{"id":"https://openalex.org/W4412560833","doi":"https://doi.org/10.1109/mocast65744.2025.11083943","title":"Streamlining SIMD ISA Extensions with Takum Arithmetic: A Case Study on Intel AVX10.2","display_name":"Streamlining SIMD ISA Extensions with Takum Arithmetic: A Case Study on Intel AVX10.2","publication_year":2025,"publication_date":"2025-06-11","ids":{"openalex":"https://openalex.org/W4412560833","doi":"https://doi.org/10.1109/mocast65744.2025.11083943"},"language":"en","primary_location":{"id":"doi:10.1109/mocast65744.2025.11083943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mocast65744.2025.11083943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 14th International Conference on Modern Circuits and Systems Technologies (MOCAST)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.14067","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078859292","display_name":"Laslo Hunhold","orcid":null},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Laslo Hunhold","raw_affiliation_strings":["University of Cologne,Parallel and Distributed Systems Group,Cologne,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cologne,Parallel and Distributed Systems Group,Cologne,Germany","institution_ids":["https://openalex.org/I180923762"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078859292"],"corresponding_institution_ids":["https://openalex.org/I180923762"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17245632,"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":"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":0.9571999907493591,"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":0.9571999907493591,"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/simd","display_name":"SIMD","score":0.757768452167511},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7483077049255371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6919740438461304},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.5506533980369568},{"id":"https://openalex.org/keywords/mmx","display_name":"MMX","score":0.46696048974990845},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36524438858032227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11827227473258972}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.757768452167511},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7483077049255371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6919740438461304},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.5506533980369568},{"id":"https://openalex.org/C85918911","wikidata":"https://www.wikidata.org/wiki/Q904336","display_name":"MMX","level":2,"score":0.46696048974990845},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36524438858032227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11827227473258972}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mocast65744.2025.11083943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mocast65744.2025.11083943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 14th International Conference on Modern Circuits and Systems Technologies (MOCAST)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.14067","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.14067","pdf_url":"https://arxiv.org/pdf/2503.14067","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.14067","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.14067","pdf_url":"https://arxiv.org/pdf/2503.14067","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2035080386","https://openalex.org/W2743322459","https://openalex.org/W2908782257","https://openalex.org/W2955474694","https://openalex.org/W4403465548","https://openalex.org/W4411688454","https://openalex.org/W6875494535","https://openalex.org/W6876991617","https://openalex.org/W6891860136","https://openalex.org/W6967040123"],"related_works":["https://openalex.org/W1563340050","https://openalex.org/W4708796","https://openalex.org/W1480874568","https://openalex.org/W602477477","https://openalex.org/W2164226499","https://openalex.org/W1989216001","https://openalex.org/W2129537883","https://openalex.org/W1984515673","https://openalex.org/W2119424570","https://openalex.org/W1970816443"],"abstract_inverted_index":{"Modern":[0],"microprocessors":[1],"extend":[2],"their":[3],"instruction":[4,152],"set":[5],"architecture":[6],"(ISA)":[7],"with":[8,140],"Single":[9],"Instruction,":[10],"Multiple":[11],"Data":[12],"(SIMD)":[13],"operations":[14],"to":[15,62,106],"improve":[16],"performance.":[17],"The":[18,37,146],"Intel":[19,33],"Advanced":[20],"Vector":[21],"Extensions":[22],"(AVX)":[23],"enhance":[24],"the":[25,76,90,95,127,130,135],"x86":[26],"ISA":[27],"and":[28,34,52,86,113,156,163],"are":[29],"widely":[30],"supported":[31],"in":[32],"AMD":[35],"processors.":[36],"latest":[38],"version,":[39],"AVX10.2,":[40],"places":[41],"a":[42,117,124,143,149],"strong":[43],"emphasis":[44],"on":[45],"low-precision,":[46],"non-standard":[47],"floating-point":[48,100],"formats,":[49],"including":[50],"bfloat16":[51],"E4M3/E5M2":[53],"float8":[54],"(OCP":[55],"8-bit":[56],"Floating":[57],"Point,":[58],"OFP8),":[59],"primarily":[60],"catering":[61],"deep":[63],"learning":[64],"applications":[65],"rather":[66],"than":[67],"general-purpose":[68,118,165],"arithmetic.":[69,167],"However,":[70],"as":[71,116,123,142],"these":[72],"formats":[73,139],"remain":[74],"within":[75],"IEEE":[77,111],"754":[78,112],"framework,":[79],"they":[80],"inherit":[81],"its":[82,114],"limitations,":[83],"introducing":[84],"inconsistencies":[85],"added":[87],"complexity":[88],"into":[89],"ISA.":[91],"This":[92],"paper":[93,128],"examines":[94],"recently":[96],"proposed":[97],"taperedprecision":[98],"takum":[99,141],"format,":[101],"which":[102],"has":[103],"been":[104],"shown":[105],"offer":[107],"significant":[108],"advantages":[109],"over":[110],"derivatives":[115],"number":[119],"format.":[120],"Using":[121],"AVX10.2":[122],"case":[125],"study,":[126],"explores":[129],"potential":[131,160],"benefits":[132],"of":[133,137],"replacing":[134],"multitude":[136],"floatingpoint":[138],"uniform":[144],"basis.":[145],"results":[147],"indicate":[148],"more":[150],"consistent":[151],"set,":[153],"improving":[154],"readability":[155],"flexibility":[157],"while":[158],"offering":[159],"for":[161],"8-":[162],"16-bit":[164],"SIMD":[166]},"counts_by_year":[],"updated_date":"2026-04-26T08:31:28.666265","created_date":"2025-07-22T00:00:00"}