{"id":"https://openalex.org/W2018034355","doi":"https://doi.org/10.1109/sasp.2011.5941081","title":"3D recursive Gaussian IIR on GPU and FPGAs — A case for accelerating bandwidth-bounded applications","display_name":"3D recursive Gaussian IIR on GPU and FPGAs — A case for accelerating bandwidth-bounded applications","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2018034355","doi":"https://doi.org/10.1109/sasp.2011.5941081","mag":"2018034355"},"language":"en","primary_location":{"id":"doi:10.1109/sasp.2011.5941081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sasp.2011.5941081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 9th Symposium on Application Specific Processors (SASP)","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/A5016776689","display_name":"Jason Cong","orcid":"https://orcid.org/0000-0003-2887-6963"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Cong","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA","Computer Science Department - University of California, Los Angeles, 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Computer Science Department - University of California, Los Angeles, 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034338235","display_name":"Muhuan Huang","orcid":"https://orcid.org/0000-0002-4067-9009"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhuan Huang","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA","Computer Science Department - University of California, Los Angeles, 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Computer Science Department - University of California, Los Angeles, 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458990","display_name":"Yi Zou","orcid":"https://orcid.org/0000-0002-4382-4670"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zou","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA","Computer Science Department - University of California, Los Angeles, 90095, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Computer Science Department - University of California, Los Angeles, 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":2.0109,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85738171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"70","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9980999827384949,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9943000078201294,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9915000200271606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7916148900985718},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7649610638618469},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6521914005279541},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5842078924179077},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5586903095245361},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5222398042678833},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5028290152549744},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.42357540130615234},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2548849582672119},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10958811640739441}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916148900985718},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7649610638618469},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6521914005279541},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5842078924179077},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5586903095245361},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5222398042678833},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5028290152549744},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.42357540130615234},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2548849582672119},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10958811640739441},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sasp.2011.5941081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sasp.2011.5941081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE 9th Symposium on Application Specific Processors (SASP)","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":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1967396726","https://openalex.org/W1972099553","https://openalex.org/W1979460758","https://openalex.org/W2009463061","https://openalex.org/W2047625347","https://openalex.org/W2116773294","https://openalex.org/W2144595616"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W4376647684"],"abstract_inverted_index":{"GPU":[0,13,39,81],"device":[1],"typically":[2,12],"has":[3],"a":[4,30],"higher":[5],"off-chip":[6],"bandwidth":[7,63,74],"than":[8],"FPGA-based":[9],"systems.":[10],"Thus":[11],"should":[14],"perform":[15],"better":[16],"for":[17],"bandwidth-bounded":[18],"massive":[19],"parallel":[20],"applications.":[21],"In":[22],"this":[23,59],"paper,":[24],"we":[25],"present":[26],"our":[27],"implementations":[28,78],"of":[29],"3D":[31],"recursive":[32],"Gaussian":[33],"IIR":[34],"on":[35,46,67,79,95],"multi-core":[36],"CPU,":[37],"many-core":[38],"and":[40,82,87],"multi-FPGA":[41],"platforms.":[42],"Our":[43,77],"baseline":[44],"implementation":[45],"the":[47,50,65,68,80],"CPU":[48],"features":[49],"smallest":[51],"arithmetic":[52],"computation":[53],"(2":[54],"MADDs":[55],"per":[56],"dimension).":[57],"While":[58],"application":[60],"is":[61],"clearly":[62],"bounded,":[64],"difference":[66],"memory":[69],"subsystems":[70],"translates":[71],"to":[72],"different":[73],"optimization":[75],"techniques.":[76],"FPGA":[83],"platforms":[84],"show":[85],"26X":[86],"33X":[88],"speedup":[89],"respectively":[90],"over":[91],"optimized":[92],"single-thread":[93],"code":[94],"CPU.":[96]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}