{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/102842"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/102842","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Fast and generic concurrent message-passing","abstract":"Communication hardware and software have a significant impact on the performance of clusters and supercomputers. Message passing model and the Message-Passing Interface (MPI) is a widely used model of communications in the High-Performance Computing (HPC) community with great success. However, it has recently faced new challenges due to the emergence of many-core architecture and of programming models with dynamic task parallelism, assuming a large number of concurrent, light-weight threads. These applications come from important classes of applications such as graph and data analytics. Using MPI with these languages/runtimes is inefficient because MPI implementation is not able to perform well with threads. Using MPI as a communication middleware is also not efficient since MPI has to provide many abstractions that are not needed for many of the frameworks, thus having extra overheads. In this thesis, we studied MPI performance under the new assumptions. We identified several factors in the message-passing model which were inherently problematic for scalability and performance. Next, we analyzed the communication of a number of graph, threading and data-flow frameworks to identify generic patterns. We then proposed a low-level communication interface (LCI) to bridge the gap between communication architecture and runtime. The core of our idea is to attach to each message a few simple operations which fit better with the current hardware and can be implemented efficiently. We show that with only a few carefully chosen primitives and appropriate design, message-passing under this interface can easily outperform production MPI when running atop of multi-threaded environment. Further, using LCI is simple for various types of usage.","abstract_html":"Communication hardware and software have a significant impact on the performance of clusters and supercomputers. Message passing model and the Message-Passing Interface (MPI) is a widely used model of communications in the High-Performance Computing (HPC) community with great success. However, it has recently faced new challenges due to the emergence of many-core architecture and of programming models with dynamic task parallelism, assuming a large number of concurrent, light-weight threads. These applications come from important classes of applications such as graph and data analytics. Using MPI with these languages/runtimes is inefficient because MPI implementation is not able to perform well with threads. Using MPI as a communication middleware is also not efficient since MPI has to provide many abstractions that are not needed for many of the frameworks, thus having extra overheads. In this thesis, we studied MPI performance under the new assumptions. We identified several factors in the message-passing model which were inherently problematic for scalability and performance. Next, we analyzed the communication of a number of graph, threading and data-flow frameworks to identify generic patterns. We then proposed a low-level communication interface (LCI) to bridge the gap between communication architecture and runtime. The core of our idea is to attach to each message a few simple operations which fit better with the current hardware and can be implemented efficiently. We show that with only a few carefully chosen primitives and appropriate design, message-passing under this interface can easily outperform production MPI when running atop of multi-threaded environment. Further, using LCI is simple for various types of usage.","abstract_has_math":false,"creators":["Dang, Hoang-Vu"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Snir, Marc","Gropp, William","Adve, Sarita","Hoefler, Torsten"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-02-07T20:44:25Z","date_published":"2019-02-07T20:44:25Z","updated_at":"2026-07-22T22:24:42Z","subjects":["MPI","message-passing","communication","runtime","concurrency","parallelism","performance"],"languages":["en"],"rights":["Copyright 2018 Hoang-Vu Dang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/102842","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Snir, Marc","Gropp, William","Adve, Sarita","Hoefler, Torsten"]},{"key":"dc:creator","label":"Author","values":["Dang, Hoang-Vu"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-02-07T20:44:25Z","2021-02-08T10:15:32Z","2018-12-06","2018-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["MPI","message-passing","communication","runtime","concurrency","parallelism","performance"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2018 Hoang-Vu Dang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/102842"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Communication hardware and software have a significant impact on the performance of clusters and supercomputers. Message passing model and the Message-Passing Interface (MPI) is a widely used model of communications in the High-Performance Computing (HPC) community with great success. However, it has recently faced new challenges due to the emergence of many-core architecture and of programming models with dynamic task parallelism, assuming a large number of concurrent, light-weight threads. These applications come from important classes of applications such as graph and data analytics. Using MPI with these languages/runtimes is inefficient because MPI implementation is not able to perform well with threads. Using MPI as a communication middleware is also not efficient since MPI has to provide many abstractions that are not needed for many of the frameworks, thus having extra overheads. In this thesis, we studied MPI performance under the new assumptions. We identified several factors in the message-passing model which were inherently problematic for scalability and performance. Next, we analyzed the communication of a number of graph, threading and data-flow frameworks to identify generic patterns. We then proposed a low-level communication interface (LCI) to bridge the gap between communication architecture and runtime. The core of our idea is to attach to each message a few simple operations which fit better with the current hardware and can be implemented efficiently. We show that with only a few carefully chosen primitives and appropriate design, message-passing under this interface can easily outperform production MPI when running atop of multi-threaded environment. Further, using LCI is simple for various types of usage.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-12-01","The student, Hoang-Vu Dang, accepted the attached license on 2018-12-06 at 08:32.","The student, Hoang-Vu Dang, submitted this Dissertation for approval on 2018-12-06 at 08:36.","This Dissertation was approved for publication on 2018-12-06 at 16:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13231 on 2019-02-07 at 14:22:54","Made available in DSpace on 2019-02-07T20:44:25Z (GMT). No. of bitstreams: 4 DANG-DISSERTATION-2018.pdf: 1938044 bytes, checksum: 81b7d2f9446db80cd0600fd96934c77f (MD5) thesis.zip: 4515845 bytes, checksum: f93a5a19366e0294793fdd40795b6d0e (MD5) thesis_1.zip: 4515845 bytes, checksum: f93a5a19366e0294793fdd40795b6d0e (MD5) LICENSE.txt: 4210 bytes, checksum: 294796ec01736833cce3182e5d13a78d (MD5) Previous issue date: 2018-12-06","Embargo set by: Seth Robbins for item 109868 Lift date: 2021-02-07T20:44:35Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 109868 on 2021-02-08T10:15:32Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Fast and generic concurrent message-passing"]}]}],"canonical_facts":{"dc:contributor":["Snir, Marc","Gropp, William","Adve, Sarita","Hoefler, Torsten"],"dc:creator":["Dang, Hoang-Vu"],"dc:date":["2019-02-07T20:44:25Z","2021-02-08T10:15:32Z","2018-12-06","2018-12"],"dc:description":["Communication hardware and software have a significant impact on the performance of clusters and supercomputers. Message passing model and the Message-Passing Interface (MPI) is a widely used model of communications in the High-Performance Computing (HPC) community with great success. However, it has recently faced new challenges due to the emergence of many-core architecture and of programming models with dynamic task parallelism, assuming a large number of concurrent, light-weight threads. These applications come from important classes of applications such as graph and data analytics. Using MPI with these languages/runtimes is inefficient because MPI implementation is not able to perform well with threads. Using MPI as a communication middleware is also not efficient since MPI has to provide many abstractions that are not needed for many of the frameworks, thus having extra overheads. In this thesis, we studied MPI performance under the new assumptions. We identified several factors in the message-passing model which were inherently problematic for scalability and performance. Next, we analyzed the communication of a number of graph, threading and data-flow frameworks to identify generic patterns. We then proposed a low-level communication interface (LCI) to bridge the gap between communication architecture and runtime. The core of our idea is to attach to each message a few simple operations which fit better with the current hardware and can be implemented efficiently. We show that with only a few carefully chosen primitives and appropriate design, message-passing under this interface can easily outperform production MPI when running atop of multi-threaded environment. Further, using LCI is simple for various types of usage.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-12-01","The student, Hoang-Vu Dang, accepted the attached license on 2018-12-06 at 08:32.","The student, Hoang-Vu Dang, submitted this Dissertation for approval on 2018-12-06 at 08:36.","This Dissertation was approved for publication on 2018-12-06 at 16:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13231 on 2019-02-07 at 14:22:54","Made available in DSpace on 2019-02-07T20:44:25Z (GMT). No. of bitstreams: 4 DANG-DISSERTATION-2018.pdf: 1938044 bytes, checksum: 81b7d2f9446db80cd0600fd96934c77f (MD5) thesis.zip: 4515845 bytes, checksum: f93a5a19366e0294793fdd40795b6d0e (MD5) thesis_1.zip: 4515845 bytes, checksum: f93a5a19366e0294793fdd40795b6d0e (MD5) LICENSE.txt: 4210 bytes, checksum: 294796ec01736833cce3182e5d13a78d (MD5) Previous issue date: 2018-12-06","Embargo set by: Seth Robbins for item 109868 Lift date: 2021-02-07T20:44:35Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 109868 on 2021-02-08T10:15:32Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/102842"],"dc:language":["en"],"dc:rights":["Copyright 2018 Hoang-Vu Dang"],"dc:subject":["MPI","message-passing","communication","runtime","concurrency","parallelism","performance"],"dc:title":["Fast and generic concurrent message-passing"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:42Z"}