{"id":"https://openalex.org/W4409714186","doi":"https://doi.org/10.1145/3723851.3726984","title":"eGPU: Extending eBPF Programmability and Observability to GPUs","display_name":"eGPU: Extending eBPF Programmability and Observability to GPUs","publication_year":2025,"publication_date":"2025-03-30","ids":{"openalex":"https://openalex.org/W4409714186","doi":"https://doi.org/10.1145/3723851.3726984"},"language":"en","primary_location":{"id":"doi:10.1145/3723851.3726984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3723851.3726984","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3723851.3726984","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 4th Workshop on Heterogeneous Composable and Disaggregated Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3723851.3726984","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103214236","display_name":"Yiwei Yang","orcid":"https://orcid.org/0000-0001-8011-5868"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yiwei Yang","raw_affiliation_strings":["UC Santa Cruz, Santa Cruz, California, USA"],"affiliations":[{"raw_affiliation_string":"UC Santa Cruz, Santa Cruz, California, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767817","display_name":"Tong Yu","orcid":"https://orcid.org/0000-0002-1819-5614"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Yu","raw_affiliation_strings":["Eunomia Inc, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Eunomia Inc, Wuhan, Hubei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110949983","display_name":"Yusheng Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusheng Zheng","raw_affiliation_strings":["UC Santa Cruz, Santa Cruz, California, USA"],"affiliations":[{"raw_affiliation_string":"UC Santa Cruz, Santa Cruz, California, USA","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054902250","display_name":"Andrew Quinn","orcid":"https://orcid.org/0000-0002-0785-4119"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Quinn","raw_affiliation_strings":["UC Santa Cruz, Santa Cruz, California, USA"],"affiliations":[{"raw_affiliation_string":"UC Santa Cruz, Santa Cruz, California, USA","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103214236"],"corresponding_institution_ids":["https://openalex.org/I185103710"],"apc_list":null,"apc_paid":null,"fwci":4.9372,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93738977,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"79"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9965999722480774,"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":0.9955999851226807,"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/observability","display_name":"Observability","score":0.9226000905036926},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7920994758605957},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5183661580085754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0479256808757782}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9226000905036926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7920994758605957},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5183661580085754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0479256808757782},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3723851.3726984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3723851.3726984","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3723851.3726984","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 4th Workshop on Heterogeneous Composable and Disaggregated Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3723851.3726984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3723851.3726984","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3723851.3726984","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 4th Workshop on Heterogeneous Composable and Disaggregated Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409714186.pdf","grobid_xml":"https://content.openalex.org/works/W4409714186.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2789572737","https://openalex.org/W2979340153","https://openalex.org/W3006113130","https://openalex.org/W3136016992","https://openalex.org/W3199133416","https://openalex.org/W3200843682","https://openalex.org/W3205191816","https://openalex.org/W4312356560","https://openalex.org/W4394871790","https://openalex.org/W4401861976"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275"],"abstract_inverted_index":{"Precise":[0],"GPU":[1,50,79,94,130],"observability":[2],"and":[3,13,29,55,69,88,138],"programmability":[4],"are":[5],"essential":[6],"for":[7,44],"optimizing":[8],"performance":[9,57,121],"in":[10],"AI":[11],"workloads":[12],"other":[14],"computationally":[15],"intensive":[16],"high-performance":[17],"computing":[18],"(HPC)":[19],"applications.In":[20],"this":[21],"paper,":[22],"we":[23],"introduce":[24],"eGPU,":[25],"the":[26],"first":[27],"framework":[28],"eBPF":[30,35,83,106],"runtime":[31],"that":[32,101,112],"dynamically":[33,81,134],"offloads":[34],"bytecode":[36],"onto":[37],"GPUs":[38],"via":[39],"dynamic":[40,53],"PTX":[41,86],"injection.Designed":[42],"primarily":[43],"observability,":[45],"our":[46],"system":[47],"leverages":[48],"real-time":[49],"telemetry,":[51],"eBPF-based":[52],"instrumentation,":[54],"automated":[56],"analysis":[58],"to":[59,136],"pinpoint":[60],"bottlenecks":[61],"at":[62],"multiple":[63],"layers-including":[64],"kernel":[65],"execution,":[66],"memory":[67],"transfers,":[68],"heterogeneous":[70],"compute":[71],"orchestration-without":[72],"incurring":[73],"significant":[74],"overhead":[75,117],"or":[76],"interrupting":[77],"active":[78],"kernels.By":[80],"compiling":[82],"programs":[84],"into":[85,92],"snippets":[87],"injecting":[89],"them":[90],"directly":[91],"running":[93],"kernels,":[95],"eGPU":[96,113,123],"provides":[97],"fine-grained,":[98],"low-overhead":[99],"instrumentation":[100,116],"seamlessly":[102],"integrates":[103],"with":[104],"existing":[105],"ecosystems.Our":[107],"initial":[108],"micro-benchmark":[109],"evaluation":[110],"demonstrates":[111],"achieves":[114],"low":[115],"while":[118],"providing":[119],"high-resolution":[120],"insights.Ultimately,":[122],"opens":[124],"a":[125],"pathway":[126],"toward":[127],"future":[128],"programmable":[129],"infrastructures":[131],"capable":[132],"of":[133],"adapting":[135],"diverse":[137],"evolving":[139],"workload":[140],"requirements.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}