquely":[94],"takes":[95],"per-layer":[96],"execution":[97],"characteristics,":[98],"(SM)":[101],"contention,":[102],"inter-accelerator":[104],"transitions":[105],"into":[106],"account":[107],"find":[109],"optimal":[110],"schedules.":[111],"We":[112],"evaluate":[113],"HaX-CoNN":[114,130],"NVIDIA":[116,118],"Orin,":[117],"Xavier,":[119],"Qualcomm":[121],"Snapdragon":[122],"865":[123],"SoCs.":[124],"experimental":[126],"results":[127],"indicate":[128],"can":[131],"contention":[134],"by":[135,145],"up":[136,146],"45%":[138],"improve":[140],"latency":[142],"32%":[148],"29%,":[150],"respectively,":[151],"compared":[152],"the":[154],"state-of-the-art.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}