{"id":{"repo_id":"utahstate","oai_identifier":"oai:digitalcommons.usu.edu:etd-8676"},"canonical_url":"https://search.ndltd.org/etd/utahstate/oai:digitalcommons.usu.edu:etd-8676","repository":{"repo_id":"utahstate","name":"Utah State University","base_url":"https://digitalcommons.usu.edu/do/oai/"},"display":{"title":"Predicting Critical Warps in Near-Threshold GPGPU Applications Using a Dynamic Choke Point Analysis","abstract":"General purpose graphics processing units (GP-GPU), owing to their enormous thread-level parallelism, can significantly improve the power consumption at the near-threshold (NTC) operating region, while offering close to a super-threshold performance. However, process variation (PV) can drastically reduce the GPU performance at NTC. In this work, choke points—a unique device-level characteristic of PV at NTC—that can exacerbate the warp criticality problem in GPUs have been explored. It is shown that the modern warp schedulers cannot tackle the choke point induced critical warps in an NTC GPU. Additionally, Choke Point Aware Warp Speculator, a circuit-architectural solution is proposed to dynamically predict the critical warps in GPUs, and accelerate them in their respective execution units. The best scheme achieves an average improvement of ∼39% in performance, and ∼31% in energy-efficiency, over one state-of-the-art warp scheduler, across 15 GPGPU applications, while incurring marginal hardware overheads.","abstract_html":"General purpose graphics processing units (GP-GPU), owing to their enormous thread-level parallelism, can significantly improve the power consumption at the near-threshold (NTC) operating region, while offering close to a super-threshold performance. However, process variation (PV) can drastically reduce the GPU performance at NTC. In this work, choke points—a unique device-level characteristic of PV at NTC—that can exacerbate the warp criticality problem in GPUs have been explored. It is shown that the modern warp schedulers cannot tackle the choke point induced critical warps in an NTC GPU. Additionally, Choke Point Aware Warp Speculator, a circuit-architectural solution is proposed to dynamically predict the critical warps in GPUs, and accelerate them in their respective execution units. The best scheme achieves an average improvement of ∼39% in performance, and ∼31% in energy-efficiency, over one state-of-the-art warp scheduler, across 15 GPGPU applications, while incurring marginal hardware overheads.","abstract_has_math":false,"creators":["Sanyal, Sourav"],"institution":"Hosted by Utah State University Libraries","degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":["Sanghamitra Roy","Koushik Chakraborty","Reyhan Baktur"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:51:15Z","subjects":["Process Variation","Near-Threshold Computing","General Purpose Graphics Processing Unit","Warp Criticality Problem","Single Instruction Multiple Data","Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["http://doi.org/10.26076/b4kn-0m81"],"render_values":[{"text":"http://doi.org/10.26076/b4kn-0m81","href":"http://doi.org/10.26076/b4kn-0m81","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usu.edu/etd/7545","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usu.edu/etd/7545","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usu.edu%3Aetd-8676","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sanghamitra Roy","Koushik Chakraborty","Reyhan Baktur"]},{"key":"dc:creator","label":"Author","values":["Sanyal, Sourav"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2010-01-01T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2019-08-01T07:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["Hosted by Utah State University Libraries"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Process Variation","Near-Threshold Computing","General Purpose Graphics Processing Unit","Warp Criticality Problem","Single Instruction Multiple Data","Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usu.edu/etd/7545"]},{"key":"dc:identifier.doi","label":"DOI","values":["http://doi.org/10.26076/b4kn-0m81"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["General purpose graphics processing units (GP-GPU), owing to their enormous thread-level parallelism, can significantly improve the power consumption at the near-threshold (NTC) operating region, while offering close to a super-threshold performance. However, process variation (PV) can drastically reduce the GPU performance at NTC. In this work, choke points—a unique device-level characteristic of PV at NTC—that can exacerbate the warp criticality problem in GPUs have been explored. It is shown that the modern warp schedulers cannot tackle the choke point induced critical warps in an NTC GPU. Additionally, Choke Point Aware Warp Speculator, a circuit-architectural solution is proposed to dynamically predict the critical warps in GPUs, and accelerate them in their respective execution units. The best scheme achieves an average improvement of ∼39% in performance, and ∼31% in energy-efficiency, over one state-of-the-art warp scheduler, across 15 GPGPU applications, while incurring marginal hardware overheads."]},{"key":"dc:title","label":"Title","values":["Predicting Critical Warps in Near-Threshold GPGPU Applications Using a Dynamic Choke Point Analysis"]}]}],"canonical_facts":{"dc:contributor":["Sanghamitra Roy","Koushik Chakraborty","Reyhan Baktur"],"dc:creator":["Sanyal, Sourav"],"dc:date.available":["2010-01-01T08:00:00Z"],"dc:date.created":["2019-08-01T07:00:00Z"],"dc:description.abstract":["General purpose graphics processing units (GP-GPU), owing to their enormous thread-level parallelism, can significantly improve the power consumption at the near-threshold (NTC) operating region, while offering close to a super-threshold performance. However, process variation (PV) can drastically reduce the GPU performance at NTC. In this work, choke points—a unique device-level characteristic of PV at NTC—that can exacerbate the warp criticality problem in GPUs have been explored. It is shown that the modern warp schedulers cannot tackle the choke point induced critical warps in an NTC GPU. Additionally, Choke Point Aware Warp Speculator, a circuit-architectural solution is proposed to dynamically predict the critical warps in GPUs, and accelerate them in their respective execution units. The best scheme achieves an average improvement of ∼39% in performance, and ∼31% in energy-efficiency, over one state-of-the-art warp scheduler, across 15 GPGPU applications, while incurring marginal hardware overheads."],"dc:identifier":["https://digitalcommons.usu.edu/etd/7545"],"dc:identifier.doi":["http://doi.org/10.26076/b4kn-0m81"],"dc:publisher":["Hosted by Utah State University Libraries"],"dc:subject":["Process Variation","Near-Threshold Computing","General Purpose Graphics Processing Unit","Warp Criticality Problem","Single Instruction Multiple Data","Computer Engineering"],"dc:title":["Predicting Critical Warps in Near-Threshold GPGPU Applications Using a Dynamic Choke Point Analysis"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T08:51:15Z"}