{"id":"https://openalex.org/W4403786292","doi":"https://doi.org/10.48550/arxiv.2409.15468","title":"FRSZ2 for In-Register Block Compression Inside GMRES on GPUs","display_name":"FRSZ2 for In-Register Block Compression Inside GMRES on GPUs","publication_year":2024,"publication_date":"2024-09-23","ids":{"openalex":"https://openalex.org/W4403786292","doi":"https://doi.org/10.48550/arxiv.2409.15468"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.15468","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.15468","pdf_url":"https://arxiv.org/pdf/2409.15468","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.15468","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103081244","display_name":"Thomas Gr\u00fctzmacher","orcid":"https://orcid.org/0000-0001-9346-2981"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gr\u00fctzmacher, Thomas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056940311","display_name":"Robert Underwood","orcid":"https://orcid.org/0000-0002-1464-729X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Underwood, Robert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066430343","display_name":"Sheng Di","orcid":"https://orcid.org/0000-0002-7339-5256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di, Sheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cappello, Franck","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012133869","display_name":"Hartwig Anzt","orcid":"https://orcid.org/0000-0003-2177-952X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anzt, Hartwig","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103081244"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9125000238418579,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9125000238418579,"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/generalized-minimal-residual-method","display_name":"Generalized minimal residual method","score":0.7752962708473206},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6663856506347656},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6599810719490051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6175363063812256},{"id":"https://openalex.org/keywords/register","display_name":"Register (sociolinguistics)","score":0.59446781873703},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4239237606525421},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.29696935415267944},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13790708780288696},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13204875588417053},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.09157532453536987},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.04626786708831787}],"concepts":[{"id":"https://openalex.org/C155332342","wikidata":"https://www.wikidata.org/wiki/Q1432976","display_name":"Generalized minimal residual method","level":3,"score":0.7752962708473206},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6663856506347656},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6599810719490051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6175363063812256},{"id":"https://openalex.org/C2779235478","wikidata":"https://www.wikidata.org/wiki/Q286576","display_name":"Register (sociolinguistics)","level":2,"score":0.59446781873703},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4239237606525421},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.29696935415267944},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13790708780288696},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13204875588417053},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09157532453536987},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.04626786708831787},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.15468","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.15468","pdf_url":"https://arxiv.org/pdf/2409.15468","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.15468","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.15468","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.15468","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.15468","pdf_url":"https://arxiv.org/pdf/2409.15468","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1732463247","display_name":null,"funder_award_id":"2311875","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2777053550","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3232922872","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3318903820","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6848031779","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6859237865","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6918803902","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G7351994996","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7954425250","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8052219770","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G8143874970","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8253304997","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G878601127","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403786292.pdf","grobid_xml":"https://content.openalex.org/works/W4403786292.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2358905935","https://openalex.org/W3046241855","https://openalex.org/W2139875628","https://openalex.org/W1995427418","https://openalex.org/W70795231","https://openalex.org/W2788372305","https://openalex.org/W2040391781","https://openalex.org/W2538790291","https://openalex.org/W2013798243","https://openalex.org/W2029210135"],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,60,79,94,99],"the":[3,12,24,32,58,61,67,76,100],"GMRES":[4,19,21],"iterative":[5],"solver":[6],"on":[7],"GPUs":[8],"is":[9,38],"limited":[10],"by":[11,22],"GPU":[13],"main":[14],"memory":[15,33],"bandwidth.":[16],"Compressed":[17],"Basis":[18],"outperforms":[20],"storing":[23],"Krylov":[25,101],"basis":[26,102],"in":[27],"low":[28,49,95],"precision,":[29],"thereby":[30],"reducing":[31],"access.":[34],"An":[35],"open":[36],"question":[37],"whether":[39],"compression":[40,98],"techniques":[41],"that":[42,72],"are":[43],"more":[44],"sophisticated":[45],"than":[46],"casting":[47],"to":[48],"precision":[50,96],"can":[51,73,103],"enable":[52],"large":[53],"runtime":[54,106],"savings":[55],"while":[56],"preserving":[57],"accuracy":[59],"final":[62,110],"results.":[63],"This":[64],"paper":[65],"presents":[66],"lightweight":[68],"in-register":[69],"compressor":[70],"FRSZ2":[71,92],"decompress":[74],"at":[75],"bandwidth":[77],"speed":[78],"a":[80],"modern":[81],"NVIDIA":[82],"H100":[83],"GPU.":[84],"In":[85],"an":[86],"experimental":[87],"evaluation,":[88],"we":[89],"demonstrate":[90],"using":[91],"instead":[93],"for":[97],"bring":[104],"larger":[105],"benefits":[107],"without":[108],"impacting":[109],"accuracy.":[111]},"counts_by_year":[],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
