{"id":"https://openalex.org/W7133491235","doi":"https://doi.org/10.1109/hpca68181.2026.11408484","title":"HERO-Sign: Hierarchical Tuning and Efficient Compiler-Time GPU Optimizations for SPHINCS+ Signature Generation","display_name":"HERO-Sign: Hierarchical Tuning and Efficient Compiler-Time GPU Optimizations for SPHINCS+ Signature Generation","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7133491235","doi":"https://doi.org/10.1109/hpca68181.2026.11408484"},"language":null,"primary_location":{"id":"doi:10.1109/hpca68181.2026.11408484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","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/A5121757285","display_name":"Yaoyun Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaoyun Zhou","raw_affiliation_strings":["University of California,Department of EECS,Merced"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of EECS,Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391009","display_name":"Qian Wang","orcid":"https://orcid.org/0000-0001-8095-061X"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Wang","raw_affiliation_strings":["University of California,Department of Electrical Engineering,Merced"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical Engineering,Merced","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I156087764"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4505999982357025,"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":0.4505999982357025,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.15639999508857727,"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/T10126","display_name":"Logic, programming, and type systems","score":0.06080000102519989,"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/signature","display_name":"Signature (topology)","score":0.42080000042915344},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.29840001463890076},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.28999999165534973},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2842999994754791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6773999929428101},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39419999718666077},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2922999858856201},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.23980000615119934},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.23510000109672546}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca68181.2026.11408484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5333433151245117,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G6127571188","display_name":"CICI: UCSS: Usable and Attack-Resistant Security Framework for Quantum Emulators","funder_award_id":"2530705","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2023415862","https://openalex.org/W2039509099","https://openalex.org/W2052891002","https://openalex.org/W2121893797","https://openalex.org/W2146537406","https://openalex.org/W2167334577","https://openalex.org/W2168676717","https://openalex.org/W2559394418","https://openalex.org/W2781738013","https://openalex.org/W2906133437","https://openalex.org/W2987483625","https://openalex.org/W3026102703","https://openalex.org/W3092548444","https://openalex.org/W3175994455","https://openalex.org/W4254366963","https://openalex.org/W4296831830","https://openalex.org/W4319300636","https://openalex.org/W4402186983","https://openalex.org/W4402451239","https://openalex.org/W4407197132","https://openalex.org/W4409212896","https://openalex.org/W4410887443","https://openalex.org/W4411995829"],"related_works":[],"abstract_inverted_index":{"SPHINCS":[0,45],"+":[3,48,126,196,265],"is":[4,152],"a":[5,37,134,143,234,332],"stateless":[6],"hash-based":[7],"signature":[8,21],"scheme":[9],"known":[10],"for":[11,40,55,95,138,185],"its":[12,66,77],"strong":[13],"post-quantum":[14],"security,":[15],"but":[16],"it":[17,132,162],"suffers":[18],"from":[19,105],"slow":[20],"speed":[22],"due":[23],"to":[24,76,163,217,239,250],"the":[25,42,62,101,186,214,255,323],"heavy":[26],"use":[27],"of":[28,34,44,65,116,146,189,223,274],"hash":[29],"operations.":[30],"The":[31],"parallel":[32],"architecture":[33],"GPUs":[35],"offers":[36],"potential":[38,103],"advantage":[39],"accelerating":[41],"computation":[43],"signatures.":[49],"However,":[50],"existing":[51],"GPU-based":[52],"optimization":[53],"efforts":[54],"SPHINCS+":[56],"either":[57],"do":[58],"not":[59],"fully":[60],"exploit":[61],"inherent":[63],"parallelism":[64],"Merkle":[67],"Tree-based":[68],"structure,":[69],"or":[70],"lack":[71],"fine-grained,":[72],"compilerlevel":[73],"customization":[74],"tailored":[75],"diverse":[78],"computational":[79],"kernels.":[80],"This":[81,204],"paper":[82],"proposes":[83],"HERO-Sign,":[84],"which":[85],"adopts":[86,178],"hierarchical":[87],"tuning":[88],"methodologies":[89],"and":[90,123,165,210,232,244,262,297,326],"efficient":[91],"compiler-time":[92],"GPU":[93,171,252],"optimizations":[94,191],"SPHINCS+.":[98],"HERO-Sign":[99,177,226,269,329],"rethinks":[100],"parallelization":[102],"arising":[104],"data":[106],"independence":[107],"in":[108,335],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">+,":[111],"components,":[112],"including":[113,322],"FORS":[114,149],"(Forest":[115],"Random":[117],"Subsets),":[118],"MSS":[119],"(Merkle":[120],"Signature":[121,129],"Scheme,":[122],"WOTS+_Sign).":[203],"automatically":[206],"selects":[207],"between":[208],"PTX":[209],"native":[211],"branches":[212],"during":[213],"phase":[216],"maximize":[218],"efficiency.":[219],"For":[220],"multiple":[221],"batches":[222],"message":[224],"signatures,":[225],"focuses":[227],"on":[228,309,319],"optimizing":[229],"kernel-level":[230],"overlapping":[231],"employs":[233],"Task":[235],"Graph-based":[236],"construction":[237],"minimize":[240],"multi-stream":[241],"idle":[242],"time":[243],"reduce":[245],"kernel":[246,336],"launch":[247,337],"overhead.":[248],"Compared":[249],"state-of-the-art":[251],"implementations,":[253],"under":[254],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">+-128f,":[258],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">+-192f":[261],"256f":[266],"parameter":[267],"sets,":[268],"demonstrates":[270],"enhanced":[272],"throughput":[273],"$\\mathbf{1.":[277,300],"2":[278,289,301],"8}":[279,290],"\\times":[280,285,291,303],"\\mathbf{-":[281,292,304],"3.":[282],"1":[283],"3}":[284],"\\mathbf{,":[286],"~}":[287],"\\mathbf{1.":[288],"2.":[293,305],"9":[294],"2}":[295],"\\times$,":[296],"4}":[302],"6":[306],"0}":[307],"\\times$":[308],"RTX":[310],"4090.":[311],"Similar":[312],"performance":[313],"improvements":[314],"have":[315],"also":[316,330],"been":[317],"achieved":[318],"other":[320],"architectures,":[321],"A100,":[324],"H100,":[325],"GTX":[327],"2080.":[328],"achieves":[331],"two-order-of-magnitude":[333],"reduction":[334],"latency.":[338]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-05T00:00:00"}