{"id":"https://openalex.org/W7092185511","doi":"https://doi.org/10.1145/3725843.3756124","title":"HiPACK: Efficient Sub-8-Bit Direct Convolution with SIMD and Bitwise Management","display_name":"HiPACK: Efficient Sub-8-Bit Direct Convolution with SIMD and Bitwise Management","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W7092185511","doi":"https://doi.org/10.1145/3725843.3756124"},"language":null,"primary_location":{"id":"doi:10.1145/3725843.3756124","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756124","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756124","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 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756124","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yao Chen","orcid":"https://orcid.org/0000-0002-5798-2282"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yao Chen","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cheng Gong","orcid":"https://orcid.org/0000-0002-6594-8375"},"institutions":[{"id":"https://openalex.org/I198091727","display_name":"Tiangong University","ror":"https://ror.org/00xsr9m91","country_code":"CN","type":"education","lineage":["https://openalex.org/I198091727"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Gong","raw_affiliation_strings":["Tiangong University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tiangong University, Tianjin, China","institution_ids":["https://openalex.org/I198091727"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bingsheng He","orcid":"https://orcid.org/0000-0001-8618-4581"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bingsheng He","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.2134,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85989362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1579","last_page":"1591"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.24469999969005585,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.24469999969005585,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.1454000025987625,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.08299999684095383,"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/bitwise-operation","display_name":"Bitwise operation","score":0.5253000259399414},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4999000132083893},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.31130000948905945},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.2921999990940094},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.2734000086784363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6244000196456909},{"id":"https://openalex.org/C134765980","wikidata":"https://www.wikidata.org/wiki/Q879126","display_name":"Bitwise operation","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4999000132083893},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39089998602867126},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.2921999990940094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2919999957084656},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725843.3756124","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756124","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756124","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 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3725843.3756124","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756124","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756124","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 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2884910486","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320322724","funder_display_name":"Ministry of Education, India"}],"funders":[{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7092185511.pdf","grobid_xml":"https://content.openalex.org/works/W7092185511.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2068977981","https://openalex.org/W2194775991","https://openalex.org/W2808739938","https://openalex.org/W2899915146","https://openalex.org/W2907166042","https://openalex.org/W2917087921","https://openalex.org/W2962856739","https://openalex.org/W2963480671","https://openalex.org/W2964209782","https://openalex.org/W2972343638","https://openalex.org/W2974514820","https://openalex.org/W3004061291","https://openalex.org/W3033428961","https://openalex.org/W3193946904","https://openalex.org/W3198679933","https://openalex.org/W4212902668","https://openalex.org/W4321446149"],"related_works":[],"abstract_inverted_index":{"Quantized":[0],"Deep":[1],"Neural":[2],"Networks":[3],"(DNNs)":[4],"have":[5],"progressed":[6],"to":[7,55,99,124,127],"utilize":[8],"sub-8-bit":[9,26,70],"data":[10],"types,":[11],"achieving":[12],"notable":[13],"reductions":[14],"in":[15,33,69],"both":[16],"memory":[17],"usage":[18],"and":[19,62,91,111,130,144],"computational":[20,109],"expenses.Nevertheless,":[21],"the":[22,34,48,57,64,75,82,88,116],"efficient":[23,51],"execution":[24],"of":[25,36,60,66,84,122],"convolution":[27,52,72],"operations":[28],"remains":[29],"insufficiently":[30],"optimized,":[31],"especially":[32],"context":[35],"Single":[37],"Instruction":[38],"Multiple":[39],"Data":[40],"(SIMD)":[41],"architectures.This":[42],"paper":[43],"introduces":[44],"HiPACK,":[45],"which":[46],"takes":[47],"packing":[49],"for":[50],"as":[53],"foundation":[54],"reduce":[56],"required":[58],"number":[59],"operations,":[61,80],"address":[63],"challenges":[65],"SIMD":[67],"incompatibility":[68],"direct":[71],"by":[73],"decoupling":[74],"unpacking":[76],"phase":[77],"from":[78],"multiplication":[79,102],"optimizing":[81],"caching":[83],"intermediate":[85],"data,":[86],"determining":[87],"ideal":[89],"segmentation,":[90],"employing":[92],"a":[93],"dual":[94],"interleaved":[95],"register":[96],"(DIR)":[97],"mechanism":[98],"facilitate":[100],"parallel":[101],"through":[103],"SIMD.Collectively,":[104],"these":[105],"optimizations":[106],"significantly":[107],"enhance":[108],"efficiency":[110],"diminish":[112],"operational":[113],"overhead.Evaluation":[114],"on":[115],"BCM2711":[117],"ARM":[118],"processor":[119],"reveals":[120],"speedups":[121],"up":[123],"4.6":[125],"compared":[126],"floating-point":[128],"calculations":[129],"1.7":[131],"when":[132],"measured":[133],"against":[134],"state-of-the-art":[135],"solutions,":[136],"thus":[137],"accelerating":[138],"model":[139],"inference.Our":[140],"implementation":[141],"is":[142],"open-sourced":[143],"available":[145],"at:":[146],"https://github.com/Xtra-Computing/HIPACK.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-17T00:00:00"}