{"id":"https://openalex.org/W4410583863","doi":"https://doi.org/10.23919/date64628.2025.10992695","title":"Coala: Coalescion-Based Acceleration of Polynomial Multiplication for GPU Execution","display_name":"Coala: Coalescion-Based Acceleration of Polynomial Multiplication for GPU Execution","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410583863","doi":"https://doi.org/10.23919/date64628.2025.10992695"},"language":"en","primary_location":{"id":"doi:10.23919/date64628.2025.10992695","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10992695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation & Test in Europe Conference (DATE)","raw_type":"proceedings-article"},"type":"article","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/A5022868555","display_name":"Homer Gamil","orcid":"https://orcid.org/0000-0003-3256-783X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Homer Gamil","raw_affiliation_strings":["NYU Tandon School of Engineering,New York,USA"],"affiliations":[{"raw_affiliation_string":"NYU Tandon School of Engineering,New York,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026224233","display_name":"Oleg Mazonka","orcid":"https://orcid.org/0000-0001-5131-9044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oleg Mazonka","raw_affiliation_strings":["New York University Abu Dhabi,Abu Dhabi,UAE"],"affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi,Abu Dhabi,UAE","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043325974","display_name":"Michail Maniatakos","orcid":"https://orcid.org/0000-0001-6899-0651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michail Maniatakos","raw_affiliation_strings":["New York University Abu Dhabi,Abu Dhabi,UAE"],"affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi,Abu Dhabi,UAE","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022868555"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12248996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9857000112533569,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9702000021934509,"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/acceleration","display_name":"Acceleration","score":0.7692399024963379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7578162550926208},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6855301856994629},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6639156341552734},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.513640820980072},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.47903648018836975},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3240342140197754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14951983094215393},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11004236340522766}],"concepts":[{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.7692399024963379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7578162550926208},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6855301856994629},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6639156341552734},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.513640820980072},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.47903648018836975},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3240342140197754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14951983094215393},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11004236340522766},{"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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date64628.2025.10992695","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10992695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation & Test in Europe Conference (DATE)","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":22,"referenced_works":["https://openalex.org/W2031533839","https://openalex.org/W2061171222","https://openalex.org/W2069441027","https://openalex.org/W2309997581","https://openalex.org/W3048071914","https://openalex.org/W3182478132","https://openalex.org/W3185722301","https://openalex.org/W3207326900","https://openalex.org/W3210706552","https://openalex.org/W4226216812","https://openalex.org/W4281609193","https://openalex.org/W4312296236","https://openalex.org/W4312578262","https://openalex.org/W4367721814","https://openalex.org/W4379115979","https://openalex.org/W4389252478","https://openalex.org/W4390097821","https://openalex.org/W4391305851","https://openalex.org/W4396956522","https://openalex.org/W4404953873","https://openalex.org/W6606597398","https://openalex.org/W6756049408"],"related_works":["https://openalex.org/W3093936885","https://openalex.org/W2994146737","https://openalex.org/W2565094479","https://openalex.org/W295308437","https://openalex.org/W2992046671","https://openalex.org/W2390829436","https://openalex.org/W1989791859","https://openalex.org/W2106539092","https://openalex.org/W4205300683","https://openalex.org/W56570565"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,112],"introduce":[4,42],"Coala,":[5],"a":[6,24,33,43,87,114,133],"novel":[7,44],"framework":[8,89],"designed":[9],"to":[10,51,117],"enhance":[11],"the":[12,28,36,57,77,80,92,98,106,125],"performance":[13,149],"of":[14,27,35,59,94,108,127,151],"finite":[15],"field":[16],"transformations":[17],"for":[18,161],"GPU":[19,109],"environments.":[20],"We":[21,41,147],"have":[22],"developed":[23],"GPU-optimized":[25],"version":[26],"Discrete":[29],"Galois":[30],"Transformation":[31],"(DGT),":[32],"variant":[34],"Number":[37],"Theoretic":[38],"Transform":[39],"(NTT).":[40],"data":[45,60],"access":[46],"pattern":[47],"scheme":[48],"specifically":[49],"engineered":[50],"enable":[52],"coalesced":[53],"accesses,":[54],"significantly":[55],"enhancing":[56],"efficiency":[58,73],"transfers":[61],"between":[62],"global":[63],"and":[64,101,121,132],"shared":[65],"memory.":[66],"This":[67],"enhancement":[68],"not":[69],"only":[70],"boosts":[71],"execution":[72,102],"but":[74],"also":[75],"optimizes":[76,91],"interaction":[78],"with":[79,166],"GPU's":[81,99],"memory":[82,170],"architecture.":[83],"Additionally,":[84],"Coala":[85],"presents":[86],"comprehensive":[88],"that":[90],"allocation":[93],"computational":[95],"tasks":[96],"across":[97],"architecture":[100],"kernels,":[103],"thereby":[104],"maximizing":[105],"use":[107],"resources.":[110],"Lastly,":[111],"provide":[113],"flexible":[115,134],"method":[116],"adjust":[118],"security":[119],"levels":[120],"polynomial":[122],"sizes":[123],"through":[124],"incorporation":[126],"an":[128],"in-kernel":[129],"RNS":[130],"method,":[131],"parameter":[135],"generation":[136],"approach.":[137],"Comparative":[138],"analysis":[139],"against":[140,155],"current":[141],"state-of-the-art":[142],"techniques":[143],"reveals":[144],"significant":[145],"improvements.":[146],"observe":[148],"gains":[150],"2.82\u2032":[152],"\u2212":[153],"17.18\u2032":[154],"other":[156],"DGT":[157],"works":[158],"on":[159],"GPUs":[160],"different":[162],"parameters,":[163],"achieved":[164],"concurrently":[165],"equal":[167],"or":[168],"lesser":[169],"utilization.":[171]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}