{"id":{"repo_id":"oregon","oai_identifier":"oai:scholarsbank.uoregon.edu:1794/25692"},"canonical_url":"https://search.dev.ndltd.org/etd/oregon/oai:scholarsbank.uoregon.edu:1794/25692","repository":{"repo_id":"oregon","name":"University of Oregon","base_url":"https://scholarsbank.uoregon.edu/server/oai/request"},"display":{"title":"In-Line vs. In-Transit In Situ: Which Technique to Use at Scale?","abstract":"In situ visualization is increasingly necessary to address I/O limitations on supercomputers. With the increasing heterogeneity of supercomputer design, efficient and cost effective use of resources is extremely difficult for in situ visualization routines. In this work, we present a time and cost analysis of two different classes of common visualization algorithms in order to determine which in situ paradigm (in-line or in-transit) to use at scale, and under what circumstances. We explore a high computation and low communication algorithm, as well as a low computation and medium communication algorithm. We use 255 individual experimental runs to compare these algorithms performance at scale (up to 32,768 cores in-line and 16,384 core in-transit) with a running simulation. Finally, we show that — contrary to community belief — in-transit in situ has the potential to be both faster and more cost efficient than in-line in situ. We term this discovery Visualization Cost Efficiency Factor (VCEF), which is a measure of how much more performant in-transit in situ is on a smaller subset of nodes than in-line in situ is at the full scale of a simulation. Our results for these algorithms showed in-transit VCEF values of up to 8X at our highest concurrencies. This dissertation includes previously published co-authored material","abstract_html":"In situ visualization is increasingly necessary to address I/O limitations on supercomputers. With the increasing heterogeneity of supercomputer design, efficient and cost effective use of resources is extremely difficult for in situ visualization routines. In this work, we present a time and cost analysis of two different classes of common visualization algorithms in order to determine which in situ paradigm (in-line or in-transit) to use at scale, and under what circumstances. We explore a high computation and low communication algorithm, as well as a low computation and medium communication algorithm. We use 255 individual experimental runs to compare these algorithms performance at scale (up to 32,768 cores in-line and 16,384 core in-transit) with a running simulation. Finally, we show that — contrary to community belief — in-transit in situ has the potential to be both faster and more cost efficient than in-line in situ. We term this discovery Visualization Cost Efficiency Factor (VCEF), which is a measure of how much more performant in-transit in situ is on a smaller subset of nodes than in-line in situ is at the full scale of a simulation. Our results for these algorithms showed in-transit VCEF values of up to 8X at our highest concurrencies. This dissertation includes previously published co-authored material","abstract_has_math":false,"creators":["Kress, James"],"institution":"University of Oregon","degree_name":"Ph.D.","degree_level":"doctoral","degree_discipline":"Department of Computer and Information Science","degree_department":null,"school":null,"contributors":[],"advisors":["Childs, Hank"],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-09-24","date_published":"2020-09-24","updated_at":"2026-08-21T16:47:18Z","subjects":["HPC","in situ","in-line","in-transit","visualization"],"languages":["en_US"],"rights":["All Rights Reserved."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1794/25692","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"source_record":{"url":"https://scholarsbank.uoregon.edu/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Ascholarsbank.uoregon.edu%3A1794%2F25692","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Childs, Hank"]},{"key":"dc:creator","label":"Author","values":["Kress, James"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-09-24T17:34:26Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-09-24"]},{"key":"dc:publisher","label":"Institution","values":["University of Oregon"]},{"key":"dc:type","label":"Dc Type","values":["Electronic Thesis or Dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Computer and Information Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Oregon"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["HPC","in situ","in-line","in-transit","visualization"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["All Rights Reserved."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1794/25692"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In situ visualization is increasingly necessary to address I/O limitations on supercomputers. With the increasing heterogeneity of supercomputer design, efficient and cost effective use of resources is extremely difficult for in situ visualization routines. In this work, we present a time and cost analysis of two different classes of common visualization algorithms in order to determine which in situ paradigm (in-line or in-transit) to use at scale, and under what circumstances. We explore a high computation and low communication algorithm, as well as a low computation and medium communication algorithm. We use 255 individual experimental runs to compare these algorithms performance at scale (up to 32,768 cores in-line and 16,384 core in-transit) with a running simulation. Finally, we show that — contrary to community belief — in-transit in situ has the potential to be both faster and more cost efficient than in-line in situ. We term this discovery Visualization Cost Efficiency Factor (VCEF), which is a measure of how much more performant in-transit in situ is on a smaller subset of nodes than in-line in situ is at the full scale of a simulation. Our results for these algorithms showed in-transit VCEF values of up to 8X at our highest concurrencies. This dissertation includes previously published co-authored material"]},{"key":"dc:title","label":"Title","values":["In-Line vs. In-Transit In Situ: Which Technique to Use at Scale?"]}]}],"canonical_facts":{"dc:contributor.advisor":["Childs, Hank"],"dc:creator":["Kress, James"],"dc:date.accessioned":["2020-09-24T17:34:26Z"],"dc:date.issued":["2020-09-24"],"dc:description.abstract":["In situ visualization is increasingly necessary to address I/O limitations on supercomputers. With the increasing heterogeneity of supercomputer design, efficient and cost effective use of resources is extremely difficult for in situ visualization routines. In this work, we present a time and cost analysis of two different classes of common visualization algorithms in order to determine which in situ paradigm (in-line or in-transit) to use at scale, and under what circumstances. We explore a high computation and low communication algorithm, as well as a low computation and medium communication algorithm. We use 255 individual experimental runs to compare these algorithms performance at scale (up to 32,768 cores in-line and 16,384 core in-transit) with a running simulation. Finally, we show that — contrary to community belief — in-transit in situ has the potential to be both faster and more cost efficient than in-line in situ. We term this discovery Visualization Cost Efficiency Factor (VCEF), which is a measure of how much more performant in-transit in situ is on a smaller subset of nodes than in-line in situ is at the full scale of a simulation. Our results for these algorithms showed in-transit VCEF values of up to 8X at our highest concurrencies. This dissertation includes previously published co-authored material"],"dc:identifier.uri":["https://hdl.handle.net/1794/25692"],"dc:language.iso":["en_US"],"dc:publisher":["University of Oregon"],"dc:rights":["All Rights Reserved."],"dc:subject":["HPC","in situ","in-line","in-transit","visualization"],"dc:title":["In-Line vs. In-Transit In Situ: Which Technique to Use at Scale?"],"dc:type":["Electronic Thesis or Dissertation"],"thesis:degree_discipline":["Department of Computer and Information Science"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Oregon"]},"updated_at":"2026-08-21T16:47:18Z"}