{"id":"https://openalex.org/W3208099998","doi":"https://doi.org/10.1145/3458817.3476182","title":"Efficient tensor core-based GPU kernels for structured sparsity under reduced precision","display_name":"Efficient tensor core-based GPU kernels for structured sparsity under reduced precision","publication_year":2021,"publication_date":"2021-10-21","ids":{"openalex":"https://openalex.org/W3208099998","doi":"https://doi.org/10.1145/3458817.3476182","mag":"3208099998"},"language":"en","primary_location":{"id":"doi:10.1145/3458817.3476182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3458817.3476182","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3458817.3476182","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3458817.3476182","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037216840","display_name":"Zhaodong Chen","orcid":"https://orcid.org/0000-0001-9601-4586"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaodong Chen","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003935082","display_name":"Zheng Qu","orcid":"https://orcid.org/0000-0001-6574-0649"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Qu","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324294","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0003-0792-8146"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu Liu","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048052285","display_name":"Yufei Ding","orcid":"https://orcid.org/0000-0002-8716-5793"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufei Ding","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110042813","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0001-6945-7437"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["University of California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2803209242"],"apc_list":null,"apc_paid":null,"fwci":3.9259,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96521739,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9733999967575073,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9610999822616577,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/speedup","display_name":"Speedup","score":0.9483156204223633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7634732723236084},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6580456495285034},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5949029326438904},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5835093259811401},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5533603429794312},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5394163727760315},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.48028039932250977},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4785324037075043},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.47659534215927124},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47423025965690613},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3589848279953003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1977662444114685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15060386061668396}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9483156204223633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634732723236084},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6580456495285034},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5949029326438904},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5835093259811401},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5533603429794312},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5394163727760315},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.48028039932250977},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4785324037075043},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.47659534215927124},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47423025965690613},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3589848279953003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1977662444114685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15060386061668396},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3458817.3476182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3458817.3476182","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3458817.3476182","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-132956","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85118624621&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3458817.3476182","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3458817.3476182","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3458817.3476182","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G1875027798","display_name":null,"funder_award_id":"MRSEC; NSF DMR 1720256","funder_id":"https://openalex.org/F4320337965","funder_display_name":"California NanoSystems Institute"},{"id":"https://openalex.org/G2045646697","display_name":null,"funder_award_id":"DMR 1720256","funder_id":"https://openalex.org/F4320333422","funder_display_name":"Materials Research Science and Engineering Center, Harvard University"},{"id":"https://openalex.org/G325663671","display_name":null,"funder_award_id":"DMR  1720256","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G3319042522","display_name":null,"funder_award_id":"MRSEC NSF DMR 1720256","funder_id":"https://openalex.org/F4320333422","funder_display_name":"Materials Research Science and Engineering Center, Harvard University"},{"id":"https://openalex.org/G4228342300","display_name":null,"funder_award_id":"NSF DMR 1720256","funder_id":"https://openalex.org/F4320332500","funder_display_name":"University of California, Santa Barbara"},{"id":"https://openalex.org/G4250104368","display_name":null,"funder_award_id":"1720256","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"},{"id":"https://openalex.org/G445623813","display_name":null,"funder_award_id":"NSF DMR-1720256","funder_id":"https://openalex.org/F4320333422","funder_display_name":"Materials Research Science and Engineering Center, Harvard University"},{"id":"https://openalex.org/G4537565017","display_name":"CC* Compute:  A high-performance GPU cluster for accelerated research","funder_award_id":"1925717","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6512159266","display_name":null,"funder_award_id":"1720256","funder_id":"https://openalex.org/F4320333422","funder_display_name":"Materials Research Science and Engineering Center, Harvard University"},{"id":"https://openalex.org/G6912258823","display_name":"Materials Research Science and Engineering Center at UCSB","funder_award_id":"1720256","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7061003935","display_name":null,"funder_award_id":"NSF DMR 1720256","funder_id":"https://openalex.org/F4320337965","funder_display_name":"California NanoSystems Institute"},{"id":"https://openalex.org/G7437795455","display_name":null,"funder_award_id":"1720256","funder_id":"https://openalex.org/F4320332500","funder_display_name":"University of California, Santa Barbara"},{"id":"https://openalex.org/G8230913862","display_name":null,"funder_award_id":"NSF DMR 1720256","funder_id":"https://openalex.org/F4320337367","funder_display_name":"Division of Materials Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320332500","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463"},{"id":"https://openalex.org/F4320333422","display_name":"Materials Research Science and Engineering Center, Harvard University","ror":null},{"id":"https://openalex.org/F4320337367","display_name":"Division of Materials Research","ror":"https://ror.org/01pc7k308"},{"id":"https://openalex.org/F4320337965","display_name":"California NanoSystems Institute","ror":"https://ror.org/00q7fqf35"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3208099998.pdf","grobid_xml":"https://content.openalex.org/works/W3208099998.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1493774699","https://openalex.org/W2119144962","https://openalex.org/W2529546376","https://openalex.org/W2608554408","https://openalex.org/W2619096655","https://openalex.org/W2626696598","https://openalex.org/W2789683730","https://openalex.org/W2796649226","https://openalex.org/W2883542588","https://openalex.org/W2913208203","https://openalex.org/W2940744433","https://openalex.org/W2946567085","https://openalex.org/W2963403868","https://openalex.org/W2963989532","https://openalex.org/W2970217631","https://openalex.org/W2970971581","https://openalex.org/W2980186997","https://openalex.org/W2984305089","https://openalex.org/W2998957070","https://openalex.org/W3034864447","https://openalex.org/W3045733172","https://openalex.org/W3104528661","https://openalex.org/W3111142806","https://openalex.org/W3130660608","https://openalex.org/W4243657877"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2,8],"DNN":[3,96],"comes":[4],"at":[5],"the":[6,54,76,101],"expense":[7],"excessive":[9],"memory/computation":[10],"cost,":[11],"which":[12],"can":[13,85],"be":[14,86],"addressed":[15],"by":[16,53],"exploiting":[17],"reduced":[18],"precision":[19],"and":[20,46,59,111,124,127,141,148],"sparsity":[21,40,50,143],"jointly.":[22],"Existing":[23],"sparse":[24,95],"GPU":[25],"kernels,":[26],"however,":[27],"fail":[28],"to":[29,88],"achieve":[30,128],"practical":[31],"speedup":[32,130,134],"over":[33,131,137],"cuBLASHgemm":[34,138],"under":[35,62,75,114,139],"half-precision.":[36,149],"Those":[37],"for":[38,48],"fine-grained":[39],"suffer":[41],"from":[42],"low":[43],"data":[44],"reuse,":[45],"others":[47],"coarse-grained":[49],"are":[51],"limited":[52],"wrestling":[55],"between":[56],"kernel":[57],"performance":[58],"model":[60],"quality":[61],"different":[63],"grain":[64,73,116,146],"sizes.":[65],"We":[66,98],"propose":[67],"column-vector-sparse-encoding":[68],"that":[69,106],"has":[70,107],"a":[71],"smaller":[72],"size":[74,147],"same":[77],"reuse":[78],"rate":[79],"compared":[80],"with":[81,144],"block":[82],"sparsity.":[83],"Column-vector-sparse-encoding":[84],"applied":[87],"both":[89],"SpMM":[90,123],"&":[91],"SDDMM,":[92],"two":[93],"major":[94],"operations.":[97],"also":[99],"introduce":[100],"Tensor-Core-based":[102],"1D":[103],"Octet":[104],"Tiling":[105],"efficient":[108],"memory":[109],"access":[110],"computation":[112],"patterns":[113],"small":[115],"size.":[117],"Based":[118],"on":[119],"these,":[120],"we":[121],"design":[122],"SDDMM":[125],"kernels":[126],"1.71-7.19x":[129],"cuSPARSE.":[132],"Practical":[133],"is":[135],"achieved":[136],">70%":[140],">90%":[142],"4x1":[145]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6}],"updated_date":"2026-08-15T07:11:24.734988","created_date":"2025-10-10T00:00:00"}