{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:34:55Z","timestamp":1780497295874,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":84,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,3,25]],"date-time":"2023-03-25T00:00:00Z","timestamp":1679702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,3,25]]},"DOI":"10.1145\/3623278.3624756","type":"proceedings-article","created":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T19:28:26Z","timestamp":1707334106000},"page":"253-267","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Predict; Don't React for Enabling Efficient Fine-Grain DVFS in GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-5210","authenticated-orcid":false,"given":"Srikant","family":"Bharadwaj","sequence":"first","affiliation":[{"name":"Microsoft, Bellevue, WA, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8001-5517","authenticated-orcid":false,"given":"Shomit","family":"Das","sequence":"additional","affiliation":[{"name":"Qualcomm, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4800-855X","authenticated-orcid":false,"given":"Kaushik","family":"Mazumdar","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Inc, Fort Collins, CO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5444-6521","authenticated-orcid":false,"given":"Bradford M.","family":"Beckmann","sequence":"additional","affiliation":[{"name":"Advanced Micro Devices, Inc, Bellevue, WA, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1656-8070","authenticated-orcid":false,"given":"Stephen","family":"Kosonocky","sequence":"additional","affiliation":[{"name":"Uhnder, Fort Collins, CO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,2,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/1481659"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1952998.1952999"},{"key":"e_1_3_2_1_3_1","volume-title":"System level analysis of fast, per-core DVFS using on-chip switching regulators","author":"Kim W.","year":"2008","unstructured":"W. Kim, M. S. Gupta, G.-Y. Wei and D. M. Brooks, \"System level analysis of fast, per-core DVFS using on-chip switching regulators,\" 2008. [Online]. Available: http:\/\/eecs.harvard.edu\/~dbrooks\/kim2008_hpca.pdf. [Accessed 25 6 2019]."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093336.3037717"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2016.2555954"},{"key":"e_1_3_2_1_6_1","volume-title":"FIVR --- Fully integrated voltage regulators on 4th generation Intel\u00ae CoreTM SoCs","author":"Burton E. A.","year":"2014","unstructured":"E. A. Burton, G. Schrom, F. Paillet, J. P. Douglas, W. J. Lambert, K. Radhakrishnan and M. J. Hill, \"FIVR --- Fully integrated voltage regulators on 4th generation Intel\u00ae CoreTM SoCs,\" 2014. [Online]. Available: https:\/\/ieeexplore.ieee.org\/document\/6803344. [Accessed 21 11 2019]."},{"key":"e_1_3_2_1_7_1","volume-title":"A Fine-Grained GALS SoC with Pausible Adaptive Clocking in 16 nm FinFET,\" in 2019 25th IEEE International Symposium on Asynchronous Circuits and Systems (ASYNC)","author":"Fojtik M.","year":"2019","unstructured":"M. Fojtik, B. Keller, A. Klinefelter, N. Pinckney, S. G. Tell, B. Zimmer, T. Raja, K. Zhou, W. J. Dally and B. Khailany, \"A Fine-Grained GALS SoC with Pausible Adaptive Clocking in 16 nm FinFET,\" in 2019 25th IEEE International Symposium on Asynchronous Circuits and Systems (ASYNC), 2019."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"X. Sun A. Boora W. Zhang V. R. Pamula and V. Sathe \"14.5 A 0.6-to-1.1V Computationally Regulated Digital LDO with 2.79-Cycle Mean Settling Time and Autonomous Runtime Gain Tracking in 65nm CMOS \" IEEE International Solid- State Circuits Conference - (ISSCC) 2019.","DOI":"10.1109\/ISSCC.2019.8662298"},{"key":"e_1_3_2_1_9_1","volume-title":"0.5-V input digital LDO with 98.7% current efficiency and 2.7-\u03bcA quiescent current in 65nm CMOS","author":"Okuma Y.","year":"2010","unstructured":"Y. Okuma, K. Ishida, Y. Ryu, X. Zhang, P.-H. Chen, K. Watanabe, M. Takamiya and T. Sakurai, \"0.5-V input digital LDO with 98.7% current efficiency and 2.7-\u03bcA quiescent current in 65nm CMOS,\" 2010. [Online]. Available: http:\/\/lowpower.iis.u-tokyo.ac.jp\/paper\/2010_22.pdf. [Accessed 25 11 2019]."},{"key":"e_1_3_2_1_10_1","first-page":"155","article-title":"Predicting Performance Impact of DVFS for Realistic Memory Systems","author":"Miftakhutdinov R.","year":"2012","unstructured":"R. Miftakhutdinov, E. Ebrahimi and Y. N. Patt, \"Predicting Performance Impact of DVFS for Realistic Memory Systems,\" IEEE Micro, pp. 155--165, 2012.","journal-title":"IEEE Micro"},{"key":"e_1_3_2_1_11_1","volume-title":"XBOX Series X: A Next-Generation Gaming Console SoC,\" in 2021 IEEE International Solid- State Circuits Conference (ISSCC)","author":"Paternoster P.","year":"2021","unstructured":"P. Paternoster, A. Maki, A. Hernandez, M. Grossman, M. Lau, D. Sutherland and A. Mathad, \"XBOX Series X: A Next-Generation Gaming Console SoC,\" in 2021 IEEE International Solid- State Circuits Conference (ISSCC), 2021."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310172"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2017.2752839"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2873584"},{"key":"e_1_3_2_1_15_1","unstructured":"D. Bouvier J. Gibney A. Branover and S. Arora \"AMD Raven-Ridge APU: Delivering a new level of visual performance in an SoC \" [Online]. Available: https:\/\/www.hotchips.org\/hc30\/1conf\/1.05_AMD_APU_AMD_Raven_HotChips30_Final.pdf."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIC.2015.7231305"},{"key":"e_1_3_2_1_17_1","volume-title":"Leuven","author":"Muthukaruppan R.","year":"2017","unstructured":"R. Muthukaruppan, T. Mahajan, H. Krishnamurthy, S. Mangal, A. Dhanshekhar, R. Ghayal and V. De, \"A digitally controlled linear regulator for per-core wide-range DVFS of atomTM cores in 14nm tri-gate CMOS featuring non-linear control, adaptive gain and code roaming,\" in ESSCIRC 2017 - 43rd IEEE European Solid State Circuits Conference, Leuven, 2017."},{"key":"e_1_3_2_1_18_1","volume-title":"A 67.1-ps FOM, 0.5-V-Hybrid Digital LDO With Asynchronous Feedforward Control Via Slope Detection and Synchronous PI With State-Based Hysteresis Clock Switching","author":"Kim S. J.","year":"2018","unstructured":"S. J. Kim, D. Kim, H. Ham, J. Kim and M. Seok, \"A 67.1-ps FOM, 0.5-V-Hybrid Digital LDO With Asynchronous Feedforward Control Via Slope Detection and Synchronous PI With State-Based Hysteresis Clock Switching,\" 2018. [Online]. Available: https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&arnumber=8490730. [Accessed 12 2 2020]."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2016.2584056"},{"key":"e_1_3_2_1_20_1","volume-title":"The CRISP performance model for dynamic voltage and frequency scaling in a GPGPU,\" in 2015 48th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Nath R.","year":"2015","unstructured":"R. Nath and D. M. Tullsen, \"The CRISP performance model for dynamic voltage and frequency scaling in a GPGPU,\" in 2015 48th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), 2015."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2525526.2525852"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.2992684"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2015.2457920"},{"key":"e_1_3_2_1_24_1","volume-title":"Interval-based models for runtime DVFS orchestration in superscalar processors","author":"Keramidas G.","year":"2010","unstructured":"G. Keramidas, V. Spiliopoulos and S. Kaxiras, \"Interval-based models for runtime DVFS orchestration in superscalar processors,\" 2010. [Online]. Available: http:\/\/pages.cs.wisc.edu\/~kaxiras\/papers\/cf10_dvfs_model.pdf. [Accessed 25 6 2019]."},{"key":"e_1_3_2_1_25_1","volume-title":"Runtime Phase Monitoring and Prediction on Real Systems with Application to Dynamic Power Management","author":"Isci C.","year":"2006","unstructured":"C. Isci, G. Contreras and M. Martonos, Live, Runtime Phase Monitoring and Prediction on Real Systems with Application to Dynamic Power Management, 2006, p. 359--370."},{"key":"e_1_3_2_1_26_1","volume-title":"Improving Provisioned Power Efficiency in HPC Systems with GPU-CAPP,\" 2018 IEEE 25th International Conference on High Performance Computing (HiPC)","author":"Straube K.","year":"2018","unstructured":"K. Straube, J. Lowe-Power, C. Nitta, M. Farrens and V. Akella, \"Improving Provisioned Power Efficiency in HPC Systems with GPU-CAPP,\" 2018 IEEE 25th International Conference on High Performance Computing (HiPC), 2018."},{"key":"e_1_3_2_1_27_1","volume-title":"v. d. Braak and H. Corporaal, \"Roofline-aware DVFS for GPUs","author":"Nugteren C. C.","year":"2014","unstructured":"C. C. Nugteren, G. G.-J. v. d. Braak and H. Corporaal, \"Roofline-aware DVFS for GPUs,\" 2014. [Online]. Available: http:\/\/ece.neu.edu\/groups\/nucar\/nucartalks\/roofline-aware_dvfs_for_gpus.pdf. [Accessed 15 8 2019]."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.4236\/ojee.2015.44009"},{"key":"e_1_3_2_1_29_1","volume-title":"Phoenix","author":"Tang Z.","year":"2019","unstructured":"Z. Tang, Y. Wang, Q. Wang and X. Chu, \"The Impact of GPU DVFS on the Energy and Performance of Deep Learning: An Empirical Study,\" in Proceedings of the Tenth ACM International Conference on Future Energy Systems, Phoenix, 2019."},{"key":"e_1_3_2_1_30_1","volume-title":"AgilePkgC: An Agile System Idle State Architecture for Energy Proportional Datacenter Servers,\" arXiv","author":"Antoniou G.","year":"2022","unstructured":"G. Antoniou, H. Volos, D. B. Bartolini, T. Rollet, Y. Sazeides and J. H. Yahya, \"AgilePkgC: An Agile System Idle State Architecture for Energy Proportional Datacenter Servers,\" arXiv, 2022."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"B. Dutta V. Adhinarayanan and W.-c. Feng \"GPU power prediction via ensemble machine learning for DVFS space exploration \" 2018. [Online]. Available: https:\/\/vtechworks.lib.vt.edu\/handle\/10919\/81997. [Accessed 15 8 2019].","DOI":"10.1145\/3203217.3203273"},{"key":"e_1_3_2_1_32_1","volume-title":"Kyoto","author":"Fan K.","year":"2019","unstructured":"K. Fan, B. Cosenza and B. Juurlink, \"Predictable GPUs Frequency Scaling for Energy and Performance,\" in Proceedings of the 48th International Conference on Parallel Processing, Kyoto, Japan, 2019."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2010.65"},{"key":"e_1_3_2_1_34_1","volume-title":"d. Supinski, \"Practical performance prediction under Dynamic Voltage Frequency Scaling","author":"Rountree B.","year":"2011","unstructured":"B. Rountree, D. K. Lowenthal, M. Schulz and B. R. d. Supinski, \"Practical performance prediction under Dynamic Voltage Frequency Scaling,\" 2011. [Online]. Available: http:\/\/yadda.icm.edu.pl\/yadda\/element\/bwmeta1.element.ieee-000006008553. [Accessed 25 6 2019]."},{"key":"e_1_3_2_1_35_1","first-page":"347","article-title":"An Analysis of Efficient Multi-Core Global Power Management Policies: Maximizing Performance for a Given Power Budget","author":"Isci C.","year":"2006","unstructured":"C. Isci, A. Buyuktosunoglu, C.-Y. Chen, P. Bose and M. Martonosi, \"An Analysis of Efficient Multi-Core Global Power Management Policies: Maximizing Performance for a Given Power Budget,\" IEEE Micro, pp. 347--358, 2006.","journal-title":"IEEE Micro"},{"key":"e_1_3_2_1_36_1","volume-title":"PCP: A Generalized Approach to Optimizing Performance Under Power Constraints through Resource Management","author":"Hoffmann H.","year":"2014","unstructured":"H. Hoffmann and M. Maggio, \"PCP: A Generalized Approach to Optimizing Performance Under Power Constraints through Resource Management,\" 2014. [Online]. Available: https:\/\/usenix.org\/system\/files\/conference\/icac14\/icac14-paper-hoffman.pdf. [Accessed 23 7 2019]."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2012.2235126"},{"key":"e_1_3_2_1_38_1","volume-title":"Green governors: A framework for Continuously Adaptive DVFS","author":"Spiliopoulos V.","year":"2011","unstructured":"V. Spiliopoulos, S. Kaxiras and G. Keramidas, \"Green governors: A framework for Continuously Adaptive DVFS,\" 2011. [Online]. Available: http:\/\/diva-portal.org\/smash\/record.jsf?pid=diva2:474791. [Accessed 25 6 2019]."},{"key":"e_1_3_2_1_39_1","volume-title":"Scheduling for reduced CPU energy","author":"Weiser M.","year":"1994","unstructured":"M. Weiser, B. B. Welch, A. J. Demers and S. Shenker, \"Scheduling for reduced CPU energy,\" 1994. [Online]. Available: https:\/\/link.springer.com\/chapter\/10.1007\/978-0-585-29603-6_17. [Accessed 25 6 2019]."},{"key":"e_1_3_2_1_40_1","volume-title":"Cloud and Internet Computing (CCGRID)","author":"Zou P.","year":"2020","unstructured":"P. Zou, A. Li, K. Barker and R. Ge, \"Indicator-Directed Dynamic Power Management for Iterative Workloads on GPU-Accelerated Systems,\" in 2020 20th IEEE\/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID), 2020."},{"key":"e_1_3_2_1_41_1","volume-title":"Ivory: Early-Stage Design Space Exploration Tool for Integrated Voltage Regulators","author":"Zou A.","year":"2017","unstructured":"A. Zou, J. Leng, Y. Zu, T. Tong, V. J. Reddi, D. M. Brooks, G.-Y. Wei and X. Zhang, \"Ivory: Early-Stage Design Space Exploration Tool for Integrated Voltage Regulators,\" 2017. [Online]. Available: https:\/\/dl.acm.org\/citation.cfm?id=3062268. [Accessed 23 7 2019]."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2016.2555954"},{"key":"e_1_3_2_1_43_1","volume-title":"FlexWatts: A Power- and Workload-Aware Hybrid Power Delivery Network for Energy-Efficient Microprocessors,\" arXiv","author":"Haj-Yahya J.","year":"2020","unstructured":"J. Haj-Yahya, M. Alser, J. S. Kim, L. Orosa, E. Rotem, A. Mendelson, A. Chattopadhyay and O. Mutlu, \"FlexWatts: A Power- and Workload-Aware Hybrid Power Delivery Network for Energy-Efficient Microprocessors,\" arXiv, 2020."},{"key":"e_1_3_2_1_44_1","volume-title":"Orlando","author":"Sankarasubramanian M.","year":"2020","unstructured":"M. Sankarasubramanian, K. Radhakrishnan, Y. Min, W. Lambert, M. J. Hill, A. Dani, R. Mesch, L. Wojewoda, J. Chavarria and A. Augustine, \"Magnetic Inductor Arrays for Intel\u00ae Fully Integrated Voltage Regulator (FIVR) on 10th generation Intel\u00ae CoreTM SoCs,\" in 2020 IEEE 70th Electronic Components and Technology Conference (ECTC), Orlando, 2020."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2946218"},{"key":"e_1_3_2_1_46_1","volume-title":"AgileRegulator: A hybrid voltage regulator scheme redeeming dark silicon for power efficiency in a multicore architecture","author":"Yan G.","year":"2012","unstructured":"G. Yan, Y. Li, Y. Han, X. Li, M. Guo and X. Liang, \"AgileRegulator: A hybrid voltage regulator scheme redeeming dark silicon for power efficiency in a multicore architecture,\" 2012. [Online]. Available: http:\/\/cs.sjtu.edu.cn\/~guo-my\/pdf\/conferences\/c130.pdf. [Accessed 5 7 2019]."},{"key":"e_1_3_2_1_47_1","first-page":"143","article-title":"CoScale: Coordinating CPU and Memory System DVFS in Server Systems","author":"Deng Q.","year":"2012","unstructured":"Q. Deng, D. Meisner, A. Bhattacharjee, T. F. Wenisch and R. Bianchini, \"CoScale: Coordinating CPU and Memory System DVFS in Server Systems,\" IEEE Micro, pp. 143--154, 2012.","journal-title":"IEEE Micro"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2016.7482070"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2954679.2872375"},{"key":"e_1_3_2_1_50_1","volume-title":"PCP: A Generalized Approach to Optimizing Performance Under Power Constraints through Resource Management","author":"Hoffmann H.","year":"2014","unstructured":"H. Hoffmann and M. Maggio, \"PCP: A Generalized Approach to Optimizing Performance Under Power Constraints through Resource Management,\" 2014. [Online]. Available: https:\/\/lup.lub.lu.se\/search\/publication\/44544051-23aa-4be2-904f-b780181c3f90. [Accessed 5 7 2019]."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2014.47"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/1183401.1183426"},{"key":"e_1_3_2_1_53_1","first-page":"445","article-title":"PPEP: Online Performance, Power, and Energy Prediction Framework and DVFS Space Exploration","author":"Su B.","year":"2014","unstructured":"B. Su, J. Gu, L. Shen, W. Huang, J. L. Greathouse and Z. Wang, \"PPEP: Online Performance, Power, and Energy Prediction Framework and DVFS Space Exploration,\" IEEE Micro, pp. 445--457, 2014.","journal-title":"IEEE Micro"},{"key":"e_1_3_2_1_54_1","volume-title":"I-DVFS: Instantaneous Frequency Switch During Dynamic Voltage and Frequency Scaling,\" in IEEE Micro","author":"Gendler A.","year":"2021","unstructured":"A. Gendler, E. Knoll and Y. Sazeides, \"I-DVFS: Instantaneous Frequency Switch During Dynamic Voltage and Frequency Scaling,\" in IEEE Micro, 2021."},{"key":"e_1_3_2_1_55_1","volume-title":"Virtual Event","author":"Haj-Yahya J.","year":"2020","unstructured":"J. Haj-Yahya, M. Alser, J. Kim, A. G. Yaglik\u00e7i, N. Vijaykumar, E. Rotem and O. Mutlu, \"SysScale: Exploiting Multi-domain Dynamic Voltage and Frequency Scaling for Energy Efficient Mobile Processors,\" in Proceedings of the ACM\/IEEE 47th Annual International Symposium on Computer Architecture, Virtual Event, 2020."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/514191.514200"},{"key":"e_1_3_2_1_57_1","first-page":"271","article-title":"A Dynamic Compilation Framework for Controlling Microprocessor Energy and Performance","author":"Wu Q.","year":"2005","unstructured":"Q. Wu, M. Martonosi, D. W. Clark, V. J. Reddi, D. A. Connors, Y. Wu, J. Lee and D. M. Brooks, \"A Dynamic Compilation Framework for Controlling Microprocessor Energy and Performance,\" IEEE Micro, pp. 271--282, 2005.","journal-title":"IEEE Micro"},{"key":"e_1_3_2_1_58_1","volume-title":"The Danger of Interval-Based Power Efficiency Metrics: When Worst Is Best,\" in IEEE Computer Architecture Letters","author":"Sazeides Y.","year":"2005","unstructured":"Y. Sazeides, R. Kumar, D. Tullsen and T. Constantinou, \"The Danger of Interval-Based Power Efficiency Metrics: When Worst Is Best,\" in IEEE Computer Architecture Letters, 2005."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2016.2609903"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2005.93"},{"key":"e_1_3_2_1_61_1","volume-title":"Predictive power management for multi-core processors","author":"Bircher W. L.","year":"2010","unstructured":"W. L. Bircher and L. K. John, \"Predictive power management for multi-core processors,\", 2010. [Online]. Available: https:\/\/link.springer.com\/chapter\/10.1007\/978-3-642-24322-6_21. [Accessed 21 11 2019]."},{"key":"e_1_3_2_1_62_1","volume-title":"AMD InstinctTM MI200 Series Accelerator and Node Architectures,\" in 2022 IEEE Hot Chips 34 Symposium (HCS)","author":"Smith A.","year":"2022","unstructured":"A. Smith and N. James, \"AMD InstinctTM MI200 Series Accelerator and Node Architectures,\" in 2022 IEEE Hot Chips 34 Symposium (HCS), 2022."},{"key":"e_1_3_2_1_63_1","volume-title":"EmerGPU: Understanding and mitigating resonance-induced voltage noise in GPU architectures","author":"Thomas R.","year":"2016","unstructured":"R. Thomas, N. Sedaghati and R. Teodorescu, \"EmerGPU: Understanding and mitigating resonance-induced voltage noise in GPU architectures,\" 2016. [Online]. Available: https:\/\/ieeexplore.ieee.org\/document\/7482076. [Accessed 24 11 2021]."},{"key":"e_1_3_2_1_64_1","volume-title":"Phase characterization for power: evaluating control-flow-based and event-counter-based techniques","author":"Isci C.","year":"2006","unstructured":"C. Isci and M. Martonosi, \"Phase characterization for power: evaluating control-flow-based and event-counter-based techniques,\" 2006. [Online]. Available: http:\/\/parapet.ee.princeton.edu\/papers\/canturk-hpca2006.pdf. [Accessed 15 8 2019]."},{"key":"e_1_3_2_1_65_1","volume-title":"Microvisor: a runtime architecture for thermal management in chip multiprocessors","author":"Khan O.","year":"2011","unstructured":"O. Khan and S. Kundu, \"Microvisor: a runtime architecture for thermal management in chip multiprocessors,\" 2011. [Online]. Available: https:\/\/link.springer.com\/chapter\/10.1007\/978-3-642-24568-8_5. [Accessed 20 11 2019]."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/isvlsi.2013.6654634"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/780822.781138"},{"key":"e_1_3_2_1_68_1","volume-title":"Lost in Abstraction: Pitfalls of Analyzing GPUs at the Intermediate Language Level","author":"Gutierrez A.","year":"2018","unstructured":"A. Gutierrez, B. M. Beckmann, A. Dutu, J. Gross, M. LeBeane, J. Kalamatianos, O. Kayiran, M. Poremba, B. Potter, S. Puthoor, M. D. Sinclair, M. Wyse, J. Yin, X. Zhang, A. Jain and T. G. Rogers, \"Lost in Abstraction: Pitfalls of Analyzing GPUs at the Intermediate Language Level,\" 2018. [Online]. Available: https:\/\/ieeexplore.ieee.org\/document\/8327041. [Accessed 30 7 2019]."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_3_2_1_70_1","volume-title":"Kite: A Family of Heterogeneous Interposer Topologies Enabled via Accurate Interconnect Modeling,\" in 57th ACM\/IEEE Design Automation Conference (DAC)","author":"Bharadwaj S.","year":"2020","unstructured":"S. Bharadwaj, J. Yin, B. Beckmann and T. Krishna, \"Kite: A Family of Heterogeneous Interposer Topologies Enabled via Accurate Interconnect Modeling,\" in 57th ACM\/IEEE Design Automation Conference (DAC), San Francisco, CA, US, 2020."},{"key":"e_1_3_2_1_71_1","volume-title":"Machine learning for performance and power modeling of heterogeneous systems,\" In Proceedings of the International Conference on Computer-Aided Design (ICCAD '18). ACM","author":"Greathouse J. L.","year":"2018","unstructured":"J. L. Greathouse and G. H. Loh, \"Machine learning for performance and power modeling of heterogeneous systems,\" In Proceedings of the International Conference on Computer-Aided Design (ICCAD '18). ACM, New York, NY, USA, Article 47, 6pages, 2018."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.2172\/1090032"},{"key":"e_1_3_2_1_73_1","unstructured":"BAIDU Research \"DeepBench \" [Online]. Available: https:\/\/github.com\/baidu-research\/DeepBench."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038228.3038239"},{"key":"e_1_3_2_1_75_1","volume-title":"Scalable Power Management in the Many-Core Era,\" in IEEE Computer Architecture Letters","author":"Shah P.","year":"2021","unstructured":"P. Shah, R. G. Shenoy, V. Srinivasan, P. Bose and A. Buyuktosunoglu, \"TokenSmart: Distributed, Scalable Power Management in the Many-Core Era,\" in IEEE Computer Architecture Letters, 2021."},{"key":"e_1_3_2_1_76_1","first-page":"359","article-title":"Live, Runtime Phase Monitoring and Prediction on Real Systems with Application to Dynamic Power Management","author":"Isci C.","year":"2006","unstructured":"C. Isci, G. Contreras and M. Martonosi, \"Live, Runtime Phase Monitoring and Prediction on Real Systems with Application to Dynamic Power Management,\" IEEE Micro, pp. 359--370, 2006.","journal-title":"IEEE Micro"},{"key":"e_1_3_2_1_77_1","volume-title":"Fine-grained dynamic voltage and frequency scaling for precise energy and performance trade-off based on the ratio of off-chip access to on-chip computation times","author":"Choi K.","year":"2004","unstructured":"K. Choi, R. Soma and M. Pedram, \"Fine-grained dynamic voltage and frequency scaling for precise energy and performance trade-off based on the ratio of off-chip access to on-chip computation times,\" 2004. [Online]. Available: http:\/\/sportlab.usc.edu\/~kihwan\/fg-dvfs.pdf. [Accessed 5 7 2019]."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2013.75"},{"key":"e_1_3_2_1_79_1","first-page":"271","article-title":"Clark and yes","author":"Wu Q.","year":"2005","unstructured":"Q. Wu, V. J. Reddi, Y. Wu, J. Lee, D. Connors, D. Brooks, M. Martonosi, D. W. Clark and yes, A Dynamic Compilation Framework for Controlling Microprocessor Energy and Performance, 2005, p. 271--282.","journal-title":"A Dynamic Compilation Framework for Controlling Microprocessor Energy and Performance"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757354"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2778080"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964791.2901468"},{"key":"e_1_3_2_1_83_1","unstructured":"AMD \"Polaris Whitepaper\"."},{"key":"e_1_3_2_1_84_1","volume-title":"MDM: The GPU Memory Divergence Model,\" in International Symposium on Microarchitecture(MICRO)","author":"Wang L.","year":"2020","unstructured":"L. Wang, M. Jahre, A. Adileho and L. Eeckhout, \"MDM: The GPU Memory Divergence Model,\" in International Symposium on Microarchitecture(MICRO), 2020."}],"event":{"name":"ASPLOS '23: 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4","location":"Vancouver BC Canada","acronym":"ASPLOS '23","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3623278.3624756","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3623278.3624756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:26Z","timestamp":1750178186000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3623278.3624756"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,25]]},"references-count":84,"alternative-id":["10.1145\/3623278.3624756","10.1145\/3623278"],"URL":"https:\/\/doi.org\/10.1145\/3623278.3624756","relation":{},"subject":[],"published":{"date-parts":[[2023,3,25]]},"assertion":[{"value":"2024-02-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}