{"id":"https://openalex.org/W2771613338","doi":"https://doi.org/10.1145/3151032","title":"A Framework for Automated and Controlled Floating-Point Accuracy Reduction in Graphics Applications on GPUs","display_name":"A Framework for Automated and Controlled Floating-Point Accuracy Reduction in Graphics Applications on GPUs","publication_year":2017,"publication_date":"2017-12-05","ids":{"openalex":"https://openalex.org/W2771613338","doi":"https://doi.org/10.1145/3151032","mag":"2771613338"},"language":"en","primary_location":{"id":"doi:10.1145/3151032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3151032","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3151032?download=true","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3151032?download=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081917319","display_name":"Alexandra Angerd","orcid":null},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Alexandra Angerd","raw_affiliation_strings":["Chalmers University of Technology, G\u00f6teborg, Sweden"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, G\u00f6teborg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027492252","display_name":"Erik Sintorn","orcid":"https://orcid.org/0000-0003-3784-3936"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Erik Sintorn","raw_affiliation_strings":["Chalmers University of Technology, G\u00f6teborg, Sweden"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, G\u00f6teborg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091704449","display_name":"Per Stenstr\u00f6m","orcid":"https://orcid.org/0000-0002-7441-8245"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Per Stenstr\u00f6m","raw_affiliation_strings":["Chalmers University of Technology, G\u00f6teborg, Sweden"],"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology, G\u00f6teborg, Sweden","institution_ids":["https://openalex.org/I66862912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081917319"],"corresponding_institution_ids":["https://openalex.org/I66862912"],"apc_list":null,"apc_paid":null,"fwci":1.158,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.8074663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"14","issue":"4","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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":0.994700014591217,"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/register-file","display_name":"Register file","score":0.9351852536201477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8340755701065063},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.776247501373291},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7245751619338989},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.6923686265945435},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5589888691902161},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.5217962265014648},{"id":"https://openalex.org/keywords/register-allocation","display_name":"Register allocation","score":0.5058066844940186},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5048149228096008},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4874022603034973},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.48387444019317627},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4477342963218689},{"id":"https://openalex.org/keywords/floating-point-unit","display_name":"Floating-point unit","score":0.43483296036720276},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.36093199253082275},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2754392921924591},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.20524781942367554},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1759341061115265}],"concepts":[{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.9351852536201477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8340755701065063},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.776247501373291},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7245751619338989},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.6923686265945435},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5589888691902161},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.5217962265014648},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.5058066844940186},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5048149228096008},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4874022603034973},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.48387444019317627},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4477342963218689},{"id":"https://openalex.org/C110305270","wikidata":"https://www.wikidata.org/wiki/Q733507","display_name":"Floating-point unit","level":3,"score":0.43483296036720276},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.36093199253082275},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2754392921924591},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.20524781942367554},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1759341061115265},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3151032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3151032","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3151032?download=true","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:publications.lib.chalmers.se:253839","is_oa":false,"landing_page_url":"http://publications.lib.chalmers.se/publication/253839-a-framework-for-automated-and-controlled-floating-point-accuracy-reduction-in-graphics-applications","pdf_url":null,"source":{"id":"https://openalex.org/S4377196470","display_name":"Chalmers Publication Library (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text.Article.Journal.PeerReviewed"},{"id":"pmh:oai:research.chalmers.se:500677","is_oa":false,"landing_page_url":"https://research.chalmers.se/en/publication/9503eb1a-99ca-470f-804e-015e6361b4c2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402469","display_name":"Chalmers Research (Chalmers University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66862912","host_organization_name":"Chalmers University of Technology","host_organization_lineage":["https://openalex.org/I66862912"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.1145/3151032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3151032","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3151032?download=true","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9100000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2771613338.pdf","grobid_xml":"https://content.openalex.org/works/W2771613338.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1976928721","https://openalex.org/W1991518265","https://openalex.org/W2014423307","https://openalex.org/W2026186397","https://openalex.org/W2057434193","https://openalex.org/W2078206529","https://openalex.org/W2078782167","https://openalex.org/W2081140905","https://openalex.org/W2081368694","https://openalex.org/W2111502420","https://openalex.org/W2133665775","https://openalex.org/W2138777150","https://openalex.org/W2142096775","https://openalex.org/W2143283746","https://openalex.org/W2153185479","https://openalex.org/W2159211021","https://openalex.org/W2160203169","https://openalex.org/W2164474450","https://openalex.org/W2170881177","https://openalex.org/W2238992335","https://openalex.org/W2244395066","https://openalex.org/W2567051523","https://openalex.org/W2610467942","https://openalex.org/W2612048219","https://openalex.org/W4240237526","https://openalex.org/W4255681033"],"related_works":["https://openalex.org/W2116803521","https://openalex.org/W1564887326","https://openalex.org/W2169016399","https://openalex.org/W3215589575","https://openalex.org/W2000092506","https://openalex.org/W1589067093","https://openalex.org/W2363539709","https://openalex.org/W2541658314","https://openalex.org/W2462751277","https://openalex.org/W2771613338"],"abstract_inverted_index":{"Reducing":[0],"the":[1,21,35,39,43,52,61,125,160,168,191,197],"precision":[2,22,55,66,126],"of":[3,24,54,56,67,128,139,159,188],"floating-point":[4,25,58,69,74,108,129,165,183],"values":[5,26,75,110,166,184],"can":[6,71,106,154,217],"improve":[7],"performance":[8],"and/or":[9],"reduce":[10],"energy":[11],"expenditure":[12],"in":[13,27,149,167,228],"computer":[14],"graphics,":[15],"among":[16],"other,":[17],"applications.":[18],"However,":[19],"reducing":[20],"level":[23,127],"a":[28,46,64,80,99,120,132,136,144,156,212],"controlled":[29],"fashion":[30],"needs":[31],"support":[32],"both":[33],"at":[34,38,111],"compiler":[36,44],"and":[37,98,135,173,206],"microarchitecture":[40,62],"level.":[41],"At":[42,60],"level,":[45,63],"method":[47,97,118,153],"is":[48],"needed":[49,162],"to":[50,76,163,204,220,223],"automate":[51],"reduction":[53],"each":[57,68],"value.":[59],"lower":[65],"register":[70,81,88,102,109,177,198],"allow":[72],"more":[73],"be":[77],"packed":[78],"into":[79,190],"file.":[82],"This,":[83],"however,":[84],"calls":[85],"for":[86,123,211],"new":[87],"file":[89,103,178],"organizations.":[90],"This":[91,195,216],"article":[92],"proposes":[93],"an":[94],"automated":[95,116],"precision-selection":[96,117],"novel":[100],"GPU":[101],"organization":[104,179],"that":[105],"store":[107],"arbitrary":[112],"precisions":[113],"densely.":[114],"The":[115],"uses":[119],"data-driven":[121],"approach":[122],"setting":[124],"values,":[130],"given":[131],"quality":[133],"threshold":[134],"representative":[137],"set":[138],"input":[140],"data.":[141],"By":[142],"allowing":[143],"small,":[145],"but":[146],"acceptable,":[147],"degradation":[148],"output":[150],"quality,":[151],"our":[152],"remove":[155],"significant":[157],"amount":[158],"bits":[161],"represent":[164],"investigated":[169],"kernels":[170],"(between":[171],"28%":[172],"60%).":[174],"Our":[175],"proposed":[176],"exploits":[180],"these":[181],"lower-precision":[182],"by":[185,202,207],"packing":[186],"several":[187],"them":[189],"same":[192],"physical":[193],"register.":[194],"reduces":[196],"pressure":[199],"per":[200],"thread":[201],"up":[203,222],"48%,":[205],"27%":[208],"on":[209],"average,":[210],"negligible":[213],"output-quality":[214],"degradation.":[215],"enable":[218],"GPUs":[219],"keep":[221],"twice":[224],"as":[225],"many":[226],"threads":[227],"flight":[229],"simultaneously.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
