{"id":"https://openalex.org/W4393576100","doi":"https://doi.org/10.1145/3626202.3637568","title":"LevelST: Stream-based Accelerator for Sparse Triangular Solver","display_name":"LevelST: Stream-based Accelerator for Sparse Triangular Solver","publication_year":2024,"publication_date":"2024-04-01","ids":{"openalex":"https://openalex.org/W4393576100","doi":"https://doi.org/10.1145/3626202.3637568"},"language":"en","primary_location":{"id":"doi:10.1145/3626202.3637568","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626202.3637568","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626202.3637568","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","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/10.1145/3626202.3637568","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103241031","display_name":"Zifan He","orcid":"https://orcid.org/0009-0008-3482-838X"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zifan He","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0009-0008-3482-838X","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036239104","display_name":"Linghao Song","orcid":"https://orcid.org/0000-0002-7450-2842"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linghao Song","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-7450-2842","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025422213","display_name":"Robert F. Lucas","orcid":"https://orcid.org/0000-0003-1303-2012"},"institutions":[{"id":"https://openalex.org/I21160419","display_name":"Ansys (United States)","ror":"https://ror.org/05cf5b117","country_code":"US","type":"company","lineage":["https://openalex.org/I21160419"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert F. Lucas","raw_affiliation_strings":["Ansys, Inc., Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0003-1303-2012","affiliations":[{"raw_affiliation_string":"Ansys, Inc., Livermore, USA","institution_ids":["https://openalex.org/I21160419"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016776689","display_name":"Jason Cong","orcid":"https://orcid.org/0000-0003-2887-6963"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Cong","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0003-2887-6963","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103241031"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":3.7948,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9423771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"77"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.8552472591400146},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6577395796775818},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5983039140701294},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.575476884841919},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5675263404846191},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5664076209068298},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4593302607536316},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.453899085521698},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4356231987476349},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.26601341366767883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8552472591400146},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6577395796775818},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5983039140701294},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.575476884841919},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5675263404846191},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5664076209068298},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4593302607536316},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.453899085521698},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4356231987476349},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.26601341366767883},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626202.3637568","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626202.3637568","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626202.3637568","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3626202.3637568","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626202.3637568","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626202.3637568","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1201618783","display_name":null,"funder_award_id":"000705769","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G2965377465","display_name":null,"funder_award_id":"000705769","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393576100.pdf","grobid_xml":"https://content.openalex.org/works/W4393576100.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1561017135","https://openalex.org/W1969468690","https://openalex.org/W2002555321","https://openalex.org/W2014730252","https://openalex.org/W2035080386","https://openalex.org/W2045285941","https://openalex.org/W2071877138","https://openalex.org/W2092762191","https://openalex.org/W2094756095","https://openalex.org/W2095258827","https://openalex.org/W2095420020","https://openalex.org/W2105430723","https://openalex.org/W2167334577","https://openalex.org/W2316564661","https://openalex.org/W2469975815","https://openalex.org/W2622148586","https://openalex.org/W2626696598","https://openalex.org/W2789228469","https://openalex.org/W2793572619","https://openalex.org/W2950629094","https://openalex.org/W2985437351","https://openalex.org/W3048232878","https://openalex.org/W3048330007","https://openalex.org/W3133395503","https://openalex.org/W3198975860","https://openalex.org/W4232006005","https://openalex.org/W4248633161","https://openalex.org/W4293024216","https://openalex.org/W4313447739"],"related_works":["https://openalex.org/W1973046741","https://openalex.org/W2983282793","https://openalex.org/W4376647684","https://openalex.org/W2052993554","https://openalex.org/W2046125858","https://openalex.org/W2532502681","https://openalex.org/W1541167181","https://openalex.org/W4389888442","https://openalex.org/W2149529325","https://openalex.org/W3103168911"],"abstract_inverted_index":{"Over":[0],"the":[1,11,37,54,138,176,212,220,234,237],"past":[2],"decade,":[3],"much":[4],"progress":[5],"has":[6],"been":[7],"made":[8],"to":[9,29,106,173,182],"advance":[10],"acceleration":[12],"of":[13,157,236],"sparse":[14,31,149,207],"linear":[15,46],"operators":[16],"such":[17,52,67],"as":[18,53,68],"SpMM":[19],"and":[20,36,71,99,120,185,203,215,228,240],"SpMV":[21],"on":[22,196,248],"FPGAs.":[23],"Nevertheless,":[24],"few":[25],"works":[26],"have":[27,135],"attempted":[28],"address":[30,131],"triangular":[32,150,208],"solver":[33],"(SpTRSV)":[34],"acceleration,":[35],"performance":[38],"boost":[39],"is":[40,43,77,194,246],"limited.":[41],"SpTRSV":[42,76],"an":[44,125,197],"elementary":[45],"operator":[47],"for":[48,115,124,147],"many":[49,80],"numerical":[50],"methods,":[51,58],"least-square":[55],"method.":[56],"These":[57],"among":[59],"others,":[60],"are":[61],"widely":[62],"used":[63],"in":[64],"various":[65],"areas,":[66],"physical":[69],"simulation":[70],"signal":[72],"processing.":[73],"Therefore,":[74],"accelerating":[75,83],"crucial.":[78],"However,":[79],"challenges":[81],"impede":[82],"SpTRSV,":[84],"including":[85],"(1)":[86,154],"resolving":[87],"dependencies":[88],"between":[89],"elements":[90],"during":[91],"forward":[92],"or":[93,118],"backward":[94],"substitutions,":[95],"(2)":[96,166],"random":[97],"access":[98,114],"unbalanced":[100],"workloads":[101],"across":[102],"memory":[103,113,145],"channels":[104],"due":[105],"sparsity,":[107],"(3)":[108,178],"latency":[109],"incurred":[110],"by":[111],"off-chip":[112,163,191],"large":[116],"matrices":[117],"vectors,":[119],"(4)":[121,186],"data":[122,127,164,188],"reuse":[123],"unpredictable":[126],"sharing":[128,168],"pattern.":[129],"To":[130],"these":[132],"issues,":[133],"we":[134],"designed":[136],"LevelST,":[137],"first":[139],"FPGA":[140,202],"accelerator":[141],"leveraging":[142],"high":[143],"bandwidth":[144],"(HBM)":[146],"solving":[148],"systems.":[151],"LevelST":[152,193,223],"features":[153],"algorithm-hardware":[155],"co-design":[156],"stream-based":[158],"dependency":[159],"resolution":[160],"with":[161,205,211],"reduced":[162],"movement,":[165],"resource":[167,171],"that":[169],"improves":[170],"utilization":[172],"scale":[174],"up":[175],"architecture,":[177],"index":[179],"modulo":[180],"scheduling":[181],"balance":[183],"workload,":[184],"selective":[187],"prefetching":[189],"from":[190],"memory.":[192],"prototyped":[195],"AMD":[198],"Xilinx":[199],"U280":[200],"HBM":[201],"evaluated":[204],"16":[206],"matrices.":[209],"Compared":[210],"NVIDIA":[213],"V100":[214,238],"RTX":[216,241],"3060":[217,242],"GPUs":[218],"over":[219],"cuSPARSE":[221],"library,":[222],"achieves":[224],"a":[225],"2.65x":[226],"speedup":[227],"9.82x":[229],"higher":[230],"energy":[231],"efficiency":[232],"than":[233],"best":[235],"GPU":[239],"GPU.":[243],"The":[244],"code":[245],"released":[247],"https://github.com/OswaldHe/LevelST":[249],"(DOI:":[250],"https://doi.org/10.5281/zenodo.10463345).":[251]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}