{"id":{"repo_id":"missouri","oai_identifier":"oai:mospace.umsystem.edu:10355/60461"},"canonical_url":"https://search.dev.ndltd.org/etd/missouri/oai:mospace.umsystem.edu:10355/60461","repository":{"repo_id":"missouri","name":"University of Missouri","base_url":"https://mospace.umsystem.edu/oai/request"},"display":{"title":"Analysis of performance/accuracy tradeoffs for floating point applications on GPUS","abstract":"Floating-point computations produce approximate results, which can lead to inaccuracy problems. Existing work addresses two issues: first, the design of high precision floatingpoint representations; second, the study of methods to trade-off accuracy and performance of serial CPU applications. However, a comprehensive study of the trade-off between accuracy and performance for multithreaded applications is missing. In my thesis, I study this trade-off on GPU. In particular, my study covers the use of different floating-point precisions (i.e., single and double floating-point precision in IEEE 754 standard, GNU Multiple Precision, and composite floating-point precision) on a variety of real-world and synthetic benchmark applications. I explore how the use of multithreading and instruction-level parallelism on GPU can allow the use of higher precision arithmetic to improve accuracy without paying in terms of execution time. As a result of my analysis, I provide insights to guide users to the selection of the arithmetic precision leading to a good performance/accuracy tradeoff depending on the arithmetic operations used in their program (addition, multiplication, division), the degree of multithreading of their program, and its arithmetic intensity.","abstract_html":"Floating-point computations produce approximate results, which can lead to inaccuracy problems. Existing work addresses two issues: first, the design of high precision floatingpoint representations; second, the study of methods to trade-off accuracy and performance of serial CPU applications. However, a comprehensive study of the trade-off between accuracy and performance for multithreaded applications is missing. In my thesis, I study this trade-off on GPU. In particular, my study covers the use of different floating-point precisions (i.e., single and double floating-point precision in IEEE 754 standard, GNU Multiple Precision, and composite floating-point precision) on a variety of real-world and synthetic benchmark applications. I explore how the use of multithreading and instruction-level parallelism on GPU can allow the use of higher precision arithmetic to improve accuracy without paying in terms of execution time. As a result of my analysis, I provide insights to guide users to the selection of the arithmetic precision leading to a good performance/accuracy tradeoff depending on the arithmetic operations used in their program (addition, multiplication, division), the degree of multithreading of their program, and its arithmetic intensity.","abstract_has_math":false,"creators":["Nguyen, Huyen"],"institution":"University of Missouri--Columbia","degree_name":"M.S.","degree_level":"Masters","degree_discipline":"Computer engineering (MU)","degree_department":null,"school":null,"contributors":[],"advisors":["Becchi, Michela"],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016","date_published":"2016","updated_at":"2026-07-24T03:08:32Z","subjects":[],"languages":["eng","English"],"rights":["OpenAccess."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10355/60461","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Becchi, Michela"]},{"key":"dc:creator","label":"Author","values":["Nguyen, Huyen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2017-05-19T17:06:35Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2017-05-19T17:06:35Z"]},{"key":"dc:date.issued","label":"Date","values":["2016"]},{"key":"dc:publisher","label":"Institution","values":["University of Missouri--Columbia"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer engineering (MU)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Missouri--Columbia"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["OpenAccess."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10355/60461"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Floating-point computations produce approximate results, which can lead to inaccuracy problems. Existing work addresses two issues: first, the design of high precision floatingpoint representations; second, the study of methods to trade-off accuracy and performance of serial CPU applications. However, a comprehensive study of the trade-off between accuracy and performance for multithreaded applications is missing. In my thesis, I study this trade-off on GPU. In particular, my study covers the use of different floating-point precisions (i.e., single and double floating-point precision in IEEE 754 standard, GNU Multiple Precision, and composite floating-point precision) on a variety of real-world and synthetic benchmark applications. I explore how the use of multithreading and instruction-level parallelism on GPU can allow the use of higher precision arithmetic to improve accuracy without paying in terms of execution time. As a result of my analysis, I provide insights to guide users to the selection of the arithmetic precision leading to a good performance/accuracy tradeoff depending on the arithmetic operations used in their program (addition, multiplication, division), the degree of multithreading of their program, and its arithmetic intensity."]},{"key":"dc:title","label":"Title","values":["Analysis of performance/accuracy tradeoffs for floating point applications on GPUS"]}]}],"canonical_facts":{"dc:contributor.advisor":["Becchi, Michela"],"dc:creator":["Nguyen, Huyen"],"dc:date.accessioned":["2017-05-19T17:06:35Z"],"dc:date.available":["2017-05-19T17:06:35Z"],"dc:date.issued":["2016"],"dc:description.abstract":["Floating-point computations produce approximate results, which can lead to inaccuracy problems. Existing work addresses two issues: first, the design of high precision floatingpoint representations; second, the study of methods to trade-off accuracy and performance of serial CPU applications. However, a comprehensive study of the trade-off between accuracy and performance for multithreaded applications is missing. In my thesis, I study this trade-off on GPU. In particular, my study covers the use of different floating-point precisions (i.e., single and double floating-point precision in IEEE 754 standard, GNU Multiple Precision, and composite floating-point precision) on a variety of real-world and synthetic benchmark applications. I explore how the use of multithreading and instruction-level parallelism on GPU can allow the use of higher precision arithmetic to improve accuracy without paying in terms of execution time. As a result of my analysis, I provide insights to guide users to the selection of the arithmetic precision leading to a good performance/accuracy tradeoff depending on the arithmetic operations used in their program (addition, multiplication, division), the degree of multithreading of their program, and its arithmetic intensity."],"dc:identifier.uri":["https://hdl.handle.net/10355/60461"],"dc:language":["English"],"dc:language.iso":["eng"],"dc:publisher":["University of Missouri--Columbia"],"dc:rights":["OpenAccess."],"dc:title":["Analysis of performance/accuracy tradeoffs for floating point applications on GPUS"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer engineering (MU)"],"thesis:degree_level":["Masters"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Missouri--Columbia"]},"updated_at":"2026-07-24T03:08:32Z"}