{"id":"https://openalex.org/W4416004433","doi":"https://doi.org/10.1145/3731599.3767574","title":"A Study of Performance Portability of Low-bit Fused Matrix-Vector Multiplication Kernels in SYCL","display_name":"A Study of Performance Portability of Low-bit Fused Matrix-Vector Multiplication Kernels in SYCL","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004433","doi":"https://doi.org/10.1145/3731599.3767574"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767574","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767574","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767574","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101790023","display_name":"Zheming Jin","orcid":"https://orcid.org/0000-0002-7197-780X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zheming Jin","raw_affiliation_strings":["Oak Ridge National Lab, Oak Ridge, USA"],"raw_orcid":"https://orcid.org/0000-0002-7197-780X","affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab, Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101790023"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35455013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2129","last_page":"2136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9495999813079834,"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":0.9495999813079834,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.01590000092983246,"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":0.00930000003427267,"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/software-portability","display_name":"Software portability","score":0.7818999886512756},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.64410001039505},{"id":"https://openalex.org/keywords/laptop","display_name":"Laptop","score":0.5188999772071838},{"id":"https://openalex.org/keywords/general-purpose","display_name":"General purpose","score":0.445499986410141},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4129999876022339},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.39500001072883606}],"concepts":[{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.7818999886512756},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762999892234802},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.64410001039505},{"id":"https://openalex.org/C2780008327","wikidata":"https://www.wikidata.org/wiki/Q3962","display_name":"Laptop","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2635999917984009},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.26089999079704285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767574","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767574","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767574","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767574","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2016939324","https://openalex.org/W2107911628","https://openalex.org/W3209449653","https://openalex.org/W4250981202","https://openalex.org/W4403852655"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"the":[1,45,49,55,58,72,91],"causes":[2,73],"of":[3,27,57,74],"performance":[4,20,25,56,75],"gaps":[5],"between":[6],"a":[7,12],"portable":[8],"programming":[9,14],"model":[10,15],"and":[11,61,67,70,86],"vendor-specific":[13],"is":[16],"important":[17],"for":[18],"improving":[19],"portability.":[21],"This":[22,42],"paper":[23],"studies":[24],"portability":[26],"low-bit":[28],"fused":[29],"general":[30],"matrix-vector":[31],"multiplication":[32],"kernels":[33,63],"in":[34,52],"SYCL":[35,62],"on":[36,64],"vendors\u2019":[37],"graphics":[38],"processing":[39],"units":[40],"(GPUs).":[41],"work":[43],"introduces":[44],"use":[46],"case,":[47],"explains":[48],"kernel":[50,83],"implementations":[51],"detail,":[53],"evaluates":[54],"CUDA,":[59],"HIP,":[60],"datacenter,":[65],"desktop,":[66],"laptop":[68],"GPUs,":[69],"investigates":[71],"gaps.":[76,92],"The":[77],"results":[78],"show":[79],"that":[80],"loop":[81],"unrolling,":[82],"dispatch":[84],"overhead,":[85],"sum":[87],"reduction":[88],"contribute":[89],"to":[90]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-07T00:00:00"}