{"id":"https://openalex.org/W4409132226","doi":"https://doi.org/10.1109/hpec62836.2024.10938457","title":"Optimization Strategies to Accelerate BLAS Operations with ARM SVE","display_name":"Optimization Strategies to Accelerate BLAS Operations with ARM SVE","publication_year":2024,"publication_date":"2024-09-23","ids":{"openalex":"https://openalex.org/W4409132226","doi":"https://doi.org/10.1109/hpec62836.2024.10938457"},"language":"en","primary_location":{"id":"doi:10.1109/hpec62836.2024.10938457","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5116901275","display_name":"Aniket P. Garade","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aniket P. Garade","raw_affiliation_strings":["Centre for Development of Advanced Computing,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Development of Advanced Computing,Bengaluru,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sushil Pratap Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sushil Pratap Singh","raw_affiliation_strings":["Centre for Development of Advanced Computing,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Development of Advanced Computing,Bengaluru,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Juliya James","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Juliya James","raw_affiliation_strings":["Centre for Development of Advanced Computing,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Development of Advanced Computing,Bengaluru,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083731232","display_name":"H V Deepika","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"H V Deepika","raw_affiliation_strings":["Centre for Development of Advanced Computing,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Development of Advanced Computing,Bengaluru,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038622495","display_name":"P Haribabu","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Haribabu P","raw_affiliation_strings":["Centre for Development of Advanced Computing,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Development of Advanced Computing,Bengaluru,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101957775","display_name":"Sathish Kumar","orcid":"https://orcid.org/0000-0002-3162-2211"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S A Kumar","raw_affiliation_strings":["Centre for Development of Advanced Computing,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Development of Advanced Computing,Bengaluru,India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102868385","display_name":"S D Sudarsan","orcid":"https://orcid.org/0000-0002-7990-6686"},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S D Sudarsan","raw_affiliation_strings":["Centre for Development of Advanced Computing,Bengaluru,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Development of Advanced Computing,Bengaluru,India","institution_ids":["https://openalex.org/I1331500379"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1331500379"],"apc_list":null,"apc_paid":null,"fwci":0.8523,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75934565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.6294999718666077,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.6294999718666077,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.6029999852180481,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.5902000069618225,"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":0.5856723785400391},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3607558012008667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5856723785400391},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3607558012008667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec62836.2024.10938457","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","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":16,"referenced_works":["https://openalex.org/W2002257715","https://openalex.org/W2038469228","https://openalex.org/W2064872546","https://openalex.org/W2073061372","https://openalex.org/W2082444966","https://openalex.org/W2149381887","https://openalex.org/W2252007067","https://openalex.org/W2340076492","https://openalex.org/W2613264175","https://openalex.org/W2750126981","https://openalex.org/W2806900363","https://openalex.org/W3086504363","https://openalex.org/W3091837582","https://openalex.org/W3136479147","https://openalex.org/W3194605763","https://openalex.org/W4360995240"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Optimized":[0],"mathematical":[1],"libraries":[2,20],"designed":[3],"for":[4,10,37,62,80],"specific":[5],"hardware":[6],"platforms":[7],"are":[8],"critical":[9],"achieving":[11],"maximum":[12],"performance":[13,55,97],"in":[14,25,104],"scientific":[15],"and":[16,28,72,92],"engineering":[17],"applications.":[18],"These":[19],"play":[21],"a":[22,42],"key":[23],"role":[24],"accelerating":[26,105],"computations":[27],"improving":[29],"code":[30],"efficiency.":[31],"The":[32,86],"Scalable":[33],"Vector":[34],"Extension":[35],"(SVE)":[36],"the":[38,78,100],"ARM":[39,109],"architecture":[40],"is":[41,88],"recent":[43],"development":[44],"that":[45],"enhances":[46],"vectorization":[47],"capabilities,":[48],"with":[49,90],"wide":[50],"vectors,":[51],"leading":[52],"to":[53],"significant":[54],"improvements.":[56],"This":[57],"paper":[58],"explores":[59],"vector":[60],"optimizations":[61],"Basic":[63],"Linear":[64],"Algebra":[65],"Subprograms":[66],"(BLAS)":[67],"routines,":[68],"targeting":[69],"both":[70],"single":[71],"double":[73],"precision":[74],"data.":[75],"It":[76],"details":[77],"strategies":[79],"vectorizing":[81],"BLAS":[82],"operations":[83],"using":[84],"SVE.":[85],"approach":[87],"implemented":[89],"OpenBLAS,":[91],"experimental":[93],"results":[94],"reveal":[95],"notable":[96],"gains,":[98],"demonstrating":[99],"efficacy":[101],"of":[102],"SVE":[103],"computational":[106],"tasks":[107],"on":[108],"platforms.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}