{"id":"https://openalex.org/W4404134088","doi":"https://doi.org/10.1145/3649329.3658494","title":"SARIS: Accelerating Stencil Computations on Energy-Efficient RISC-V Compute Clusters with Indirect Stream Registers","display_name":"SARIS: Accelerating Stencil Computations on Energy-Efficient RISC-V Compute Clusters with Indirect Stream Registers","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404134088","doi":"https://doi.org/10.1145/3649329.3658494"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3658494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649329.3658494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052998498","display_name":"Paul Scheffler","orcid":"https://orcid.org/0000-0003-4230-1381"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Paul Scheffler","raw_affiliation_strings":["Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4230-1381","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094583316","display_name":"Luca Colagrande","orcid":"https://orcid.org/0000-0002-7986-1975"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luca Colagrande","raw_affiliation_strings":["Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7986-1975","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043408422","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0001-8068-3806"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["CH","IT"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland","University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8068-3806","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3549,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80310042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/stencil","display_name":"Stencil","score":0.9447146058082581},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6967997550964355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.679653525352478},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6167926788330078},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4727626442909241},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4314674437046051},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.17638781666755676},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17484217882156372}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9447146058082581},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6967997550964355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.679653525352478},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6167926788330078},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4727626442909241},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4314674437046051},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17638781666755676},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17484217882156372},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3649329.3658494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649329.3658494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/1005133","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/1005133","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2173545083","https://openalex.org/W2899691047","https://openalex.org/W2996929894","https://openalex.org/W3013692244","https://openalex.org/W3016309475","https://openalex.org/W3099814709","https://openalex.org/W3105514082","https://openalex.org/W3112773671","https://openalex.org/W4323065793","https://openalex.org/W4376123125","https://openalex.org/W4376632753","https://openalex.org/W4388469806"],"related_works":["https://openalex.org/W2039378765","https://openalex.org/W2003798513","https://openalex.org/W2151764765","https://openalex.org/W2890431355","https://openalex.org/W4376875029","https://openalex.org/W3149084271","https://openalex.org/W4247008888","https://openalex.org/W2150319905","https://openalex.org/W2962978274","https://openalex.org/W1429949169"],"abstract_inverted_index":{"Stencil":[0],"codes":[1,42],"are":[2],"performance-critical":[3],"in":[4],"many":[5],"compute-intensive":[6],"applications,":[7],"but":[8],"suffer":[9],"from":[10],"significant":[11,54],"address":[12],"calculation":[13],"and":[14,25,63,95],"irregular":[15],"memory":[16],"access":[17],"overheads.":[18],"This":[19],"work":[20],"presents":[21],"SARIS,":[22],"a":[23,78,105],"general":[24],"highly":[26],"flexible":[27],"methodology":[28],"for":[29,39],"stencil":[30,41],"acceleration":[31],"using":[32],"register-mapped":[33],"indirect":[34,50],"streams.":[35],"We":[36],"demonstrate":[37],"SARIS":[38],"various":[40],"on":[43,73],"an":[44,70,84,90],"eight-core":[45],"RISC-V":[46],"compute":[47,103],"cluster":[48],"with":[49],"stream":[51],"registers,":[52],"achieving":[53],"speedups":[55],"of":[56,61,67,88,93,101],"2.72x,":[57],"near-ideal":[58],"FPU":[59,86],"utilizations":[60],"81%,":[62],"energy":[64],"efficiency":[65],"improvements":[66],"1.58x":[68],"over":[69],"RV32G":[71],"baseline":[72],"average.":[74],"Scaling":[75],"out":[76],"to":[77,97],"256-core":[79],"manycore":[80],"system,":[81],"we":[82],"estimate":[83],"average":[85,91],"utilization":[87],"64%,":[89],"speedup":[92],"2.14x,":[94],"up":[96],"15%":[98],"higher":[99],"fractions":[100],"peak":[102],"than":[104],"leading":[106],"GPU":[107],"code":[108],"generator.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
