{"id":"https://openalex.org/W2983340695","doi":"https://doi.org/10.1145/3356045.3365385","title":"Compute cache for data parallel acceleration","display_name":"Compute cache for data parallel acceleration","publication_year":2019,"publication_date":"2019-10-13","ids":{"openalex":"https://openalex.org/W2983340695","doi":"https://doi.org/10.1145/3356045.3365385","mag":"2983340695"},"language":"en","primary_location":{"id":"doi:10.1145/3356045.3365385","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3356045.3365385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Workshop on Network on Chip Architectures","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043784059","display_name":"Reetu Das","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Reetu Das","raw_affiliation_strings":["University of Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043784059"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14349074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9900000095367432,"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":0.9900000095367432,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9458000063896179,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10320","display_name":"Neural Networks and Applications","score":0.9316999912261963,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8882117867469788},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.8112345337867737},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.8043487071990967},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.7728193998336792},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7529635429382324},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.7418845891952515},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.7100359201431274},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.6826468706130981},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.5748884677886963},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.5136675238609314},{"id":"https://openalex.org/keywords/mesi-protocol","display_name":"MESI protocol","score":0.42377400398254395},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.35307762026786804},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.332073450088501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8882117867469788},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.8112345337867737},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.8043487071990967},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.7728193998336792},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7529635429382324},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.7418845891952515},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.7100359201431274},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.6826468706130981},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.5748884677886963},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.5136675238609314},{"id":"https://openalex.org/C120936851","wikidata":"https://www.wikidata.org/wiki/Q1408065","display_name":"MESI protocol","level":5,"score":0.42377400398254395},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.35307762026786804},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.332073450088501}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3356045.3365385","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3356045.3365385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Workshop on Network on Chip Architectures","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G339059864","display_name":null,"funder_award_id":"1652294","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2098406302","https://openalex.org/W2184371594","https://openalex.org/W4312759433","https://openalex.org/W2535115842","https://openalex.org/W2734782074","https://openalex.org/W2148571123","https://openalex.org/W2546991807","https://openalex.org/W2801630946","https://openalex.org/W273173017","https://openalex.org/W2539551105"],"abstract_inverted_index":{"The":[0],"talk":[1],"will":[2,32],"start":[3],"with":[4,77],"an":[5],"overview":[6],"of":[7,16,55,79],"our":[8],"work":[9,66],"Neural":[10,63],"Cache":[11,37,74],"architecture":[12,38],"which":[13,42],"is":[14],"capable":[15,54],"fully":[17,20],"executing":[18],"convolutional,":[19],"connected,":[21],"pooling":[22],"layers":[23],"in-cache":[24,81],"and":[25,83,100],"also":[26],"supports":[27],"quantization":[28],"in-cache.":[29],"Then":[30],"I":[31],"present":[33],"a":[34,68,93],"versatile":[35],"Compute":[36,73],"named":[39],"Duality":[40],"Cache,":[41],"re-purposes":[43],"cache":[44],"structures":[45],"to":[46,71],"transform":[47],"them":[48],"into":[49],"massively":[50],"parallel":[51,59],"compute":[52],"units":[53],"running":[56],"arbitrary":[57],"data":[58],"workloads":[60],"including":[61],"Deep":[62],"Networks.":[64],"Our":[65],"presents":[67],"holistic":[69],"approach":[70],"building":[72],"system":[75],"stack":[76],"techniques":[78],"performing":[80],"floating-point":[82],"fixed-point":[84],"arithmetic,":[85],"transcendental":[86],"functions,":[87],"enabling":[88],"SIMT":[89],"execution":[90],"model,":[91],"designing":[92],"compiler":[94],"that":[95],"accepts":[96],"existing":[97],"CUDA":[98],"programs,":[99],"providing":[101],"flexibility":[102],"in":[103],"adapting":[104],"for":[105],"various":[106],"workload":[107],"characteristics.":[108]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}