{"id":"https://openalex.org/W4416004077","doi":"https://doi.org/10.1145/3731599.3767361","title":"Towards an Automated Workflow for Floating-Point Analysis of GPU Kernels","display_name":"Towards an Automated Workflow for Floating-Point Analysis of GPU Kernels","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004077","doi":"https://doi.org/10.1145/3731599.3767361"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767361","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops 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://doi.org/10.1145/3731599.3767361","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001193508","display_name":"Esteban Rangel","orcid":"https://orcid.org/0000-0003-2330-9820"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Esteban Miguel Rangel","raw_affiliation_strings":["Argonne National Laboratory (ANL), Lemont, USA"],"raw_orcid":"https://orcid.org/0000-0003-2330-9820","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory (ANL), Lemont, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084262733","display_name":"S. J. Pennycook","orcid":"https://orcid.org/0000-0003-0237-3823"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. John Pennycook","raw_affiliation_strings":["Intel Corporation, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0003-0237-3823","affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34121622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"217","last_page":"224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5756999850273132,"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":0.5756999850273132,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.2345999926328659,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.050700001418590546,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/compiler","display_name":"Compiler","score":0.7060999870300293},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6915000081062317},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5932000279426575},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.44110000133514404},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.41600000858306885},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4090000092983246},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.39719998836517334},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.37290000915527344},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.37229999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500999808311462},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7060999870300293},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6915000081062317},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5932000279426575},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49779999256134033},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.44110000133514404},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4196000099182129},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3506999909877777},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2978000044822693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C115874739","wikidata":"https://www.wikidata.org/wiki/Q825377","display_name":"Critical path method","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C2984968299","wikidata":"https://www.wikidata.org/wiki/Q1077784","display_name":"Software tool","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.2623000144958496},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767361","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767361","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1985462363","https://openalex.org/W1991592471","https://openalex.org/W2086748522","https://openalex.org/W2802647233","https://openalex.org/W2948348275","https://openalex.org/W2952851876","https://openalex.org/W2962766833","https://openalex.org/W2967088612","https://openalex.org/W3023584751","https://openalex.org/W3195293013","https://openalex.org/W4246166885","https://openalex.org/W4388581065","https://openalex.org/W4388665000"],"related_works":[],"abstract_inverted_index":{"We":[0,50],"present":[1],"early":[2],"work":[3,101],"towards":[4],"establishing":[5],"an":[6],"automated":[7],"workflow":[8],"for":[9,22],"floating-point":[10,42,110],"error":[11,43],"analysis":[12],"of":[13,30,82,109],"SYCL":[14,32],"kernels.":[15],"The":[16],"method":[17],"leverages":[18],"the":[19,28,47,52,80,83],"Intercept":[20],"Layer":[21],"OpenCL":[23],"Applica-":[24],"tions":[25],"to":[26],"record":[27],"execution":[29],"GPU-targeted":[31],"kernels":[33],"and":[34,64,70,92,98],"replay":[35],"them":[36],"with":[37],"CPU":[38],"runtimes,":[39],"enabling":[40],"detailed":[41],"evaluation":[44,112],"without":[45],"modifying":[46],"original":[48],"application.":[49],"analyze":[51],"force":[53],"kernel":[54],"from":[55],"a":[56,103],"large-scale":[57],"cosmology":[58],"application":[59],"code":[60],"(HACC)":[61],"using":[62,87],"PoCL":[63],"Verificarlo,":[65],"exploring":[66],"both":[67],"IEEE-compliant":[68],"configurations":[69],"reduced-precision":[71],"modes":[72],"(e.g.,,":[73],"FP16,":[74],"TF32,":[75],"BF16),":[76],"as":[77,79],"well":[78],"effects":[81],"-ffast-math":[84],"compiler":[85],"optimization":[86],"stochastic":[88],"arithmetic":[89],"via":[90],"MCA":[91],"PRISM.":[93],"By":[94],"leveraging":[95],"open":[96],"tools":[97],"standards,":[99],"this":[100],"contributes":[102],"reusable":[104],"path":[105],"toward":[106],"broader":[107],"adoption":[108],"accuracy":[111],"in":[113],"HPC.":[114]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-07T00:00:00"}
