{"id":"https://openalex.org/W4308659641","doi":"https://doi.org/10.1109/vlsi-soc54400.2022.9939591","title":"ZaLoBI: Zero avoiding Load Balanced Inference accelerator","display_name":"ZaLoBI: Zero avoiding Load Balanced Inference accelerator","publication_year":2022,"publication_date":"2022-10-03","ids":{"openalex":"https://openalex.org/W4308659641","doi":"https://doi.org/10.1109/vlsi-soc54400.2022.9939591"},"language":"en","primary_location":{"id":"doi:10.1109/vlsi-soc54400.2022.9939591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vlsi-soc54400.2022.9939591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IFIP/IEEE 30th International Conference on Very Large Scale Integration (VLSI-SoC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086454875","display_name":"Imlijungla Longchar","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Imlijungla Longchar","raw_affiliation_strings":["IIT Guwahati,Department of CSE,Guwahati,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Guwahati,Department of CSE,Guwahati,India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021176902","display_name":"Palash Das","orcid":"https://orcid.org/0000-0002-1979-0298"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Palash Das","raw_affiliation_strings":["IIT Guwahati,Department of CSE,Guwahati,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Guwahati,Department of CSE,Guwahati,India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070605948","display_name":"Hemangee K. Kapoor","orcid":"https://orcid.org/0000-0002-9376-7686"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemangee K. Kapoor","raw_affiliation_strings":["IIT Guwahati,Department of CSE,Guwahati,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Guwahati,Department of CSE,Guwahati,India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.6958,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6295421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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":0.9998000264167786,"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":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8676559925079346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8470978736877441},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5859394073486328},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.579037070274353},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5745234489440918},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.5174303650856018},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5002663135528564},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.46177542209625244},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4562784433364868},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45520830154418945},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.4469178318977356},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.4183218777179718},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3838318884372711},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32110899686813354},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2773147225379944},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.27689898014068604},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.21925115585327148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16711843013763428},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09722265601158142},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.09456378221511841}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8676559925079346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8470978736877441},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5859394073486328},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.579037070274353},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5745234489440918},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.5174303650856018},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5002663135528564},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.46177542209625244},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4562784433364868},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45520830154418945},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.4469178318977356},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.4183218777179718},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3838318884372711},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32110899686813354},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2773147225379944},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.27689898014068604},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.21925115585327148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16711843013763428},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09722265601158142},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.09456378221511841},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vlsi-soc54400.2022.9939591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vlsi-soc54400.2022.9939591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IFIP/IEEE 30th International Conference on Very Large Scale Integration (VLSI-SoC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2048266589","https://openalex.org/W2102449048","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2516141709","https://openalex.org/W2518511512","https://openalex.org/W2582737986","https://openalex.org/W2963674932","https://openalex.org/W2964080840","https://openalex.org/W2979439447","https://openalex.org/W3084185164","https://openalex.org/W3114479342","https://openalex.org/W3118608800","https://openalex.org/W4236868170","https://openalex.org/W4240168186","https://openalex.org/W6637373629","https://openalex.org/W6638632666","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2556282987","https://openalex.org/W1533508804","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2532502681"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"are":[3],"prevalent":[4],"machine":[5],"learning":[6],"tools":[7],"used":[8],"in":[9,71,76,103,118,129],"computer":[10],"vision.":[11],"Their":[12],"ubiquitous":[13],"use":[14],"and":[15,25,65,150,157],"high":[16],"compute":[17],"requirement":[18],"have":[19],"given":[20],"rise":[21],"to":[22,35,88,109,137],"the":[23,30,37,59,110,119,138,154,160],"design":[24,56],"development":[26],"of":[27,39,61,85,99,112],"accelerators":[28],"for":[29],"same.":[31],"Among":[32],"several":[33],"approaches":[34],"improve":[36],"performance":[38],"these":[40],"accelerators,":[41],"exploiting":[42],"data":[43,63,86],"sparsity":[44],"has":[45],"become":[46],"very":[47],"popular.":[48],"Along":[49],"similar":[50],"lines,":[51],"this":[52,123],"paper":[53],"proposes":[54],"a":[55],"that":[57],"skips":[58],"computation":[60],"zero-valued":[62,72],"operands":[64],"achieves":[66,147],"better":[67],"speedup.":[68],"The":[69,79,96],"savings":[70],"computations":[73],"also":[74,158],"results":[75,102],"energy":[77],"savings.":[78],"proposed":[80],"accelerator":[81,145],"exploits":[82],"two":[83],"levels":[84],"parallelism":[87],"distribute":[89],"work":[90],"across":[91],"multiple":[92],"processing":[93],"elements":[94],"(PEs).":[95],"random":[97],"distribution":[98],"zero":[100,142],"values":[101],"certain":[104],"PEs":[105],"getting":[106],"idle":[107,139],"due":[108],"skipping":[111],"computations,":[113],"thus":[114],"creating":[115],"load":[116,131],"imbalance":[117],"system.":[120],"To":[121],"address":[122],"issue,":[124],"we":[125],"extend":[126],"our":[127],"contribution":[128],"performing":[130],"balancing":[132],"by":[133],"dynamically":[134],"scheduling":[135],"tasks":[136],"PEs.":[140],"Our":[141],"avoiding":[143],"load-balanced":[144],"(ZaLoBI)":[146],"around":[148],"76%":[149],"5.57%":[151],"speedup":[152],"over":[153],"respective":[155],"baselines":[156],"outperforms":[159],"state-of-the-art":[161],"works":[162],"while":[163],"saving":[164],"energy.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}