{"id":"https://openalex.org/W3088013723","doi":"https://doi.org/10.1109/sips50750.2020.9195237","title":"Optimizing Halide for Digital Signal Processors","display_name":"Optimizing Halide for Digital Signal Processors","publication_year":2020,"publication_date":"2020-09-23","ids":{"openalex":"https://openalex.org/W3088013723","doi":"https://doi.org/10.1109/sips50750.2020.9195237","mag":"3088013723"},"language":"en","primary_location":{"id":"doi:10.1109/sips50750.2020.9195237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips50750.2020.9195237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Workshop on Signal Processing Systems (SiPS)","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/A5034958091","display_name":"John A. Stratton","orcid":"https://orcid.org/0000-0002-3625-9781"},"institutions":[{"id":"https://openalex.org/I138943879","display_name":"Whitman College","ror":"https://ror.org/05axv8155","country_code":"US","type":"education","lineage":["https://openalex.org/I138943879"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John A. Stratton","raw_affiliation_strings":["Whitman College Walla, Walla, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Whitman College Walla, Walla, WA, USA","institution_ids":["https://openalex.org/I138943879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001039332","display_name":"Jyothi Krishna Viswakaran Sreelatha","orcid":"https://orcid.org/0000-0001-9402-8052"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jyothi Krishna Viswakaran Sreelatha","raw_affiliation_strings":["MulticoreWare, Inc., Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MulticoreWare, Inc., Santa Clara, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032495561","display_name":"Rajiv Ravindran","orcid":null},"institutions":[{"id":"https://openalex.org/I66217453","display_name":"Cadence Design Systems (United States)","ror":"https://ror.org/04w8xa018","country_code":"US","type":"company","lineage":["https://openalex.org/I66217453"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajiv Ravindran","raw_affiliation_strings":["Cadence Design Systems, Inc., San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cadence Design Systems, Inc., San Jose, CA, USA","institution_ids":["https://openalex.org/I66217453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014316529","display_name":"Sachin Sudhakar Dake","orcid":null},"institutions":[{"id":"https://openalex.org/I66217453","display_name":"Cadence Design Systems (United States)","ror":"https://ror.org/04w8xa018","country_code":"US","type":"company","lineage":["https://openalex.org/I66217453"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin Sudhakar Dake","raw_affiliation_strings":["Cadence Design Systems, Inc., San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cadence Design Systems, Inc., San Jose, CA, USA","institution_ids":["https://openalex.org/I66217453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030600614","display_name":"Jeevitha Palanisamy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeevitha Palanisamy","raw_affiliation_strings":["MulticoreWare, Inc., Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MulticoreWare, Inc., Santa Clara, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2254,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36133452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9994000196456909,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9994000196456909,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8525794744491577},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.7520571947097778},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7209635972976685},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6920729875564575},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.5994132161140442},{"id":"https://openalex.org/keywords/digital-signal-processor","display_name":"Digital signal processor","score":0.5882011651992798},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5706557035446167},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49251946806907654},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.46830451488494873},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4446057677268982},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35949546098709106},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.35437220335006714},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.32040172815322876},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14114215970039368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8525794744491577},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.7520571947097778},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7209635972976685},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6920729875564575},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.5994132161140442},{"id":"https://openalex.org/C161611012","wikidata":"https://www.wikidata.org/wiki/Q106370","display_name":"Digital signal processor","level":3,"score":0.5882011651992798},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5706557035446167},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49251946806907654},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.46830451488494873},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4446057677268982},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35949546098709106},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.35437220335006714},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.32040172815322876},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14114215970039368},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/sips50750.2020.9195237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips50750.2020.9195237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Workshop on Signal Processing Systems (SiPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1540764465","https://openalex.org/W1980208272","https://openalex.org/W1989988531","https://openalex.org/W2055312318","https://openalex.org/W2290665737","https://openalex.org/W2582073145","https://openalex.org/W2771043729","https://openalex.org/W4299808569"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2983282793","https://openalex.org/W2045177269","https://openalex.org/W2116582200","https://openalex.org/W1580752477","https://openalex.org/W2061453039","https://openalex.org/W2349422795","https://openalex.org/W1552773033","https://openalex.org/W2111201220"],"abstract_inverted_index":{"Halide,":[0],"a":[1,76,84,96,107],"Domain":[2],"Specific":[3],"Language":[4],"(DSL)":[5],"for":[6,23,30,43,155],"image":[7],"and":[8,41,101,116,130,147],"array":[9],"processing,":[10],"promotes":[11],"the":[12,24,28,61,80,87,121,132,142,148,156],"separation":[13],"of":[14,63,82,98,123],"functional":[15],"algorithm":[16],"from":[17],"execution":[18],"schedule,":[19],"making":[20],"it":[21],"easier":[22],"user":[25],"to":[26,68,79,104,152],"optimize":[27],"code":[29],"different":[31],"hardware":[32],"platforms.":[33],"Halide":[34,88,99],"supports":[35],"multiple":[36],"back-end":[37],"APIs,":[38],"including":[39,110],"CUDA":[40],"OpenCL":[42,89,145,154],"GPUs.":[44,70],"Although":[45],"many":[46],"modern":[47],"Digital":[48],"Signal":[49],"Processors":[50],"(DSPs)":[51],"support":[52,69,106],"OpenCL,":[53],"achieving":[54],"high":[55],"performance":[56,149],"on":[57,126],"these":[58],"devices":[59],"require":[60],"use":[62],"features":[64],"beyond":[65],"those":[66,72],"required":[67,103],"Without":[71],"features,":[73],"there":[74],"is":[75,150],"strict":[77],"limit":[78],"effectiveness":[81],"targeting":[83],"DSP":[85,108,129],"through":[86],"back-end.":[90],"In":[91],"this":[92],"paper,":[93],"we":[94,137],"describe":[95],"set":[97],"extensions":[100],"optimizations":[102],"effectively":[105],"target,":[109],"DMA":[111],"Promotion,":[112],"Type":[113],"Width":[114],"Reduction":[115],"Intrinsic":[117],"generation.":[118],"We":[119],"evaluate":[120],"effects":[122],"our":[124],"optimization":[125],"Cadence":[127],"Vision":[128],"report":[131],"results.":[133],"On":[134],"an":[135],"average,":[136],"observe":[138],"88X":[139],"speedup":[140],"over":[141],"baseline":[143],"generated":[144],"code,":[146],"comparable":[151],"handcrafted":[153],"target":[157],"platform.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}