{"id":"https://openalex.org/W4407953488","doi":"https://doi.org/10.1145/3706628.3708822","title":"Tile-Level Pipeline for Linear Scalable Stencil Computation on AMD AI Engines","display_name":"Tile-Level Pipeline for Linear Scalable Stencil Computation on AMD AI Engines","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4407953488","doi":"https://doi.org/10.1145/3706628.3708822"},"language":"en","primary_location":{"id":"doi:10.1145/3706628.3708822","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3706628.3708822","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3706628.3708822","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 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","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/10.1145/3706628.3708822","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026897196","display_name":"Zhenyu Xu","orcid":"https://orcid.org/0000-0002-3635-2409"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhenyu Xu","raw_affiliation_strings":["Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0002-3635-2409","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013631588","display_name":"Miaoxiang Yu","orcid":"https://orcid.org/0000-0002-4382-9009"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miaoxiang Yu","raw_affiliation_strings":["Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0002-4382-9009","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016662307","display_name":"Yanze Zhang","orcid":"https://orcid.org/0009-0003-7128-3343"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yazhe Zhang","raw_affiliation_strings":["Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0009-0003-7128-3343","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020091845","display_name":"Jillian Cai","orcid":"https://orcid.org/0009-0001-5006-223X"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jillian Cai","raw_affiliation_strings":["Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0009-0001-5006-223X","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053032127","display_name":"Qing Yang","orcid":"https://orcid.org/0000-0002-3330-1542"},"institutions":[{"id":"https://openalex.org/I17626003","display_name":"University of Rhode Island","ror":"https://ror.org/013ckk937","country_code":"US","type":"education","lineage":["https://openalex.org/I17626003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Yang","raw_affiliation_strings":["University of Rhode Island, Kingston, RI, USA"],"raw_orcid":"https://orcid.org/0000-0002-3330-1542","affiliations":[{"raw_affiliation_string":"University of Rhode Island, Kingston, RI, USA","institution_ids":["https://openalex.org/I17626003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062578450","display_name":"Tao Wei","orcid":"https://orcid.org/0000-0002-4765-1826"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Wei","raw_affiliation_strings":["Clemson University, Clemson, SC, USA"],"raw_orcid":"https://orcid.org/0000-0002-4765-1826","affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5026897196"],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02539846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"172","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9958999752998352,"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":0.9958999752998352,"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/T12162","display_name":"Cellular Automata and Applications","score":0.9857000112533569,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9843000173568726,"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/stencil","display_name":"Stencil","score":0.7996230125427246},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7378337383270264},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.7305570840835571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6834739446640015},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6274040341377258},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5301989316940308},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4942662715911865},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3163880407810211},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2181946337223053},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18726935982704163}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7996230125427246},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7378337383270264},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.7305570840835571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6834739446640015},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6274040341377258},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5301989316940308},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4942662715911865},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3163880407810211},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2181946337223053},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18726935982704163},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3706628.3708822","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3706628.3708822","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3706628.3708822","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 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3706628.3708822","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3706628.3708822","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3706628.3708822","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 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G3327242161","display_name":null,"funder_award_id":"N00014-24-1-2623","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G742931074","display_name":null,"funder_award_id":"2027069, 2438325, 2106750","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407953488.pdf"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2142063750","https://openalex.org/W2899691047","https://openalex.org/W4318719410","https://openalex.org/W4388855690","https://openalex.org/W4389140831","https://openalex.org/W4400489024"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W2114959296","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2392765154","https://openalex.org/W2564509292","https://openalex.org/W2177020196","https://openalex.org/W1429949169","https://openalex.org/W3139770841"],"abstract_inverted_index":{"Stencil":[0],"computation":[1,81],"is":[2],"an":[3],"essential":[4],"method,":[5],"particularly":[6],"useful":[7],"for":[8,27,79],"numerical":[9],"simulations":[10],"in":[11,64],"areas":[12],"like":[13],"acoustics,":[14],"heat":[15],"transfer,":[16],"and":[17,103],"electromagnetism.":[18],"Recent":[19],"studies":[20],"have":[21],"utilized":[22],"AMD":[23],"AI":[24],"Engines":[25],"(AIEs)":[26],"stencil":[28,80],"computations":[29],"by":[30],"configuring":[31],"multiple":[32],"AIE":[33,69,101,109],"tiles":[34,110],"within":[35],"a":[36,74],"Compute":[37],"Unit":[38],"to":[39,58],"exploit":[40],"task-level":[41],"parallelism,":[42],"achieving":[43],"notable":[44],"speedup":[45],"through":[46],"concurrent":[47],"task":[48],"execution.":[49],"However,":[50],"this":[51],"setup":[52],"suffers":[53],"from":[54],"suboptimal":[55],"performance":[56,94],"due":[57],"high":[59],"memory":[60,86],"bandwidth":[61],"demands,":[62],"resulting":[63],"underutilization":[65],"of":[66,100,107],"the":[67,98,112],"available":[68],"tiles.":[70],"This":[71,88],"work":[72],"introduces":[73],"Tile-Level":[75],"Pipeline":[76],"architecture":[77],"designed":[78],"that":[82],"operates":[83],"with":[84,97],"constant":[85],"bandwidth.":[87],"approach":[89],"achieves":[90],"linear":[91],"scalability,":[92],"where":[93],"scales":[95],"linearly":[96],"number":[99],"tiles,":[102],"ensures":[104],"full":[105],"utilization":[106],"all":[108],"on":[111],"chip.":[113],"We":[114],"empirically":[115],"demonstrate":[116],"these":[117],"benefits":[118],"using":[119],"AIEs.":[120]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}