{"id":"https://openalex.org/W7166305367","doi":"https://doi.org/10.1145/3801487.3801823","title":"FlIP: Flow-Based Instruction Processing for Out-of-Order Scheduling in GPGPUs","display_name":"FlIP: Flow-Based Instruction Processing for Out-of-Order Scheduling in GPGPUs","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7166305367","doi":"https://doi.org/10.1145/3801487.3801823"},"language":null,"primary_location":{"id":"doi:10.1145/3801487.3801823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3801823","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 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3801487.3801823","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139489443","display_name":"Munawira Kotyad","orcid":"https://orcid.org/0009-0004-8999-7480"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Munawira Kotyad","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Mumbai, Maharashtra, India"],"raw_orcid":"https://orcid.org/0009-0004-8999-7480","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Bombay, Mumbai, Maharashtra, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133570753","display_name":"YASHVARDHAN RATHORE","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yashvardhan Rathore","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, Maharashtra, India"],"raw_orcid":"https://orcid.org/0009-0006-0398-4078","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, Maharashtra, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139464810","display_name":"Ganesh Sai Shanmukhi","orcid":"https://orcid.org/0009-0007-3731-2365"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ganesh Sai Shanmukhi","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, Maharashtra, India"],"raw_orcid":"https://orcid.org/0009-0007-3731-2365","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, Maharashtra, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073587430","display_name":"Virendra Singh","orcid":"https://orcid.org/0000-0002-7035-7844"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Virendra Singh","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, Maharashtra, India"],"raw_orcid":"https://orcid.org/0000-0002-7035-7844","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, Maharashtra, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.954047,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9316999912261963,"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":0.9316999912261963,"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":0.02160000056028366,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.012000000104308128,"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/scheduling","display_name":"Scheduling (production processes)","score":0.6114000082015991},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.5041999816894531},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.39959999918937683},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3709999918937683},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.33649998903274536},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.326200008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8600000143051147},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5669999718666077},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2939000129699707},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3801487.3801823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3801823","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 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3801487.3801823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3801823","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 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1971421905","https://openalex.org/W2080592089","https://openalex.org/W2315868086","https://openalex.org/W2417175077","https://openalex.org/W2936491961","https://openalex.org/W2991043486","https://openalex.org/W3088700869","https://openalex.org/W3102510044","https://openalex.org/W3133253223","https://openalex.org/W3175298944","https://openalex.org/W4211127289","https://openalex.org/W4242976792","https://openalex.org/W4360831990","https://openalex.org/W4381389673","https://openalex.org/W4382047833","https://openalex.org/W4401211787","https://openalex.org/W4403262308","https://openalex.org/W4405387414"],"related_works":[],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"achieve":[4],"high":[5],"throughput":[6],"by":[7,52],"exploiting":[8,53],"abundant":[9],"thread-level":[10],"parallelism":[11,55],"(TLP)":[12],"to":[13,38,66,68],"hide":[14],"long-latency":[15],"operations.":[16],"However,":[17],"many":[18],"emerging":[19],"general-purpose":[20],"and":[21,28,36,41,64],"scientific":[22],"workloads":[23],"exhibit":[24],"irregular":[25],"control":[26],"flow":[27],"limited":[29],"data-level":[30],"parallelism,":[31],"which":[32],"reduce":[33],"effective":[34],"TLP":[35],"lead":[37],"frequent":[39],"stalls":[40,51],"underutilized":[42],"execution":[43,47],"resources.":[44],"While":[45],"out-of-order":[46,59],"can":[48],"mitigate":[49],"such":[50],"instruction-level":[54],"(ILP),":[56],"conventional":[57],"CPU-style":[58],"approaches":[60],"are":[61],"prohibitively":[62],"complex":[63],"costly":[65],"scale":[67],"GPUs.":[69]},"counts_by_year":[],"updated_date":"2026-06-28T06:20:29.262167","created_date":"2026-06-28T00:00:00"}