{"id":"https://openalex.org/W2064250379","doi":"https://doi.org/10.1109/coolchips.2013.6547920","title":"HW/SW approaches to accelerate GRAPES in an FU array","display_name":"HW/SW approaches to accelerate GRAPES in an FU array","publication_year":2013,"publication_date":"2013-04-01","ids":{"openalex":"https://openalex.org/W2064250379","doi":"https://doi.org/10.1109/coolchips.2013.6547920","mag":"2064250379"},"language":"en","primary_location":{"id":"doi:10.1109/coolchips.2013.6547920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coolchips.2013.6547920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE COOL Chips XVI","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/A5100392244","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0003-2824-7518"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382929","display_name":"Jun Yao","orcid":"https://orcid.org/0000-0003-2682-8650"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Yao","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan","Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Ikoma, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Ikoma, Japan#TAB#","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016596981","display_name":"Youhui Zhang","orcid":"https://orcid.org/0000-0003-2333-3580"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youhui Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523284","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0002-7987-2842"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074853381","display_name":"Yasuhiko Nakashima","orcid":"https://orcid.org/0000-0002-9457-5061"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Nakashima","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan","Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Ikoma, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Grad. Sch. of Inf. Sci., Nara Inst. of Sci. & Technol., Ikoma, Japan#TAB#","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108050911","display_name":"Weimin Zheng","orcid":"https://orcid.org/0000-0002-4450-5428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Zheng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9912999868392944,"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":0.9912999868392944,"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":0.982699990272522,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9797999858856201,"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/computer-science","display_name":"Computer science","score":0.7646615505218506},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.693052351474762},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.6225935220718384},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5961452722549438},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5269052982330322},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5254689455032349},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4800471067428589},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4715937376022339},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4709806442260742},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4567112326622009},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.44858336448669434},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.42863789200782776},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4260070025920868},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.42118024826049805},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.41951602697372437},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23410505056381226},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.2290845513343811},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10715633630752563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646615505218506},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.693052351474762},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.6225935220718384},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5961452722549438},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5269052982330322},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5254689455032349},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4800471067428589},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4715937376022339},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4709806442260742},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4567112326622009},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44858336448669434},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.42863789200782776},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4260070025920868},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.42118024826049805},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.41951602697372437},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23410505056381226},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2290845513343811},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10715633630752563},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coolchips.2013.6547920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coolchips.2013.6547920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE COOL Chips XVI","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1999101084","https://openalex.org/W2013505463","https://openalex.org/W2061929217","https://openalex.org/W2104088944","https://openalex.org/W2154786353","https://openalex.org/W3152199537"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2058965144","https://openalex.org/W4316371992","https://openalex.org/W2164382479","https://openalex.org/W2186216222","https://openalex.org/W2392765154","https://openalex.org/W2564509292","https://openalex.org/W2008005532","https://openalex.org/W2010557350","https://openalex.org/W3012895752"],"abstract_inverted_index":{"In":[0],"this":[1],"research,":[2],"a":[3,15,52,59,66,76,98],"high":[4],"performance":[5],"computing":[6],"weather":[7],"forecasting":[8],"application":[9],"GRAPES":[10],"has":[11,65],"been":[12],"tuned":[13],"onto":[14],"functional":[16],"unit":[17],"(FU)":[18],"array":[19,62],"based":[20],"architecture.":[21],"Software":[22],"and":[23,34],"hardware":[24],"approaches":[25],"are":[26],"specifically":[27],"employed":[28],"to":[29,37],"increase":[30,86],"the":[31,39,71,85,93],"data":[32,35],"locality":[33],"reuse":[36],"accelerate":[38],"stencil":[40],"computation":[41],"in":[42,92,97,102],"GRAPES.":[43],"The":[44],"simulation":[45],"results":[46],"indicate":[47],"that":[48],"we":[49],"can":[50,81],"achieve":[51],"per-core":[53],"average":[54],"IPC":[55],"of":[56,75,87],"12.3":[57],"within":[58],"20-stage":[60],"FU":[61],"processor,":[63],"which":[64],"5.8x":[67],"power-efficiency":[68,100],"boost":[69,101],"than":[70],"many-core":[72],"processor":[73],"(MCP)":[74],"same":[77],"process":[78],"technology.":[79],"This":[80],"accordingly":[82],"slow":[83],"down":[84],"communication":[88],"by":[89],"one":[90],"order":[91],"cluster":[94],"system,":[95],"resulting":[96],"12x":[99],"all":[103],"PEs.":[104]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
