{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T09:41:53Z","timestamp":1775122913663,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":93,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T00:00:00Z","timestamp":1676937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CCF","award":["2217086"],"award-info":[{"award-number":["2217086"]}]},{"name":"OAC","award":["2104116"],"award-info":[{"award-number":["2104116"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,25]]},"DOI":"10.1145\/3572848.3577497","type":"proceedings-article","created":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T16:02:30Z","timestamp":1676995350000},"page":"204-217","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Merchandiser"],"prefix":"10.1145","author":[{"given":"Zhen","family":"Xie","sequence":"first","affiliation":[{"name":"University of California, Merced and Argonne National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"University of California, Merced"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajia","family":"Li","sequence":"additional","affiliation":[{"name":"North Carolina State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Li","sequence":"additional","affiliation":[{"name":"University of California, Merced"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,2,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Coefficient of variation. Encyclopedia of research design 1","author":"Abdi Herv\u00e9","year":"2010","unstructured":"Herv\u00e9 Abdi. 2010. Coefficient of variation. Encyclopedia of research design 1 (2010), 169--171."},{"key":"e_1_3_2_1_2_1","volume-title":"Thermostat: Application-transparent Page Management for Two-tiered Main Memory. In International Conference on Architectural Support for Programming Languages and Operating Systems.","author":"Agarwal Neha","unstructured":"Neha Agarwal and Thomas F. Wenisch. 2017. Thermostat: Application-transparent Page Management for Two-tiered Main Memory. In International Conference on Architectural Support for Programming Languages and Operating Systems."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037706"},{"key":"e_1_3_2_1_4_1","article-title":"Exascale applications: skin in the game","volume":"378","author":"Alexander Francis","year":"2020","unstructured":"Francis Alexander, Ann Almgren, John Bell, Amitava Bhattacharjee, Jacqueline Chen, Phil Colella, David Daniel, Jack DeSlippe, Lori Diachin, Erik Draeger, et al. 2020. Exascale applications: skin in the game. Philosophical Transactions of the Royal Society A 378, 2166 (2020), 20190056.","journal-title":"Philosophical Transactions of the Royal Society A"},{"key":"e_1_3_2_1_5_1","volume-title":"Yuhsiang Mike Tsai, and Enrique S Quintana-Ort\u00ed","author":"Anzt Hartwig","year":"2020","unstructured":"Hartwig Anzt, Terry Cojean, Goran Flegar, Fritz G\u00f6bel, Thomas Gr\u00fctzmacher, Pratik Nayak, Tobias Ribizel, Yuhsiang Mike Tsai, and Enrique S Quintana-Ort\u00ed. 2020. Ginkgo: A modern linear operator algebra framework for high performance computing. arXiv preprint arXiv:2006.16852 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Electron Dynamics with the Time-Dependent Density Matrix Renormalization Group. Journal of Chemical Theory and Computation","author":"Baiardi Alberto","year":"2021","unstructured":"Alberto Baiardi. 2021. Electron Dynamics with the Time-Dependent Density Matrix Renormalization Group. Journal of Chemical Theory and Computation (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1177\/109434209100500306"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375580"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2724717"},{"key":"e_1_3_2_1_11_1","unstructured":"C.Consortium. [n.d.]. ComputeExpressLink. https:\/\/www.computeexpresslink.org"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3389133.3389137"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368826.3377922"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDRM51949.2020.00005"},{"key":"e_1_3_2_1_15_1","unstructured":"J. Corbe. [n.d.]. AutoNUMA: the Other Approach to NUMA Scheduling. http:\/\/lwn.net\/Articles\/488709."},{"key":"e_1_3_2_1_16_1","unstructured":"Intel Corporation. 2021. MemoryOptimizer - hot page accounting and migration daemon. https:\/\/github.com\/intel\/memory-optimizer."},{"key":"e_1_3_2_1_17_1","unstructured":"Najim Dehak Reda Dehak James R Glass Douglas A Reynolds Patrick Kenny et al. 2010. Cosine similarity scoring without score normalization techniques.. In Odyssey. 15."},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"TLB-pilot: Mitigating TLB Contention Attack on GPUs with Microarchitecture-Aware Scheduling","volume":"19","author":"Di Bang","year":"2021","unstructured":"Bang Di, Daokun Hu, Zhen Xie, Jianhua Sun, Hao Chen, Jinkui Ren, and Dong Li. 2021. TLB-pilot: Mitigating TLB Contention Attack on GPUs with Microarchitecture-Aware Scheduling. ACM Transactions on Architecture and Code Optimization (TACO) 19, 1 (2021), 1--23.","journal-title":"ACM Transactions on Architecture and Code Optimization (TACO)"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901344"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190524"},{"key":"e_1_3_2_1_21_1","volume-title":"The ITensor software library for tensor network calculations. arXiv preprint arXiv:2007.14822","author":"Fishman Matthew","year":"2020","unstructured":"Matthew Fishman, Steven R White, and E Miles Stoudenmire. 2020. The ITensor software library for tensor network calculations. arXiv preprint arXiv:2007.14822 (2020)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618562.2019.1617856"},{"key":"e_1_3_2_1_23_1","volume-title":"Single machine graph analytics on massive datasets using intel optane DC persistent memory. arXiv preprint arXiv:1904.07162","author":"Gill Gurbinder","year":"2019","unstructured":"Gurbinder Gill, Roshan Dathathri, Loc Hoang, Ramesh Peri, and Keshav Pingali. 2019. Single machine graph analytics on massive datasets using intel optane DC persistent memory. arXiv preprint arXiv:1904.07162 (2019)."},{"key":"e_1_3_2_1_24_1","volume-title":"ANATOMY: An Analytical Model of Memory System Performance. In International Conference on Measurement and Modeling of Computer Systems.","author":"Gulur Nagendra","year":"2014","unstructured":"Nagendra Gulur, Mahesh Mehendale, Raman Manikantan, and Ramaswamy Govindarajan. 2014. ANATOMY: An Analytical Model of Memory System Performance. In International Conference on Measurement and Modeling of Computer Systems."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00056"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186736.1186737"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987570"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"e_1_3_2_1_29_1","volume-title":"Predicting execution time of computer programs using sparse polynomial regression. Advances in neural information processing systems 23","author":"Huang Ling","year":"2010","unstructured":"Ling Huang, Jinzhu Jia, Bin Yu, Byung-Gon Chun, Petros Maniatis, and Mayur Naik. 2010. Predicting execution time of computer programs using sparse polynomial regression. Advances in neural information processing systems 23 (2010), 883--891."},{"key":"e_1_3_2_1_30_1","volume-title":"Performance Modeling for Optimal Data Placement on GPU with Heterogeneous Memory Systems. In IEEE International Conference on Cluster Computing.","author":"Huang Yingchao","year":"2017","unstructured":"Yingchao Huang and Dong Li. 2017. Performance Modeling for Optimal Data Placement on GPU with Heterogeneous Memory Systems. In IEEE International Conference on Cluster Computing."},{"key":"e_1_3_2_1_31_1","unstructured":"Amazon Inc. 2018. Amazon EC2 High Memory Instances with 6 9 and 12 TB of Memory Perfect for SAP HANA. https:\/\/aws.amazon.com\/blogs\/aws\/now-available-amazon-ec2-high-memory-instances-with-6-9-and-12-tb-of-memory-perfectfor-sap-hana\/."},{"key":"e_1_3_2_1_32_1","unstructured":"Intel. [n.d.]. Intel Optane\u2122 Persistent Memory 200 Series Brief. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/docs\/memory-storage\/optane-persistent-memory\/optane-persistent-memory-200-series-brief.html"},{"key":"e_1_3_2_1_33_1","unstructured":"Intel. 2019. Intel Memory Optimizer. https:\/\/github.com\/intel\/memory-optimizer."},{"key":"e_1_3_2_1_34_1","unstructured":"Intel. 2021. Intel Memory Tiering. https:\/\/lwn.net\/Articles\/802544\/."},{"key":"e_1_3_2_1_35_1","unstructured":"Intel. 2021. Processor Counter Monitor (PCM). https:\/\/github.com\/opcm\/pcm."},{"key":"e_1_3_2_1_36_1","volume-title":"Zixuan Wang, Yi Xu, Subramanya R Dulloor, et al.","author":"Izraelevitz Joseph","year":"2019","unstructured":"Joseph Izraelevitz, Jian Yang, Lu Zhang, Juno Kim, Xiao Liu, Amirsaman Memaripour, Yun Joon Soh, Zixuan Wang, Yi Xu, Subramanya R Dulloor, et al. 2019. Basic performance measurements of the intel optane DC persistent memory module. arXiv preprint arXiv:1903.05714 (2019)."},{"key":"e_1_3_2_1_37_1","volume-title":"Scalability analysis of gleipnir: A memory tracing and profiling tool, on titan","author":"Janjusic Tomislav","year":"2014","unstructured":"Tomislav Janjusic, Christos Kartsaklis, and Wang Dali. 2014. Scalability analysis of gleipnir: A memory tracing and profiling tool, on titan. Cray User Group (2014)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1111583.1111589"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080245"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-4655(00)00065-5"},{"key":"e_1_3_2_1_41_1","volume-title":"Exploring the Design Space of Page Management for Multi-Tiered Memory Systems. In 2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Kim Jonghyeon","year":"2021","unstructured":"Jonghyeon Kim, Wonkyo Choe, and Jeongseob Ahn. 2021. Exploring the Design Space of Page Management for Multi-Tiered Memory Systems. In 2021 USENIX Annual Technical Conference (USENIX ATC 21)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.12.005"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378483"},{"key":"e_1_3_2_1_44_1","unstructured":"Lawrence Berkeley National Laboratory. 2021. WarpX. https:\/\/github.com\/ECP-WarpX\/WarpX."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359635"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433732"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST.2016.7483435"},{"key":"e_1_3_2_1_48_1","volume-title":"Athena: High-Performance Sparse Tensor Contraction Sequence on Heterogeneous Memory. In International Conference on Supercomputing (ICS).","author":"Liu Jiawen","year":"2021","unstructured":"Jiawen Liu, Dong Li, and Jiajia Li. 2021. Athena: High-Performance Sparse Tensor Contraction Sequence on Heterogeneous Memory. In International Conference on Supercomputing (ICS)."},{"key":"e_1_3_2_1_49_1","volume-title":"FLAME: A Self-Adaptive Auto-labeling System for Heterogeneous Mobile Processors. arXiv preprint arXiv:2003.01762","author":"Liu Jie","year":"2020","unstructured":"Jie Liu, Jiawen Liu, Zhen Xie, and Dong Li. 2020. FLAME: A Self-Adaptive Auto-labeling System for Heterogeneous Mobile Processors. arXiv preprint arXiv:2003.01762 (2020)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441581"},{"key":"e_1_3_2_1_51_1","volume-title":"Sparta: High-Performance, Element-Wise Sparse Tensor Contraction on Heterogeneous Memory. In Principles and Practice of Parallel Programming.","author":"Liu Jiawen","year":"2021","unstructured":"Jiawen Liu, Jie Ren, Roberto Gioiosa, Dong Li, and Jiajia Li. 2021. Sparta: High-Performance, Element-Wise Sparse Tensor Contraction on Heterogeneous Memory. In Principles and Practice of Parallel Programming."},{"key":"e_1_3_2_1_52_1","volume-title":"Understanding variable importances in forests of randomized trees. Advances in neural information processing systems 26","author":"Louppe Gilles","year":"2013","unstructured":"Gilles Louppe, Louis Wehenkel, Antonio Sutera, and Pierre Geurts. 2013. Understanding variable importances in forests of randomized trees. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1216374.1216380"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056027"},{"key":"e_1_3_2_1_55_1","volume-title":"Coupling profile and historical methods to predict execution time of parallel applications. Parallel and Cloud Computing 2, 3","author":"Monteil Thierry","year":"2013","unstructured":"Thierry Monteil. 2013. Coupling profile and historical methods to predict execution time of parallel applications. Parallel and Cloud Computing 2, 3 (2013), pp-81."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2009.77"},{"key":"e_1_3_2_1_57_1","volume-title":"Erwin Laure, Dirk Pleiter, and Shaun De Witt.","author":"Narasimhamurthy Sai","year":"2019","unstructured":"Sai Narasimhamurthy, Nikita Danilov, Sining Wu, Ganesan Umanesan, Stefano Markidis, Sergio Rivas-Gomez, Ivy Bo Peng, Erwin Laure, Dirk Pleiter, and Shaun De Witt. 2019. Sage: percipient storage for exascale data centric computing. Parallel computing 83 (2019), 22--33."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12133-3_25"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2686745.2686748"},{"key":"e_1_3_2_1_60_1","volume-title":"Yeom","author":"Park SeongJae","year":"2019","unstructured":"SeongJae Park, Yunjae Lee, and Heon Y. Yeom. 2019. Profiling Dynamic Data Access Patterns with Controlled Overhead and Quality."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357526.3357541"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8257931"},{"key":"e_1_3_2_1_63_1","volume-title":"Demystifying the Performance of HPC Scientific Applications on NVM-based Memory Systems. In IEEE International Parallel and Distributed Processing Symposium.","author":"Peng Ivy","year":"2020","unstructured":"Ivy Peng, Kai Wu, Jie Ren, Maya Gokhale, and Dong Li. 2020. Demystifying the Performance of HPC Scientific Applications on NVM-based Memory Systems. In IEEE International Parallel and Distributed Processing Symposium."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357526.3357568"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2017.2732344"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58144-2_5"},{"key":"e_1_3_2_1_67_1","volume-title":"Optimizing Large-Scale Plasma Simulations on Persistent Memory-based Heterogeneous Memory with Effective Data Placement Across Memory Hierarchy. In International Conference on Supercomputing (ICS).","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Jiaolin Luo, Ivy Peng, Kai Wu, and Dong Li. 2021. Optimizing Large-Scale Plasma Simulations on Persistent Memory-based Heterogeneous Memory with Effective Data Placement Across Memory Hierarchy. In International Conference on Supercomputing (ICS)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460356"},{"key":"e_1_3_2_1_69_1","volume-title":"Sentinel: Efficient Tensor Migration and Allocation on Heterogeneous Memory Systems for Deep Learning. In International Symposium on High Performance Computer Architecture (HPCA).","author":"Ren Jie","year":"2020","unstructured":"Jie Ren, Jiaolin Luo, Kai Wu, Minjia Zhang, Hyeran Jeon, and Dong Li. 2020. Sentinel: Efficient Tensor Migration and Allocation on Heterogeneous Memory Systems for Deep Learning. In International Symposium on High Performance Computer Architecture (HPCA)."},{"key":"e_1_3_2_1_70_1","volume-title":"Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He.","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. Zero-offload: Democratizing billion-scale model training. arXiv preprint arXiv:2101.06840 (2021)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00034"},{"key":"e_1_3_2_1_72_1","volume-title":"HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory. In Conference on Neural Information Processing Systems (NeurIPS).","author":"Ren Jie","year":"2020","unstructured":"Jie Ren, Minjia Zhang, and Dong Li. 2020. HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536214"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5916"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2015.71"},{"key":"e_1_3_2_1_76_1","volume-title":"Quick Execution Time Predictions for Spark Applications. In 2019 15th International Conference on Network and Service Management (CNSM). IEEE, 1--9.","author":"Shah Sarah","year":"2019","unstructured":"Sarah Shah, Yasaman Amannejad, Diwakar Krishnamurthy, and Mea Wang. 2019. Quick Execution Time Predictions for Spark Applications. In 2019 15th International Conference on Network and Service Management (CNSM). IEEE, 1--9."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1137\/19M1299633"},{"key":"e_1_3_2_1_78_1","volume-title":"Proceedings of the Symposium on Principles and Practices of Parallel Programming.","author":"Sim Jaewoong","unstructured":"Jaewoong Sim, Aniruddha Dasgupta, Hyesoon Kim, and Richard W. Vuduc. 2012. A Performance Analysis Framework for Identifying Potential Benefits in GPGPU Applications. In Proceedings of the Symposium on Principles and Practices of Parallel Programming."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","unstructured":"J.-L. Vay A. Almgren J. Bell L. Ge D.P. Grote M. Hogan O. Kononenko R. Lehe A. Myers C. Ng and et al. 2018. Warp-X: A new exascale computing platform for beam-plasma simulations. Nuclear Instruments and Methods in Physics Research Section A: Accelerators Spectrometers Detectors and Associated Equipment 909 (Nov 2018) 476--479. 10.1016\/j.nima.2018.01.035","DOI":"10.1016\/j.nima.2018.01.035"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.42"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314650"},{"key":"e_1_3_2_1_83_1","unstructured":"Haojie Wang Jidong Zhai Xiongchao Tang Bowen Yu Xiaosong Ma and Wenguang Chen. 2018. Spindle: informed memory access monitoring. In 2018 {USENIX} Annual Technical Conference ({USENIX} {ATC} 18). 561--574."},{"key":"e_1_3_2_1_84_1","volume-title":"Unimem: Runtime Data Management on Non-Volatile Memory-based Heterogeneous Main Memory. In International Conference for High Performance Computing, Networking, Storage and Analysis.","author":"Wu K.","unstructured":"K. Wu, Y. Huang, and D. Li. 2017. Unimem: Runtime Data Management on Non-Volatile Memory-based Heterogeneous Main Memory. In International Conference for High Performance Computing, Networking, Storage and Analysis."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126923"},{"key":"e_1_3_2_1_86_1","volume-title":"Runtime Data Management on Non-Volatile Memory-Based Heterogeneous Memory for Task Parallel Programs","author":"Wu Kai","unstructured":"Kai Wu, Jie Ren, and Dong Li. 2018. Runtime Data Management on Non-Volatile Memory-Based Heterogeneous Memory for Task Parallel Programs. In ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00034"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456251"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460365"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508406"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330354"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3090328"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304024"},{"key":"e_1_3_2_1_94_1","volume-title":"18th {USENIX} Conference on File and Storage Technologies ({FAST} 20). 169--182.","author":"Yang Jian","unstructured":"Jian Yang, Juno Kim, Morteza Hoseinzadeh, Joseph Izraelevitz, and Steve Swanson. 2020. An empirical guide to the behavior and use of scalable persistent memory. In 18th {USENIX} Conference on File and Storage Technologies ({FAST} 20). 169--182."}],"event":{"name":"PPoPP '23: The 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Montreal QC Canada","acronym":"PPoPP '23","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572848.3577497","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3572848.3577497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:09Z","timestamp":1750183689000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572848.3577497"}},"subtitle":["Data Placement on Heterogeneous Memory for Task-Parallel HPC Applications with Load-Balance Awareness"],"short-title":[],"issued":{"date-parts":[[2023,2,21]]},"references-count":93,"alternative-id":["10.1145\/3572848.3577497","10.1145\/3572848"],"URL":"https:\/\/doi.org\/10.1145\/3572848.3577497","relation":{},"subject":[],"published":{"date-parts":[[2023,2,21]]},"assertion":[{"value":"2023-02-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}