{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/90587"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/90587","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"GSI: a GPU stall inspector to characterize the sources of memory stalls for tightly coupled GPUs","abstract":"In recent years the power wall has prevented the continued scaling of single core performance. This has led to the rise of dark silicon and motivated a move toward parallelism and specialization. As a result, energy-efficient high-throughput GPU cores are increasingly favored for accelerating data-parallel applications. However, the best way to efficiently communicate and synchronize across heterogeneous cores remains an important open research question. Many methods have been proposed to improve the efficiency of heterogeneous memory systems, but current methods for evaluating the performance effects of these innovations are limited in their ability to attribute differences in execution time to sources of latency in the memory system. Performance characterization of tightly coupled CPU-GPU systems is complicated by the high levels of parallelism present in GPU codes. Existing simulation tools provide only coarse-grained metrics which can obscure the underlying memory system interactions that cause performance differences. In this thesis we introduce GPU Stall Inspector (GSI), a method for identifying and visualizing the causes of GPU stalls with a focus on a tightly coupled CPU-GPU memory subsystem. We demonstrate the utility of our approach by evaluating the sources of stalls in several recent architectural innovations for tightly coupled, heterogeneous CPU-GPU systems.","abstract_html":"In recent years the power wall has prevented the continued scaling of single core performance. This has led to the rise of dark silicon and motivated a move toward parallelism and specialization. As a result, energy-efficient high-throughput GPU cores are increasingly favored for accelerating data-parallel applications. However, the best way to efficiently communicate and synchronize across heterogeneous cores remains an important open research question. Many methods have been proposed to improve the efficiency of heterogeneous memory systems, but current methods for evaluating the performance effects of these innovations are limited in their ability to attribute differences in execution time to sources of latency in the memory system. Performance characterization of tightly coupled CPU-GPU systems is complicated by the high levels of parallelism present in GPU codes. Existing simulation tools provide only coarse-grained metrics which can obscure the underlying memory system interactions that cause performance differences. In this thesis we introduce GPU Stall Inspector (GSI), a method for identifying and visualizing the causes of GPU stalls with a focus on a tightly coupled CPU-GPU memory subsystem. We demonstrate the utility of our approach by evaluating the sources of stalls in several recent architectural innovations for tightly coupled, heterogeneous CPU-GPU systems.","abstract_has_math":false,"creators":["Alsop, Johnathan R."],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Adve, Sarita V."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016-07-07T19:54:22Z","date_published":"2016-07-07T19:54:22Z","updated_at":"2026-07-22T22:26:34Z","subjects":["GPUs","performance analysis","memory systems","heterogeneous computing"],"languages":["en"],"rights":["Copyright 2016 Johnathan Alsop"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/90587","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Adve, Sarita V."]},{"key":"dc:creator","label":"Author","values":["Alsop, Johnathan R."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2016-07-07T19:54:22Z","2016-04-20","2016-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"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":["GPUs","performance analysis","memory systems","heterogeneous computing"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2016 Johnathan Alsop"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/90587"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["In recent years the power wall has prevented the continued scaling of single core performance. This has led to the rise of dark silicon and motivated a move toward parallelism and specialization. As a result, energy-efficient high-throughput GPU cores are increasingly favored for accelerating data-parallel applications. However, the best way to efficiently communicate and synchronize across heterogeneous cores remains an important open research question. Many methods have been proposed to improve the efficiency of heterogeneous memory systems, but current methods for evaluating the performance effects of these innovations are limited in their ability to attribute differences in execution time to sources of latency in the memory system. Performance characterization of tightly coupled CPU-GPU systems is complicated by the high levels of parallelism present in GPU codes. Existing simulation tools provide only coarse-grained metrics which can obscure the underlying memory system interactions that cause performance differences. In this thesis we introduce GPU Stall Inspector (GSI), a method for identifying and visualizing the causes of GPU stalls with a focus on a tightly coupled CPU-GPU memory subsystem. We demonstrate the utility of our approach by evaluating the sources of stalls in several recent architectural innovations for tightly coupled, heterogeneous CPU-GPU systems.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2016-07-07 without embargo terms","The student, Johnathan Alsop, accepted the attached license on 2016-04-20 at 09:00.","The student, Johnathan Alsop, submitted this Thesis for approval on 2016-04-20 at 09:09.","This Thesis was approved for publication on 2016-04-20 at 14:51.","DSpace SAF Submission Ingestion Package generated from Vireo submission #9366 on 2016-07-07 at 13:31:41","Made available in DSpace on 2016-07-07T19:54:22Z (GMT). No. of bitstreams: 2 ALSOP-THESIS-2016.pdf: 356947 bytes, checksum: 1275267a6b4d595c5d7299ea2bb020c9 (MD5) LICENSE.txt: 4212 bytes, checksum: 61dc0d605a942a3173463731d59b0d6e (MD5) Previous issue date: 2016-04-20"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["GSI: a GPU stall inspector to characterize the sources of memory stalls for tightly coupled GPUs"]}]}],"canonical_facts":{"dc:contributor":["Adve, Sarita V."],"dc:creator":["Alsop, Johnathan R."],"dc:date":["2016-07-07T19:54:22Z","2016-04-20","2016-05"],"dc:description":["In recent years the power wall has prevented the continued scaling of single core performance. This has led to the rise of dark silicon and motivated a move toward parallelism and specialization. As a result, energy-efficient high-throughput GPU cores are increasingly favored for accelerating data-parallel applications. However, the best way to efficiently communicate and synchronize across heterogeneous cores remains an important open research question. Many methods have been proposed to improve the efficiency of heterogeneous memory systems, but current methods for evaluating the performance effects of these innovations are limited in their ability to attribute differences in execution time to sources of latency in the memory system. Performance characterization of tightly coupled CPU-GPU systems is complicated by the high levels of parallelism present in GPU codes. Existing simulation tools provide only coarse-grained metrics which can obscure the underlying memory system interactions that cause performance differences. In this thesis we introduce GPU Stall Inspector (GSI), a method for identifying and visualizing the causes of GPU stalls with a focus on a tightly coupled CPU-GPU memory subsystem. We demonstrate the utility of our approach by evaluating the sources of stalls in several recent architectural innovations for tightly coupled, heterogeneous CPU-GPU systems.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2016-07-07 without embargo terms","The student, Johnathan Alsop, accepted the attached license on 2016-04-20 at 09:00.","The student, Johnathan Alsop, submitted this Thesis for approval on 2016-04-20 at 09:09.","This Thesis was approved for publication on 2016-04-20 at 14:51.","DSpace SAF Submission Ingestion Package generated from Vireo submission #9366 on 2016-07-07 at 13:31:41","Made available in DSpace on 2016-07-07T19:54:22Z (GMT). No. of bitstreams: 2 ALSOP-THESIS-2016.pdf: 356947 bytes, checksum: 1275267a6b4d595c5d7299ea2bb020c9 (MD5) LICENSE.txt: 4212 bytes, checksum: 61dc0d605a942a3173463731d59b0d6e (MD5) Previous issue date: 2016-04-20"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/90587"],"dc:language":["en"],"dc:rights":["Copyright 2016 Johnathan Alsop"],"dc:subject":["GPUs","performance analysis","memory systems","heterogeneous computing"],"dc:title":["GSI: a GPU stall inspector to characterize the sources of memory stalls for tightly coupled GPUs"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:34Z"}