{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:03:23Z","timestamp":1776931403513,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":86,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation","award":["No.62372218, No.U24A6009"],"award-info":[{"award-number":["No.62372218, No.U24A6009"]}]},{"name":"HK RGC Collaborative Research Fund","award":["No. C5032-23GF"],"award-info":[{"award-number":["No. C5032-23GF"]}]},{"name":"Research Institute for Artificial Intelligence of Things, The Hong Kong Polytechnic University"},{"DOI":"10.13039\/100018735","name":"Ant Group","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756088","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"1178-1192","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Dimensional ML-Pipeline Optimization in Cost-Effective Disaggregated Datacenter"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9769-2570","authenticated-orcid":false,"given":"Pingyi","family":"Huo","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, The Pennsylvania State University, State College, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5273-1110","authenticated-orcid":false,"given":"Anusha","family":"Devulapally","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, State College, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0089-9370","authenticated-orcid":false,"given":"Hasan","family":"Al Maruf","sequence":"additional","affiliation":[{"name":"META, Inc, Menlo Park, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5672-795X","authenticated-orcid":false,"given":"Nandhini","family":"Chandramoorthy","sequence":"additional","affiliation":[{"name":"IBM, Inc, New York City, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3155-6269","authenticated-orcid":false,"given":"Meena","family":"Arunachalam","sequence":"additional","affiliation":[{"name":"AMD, Inc, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-2204","authenticated-orcid":false,"given":"Gulsum Gudukbay","family":"Akbulut","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, State College, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9940-9951","authenticated-orcid":false,"given":"Mahmut T","family":"Kandemir","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, State College, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6266-6068","authenticated-orcid":false,"given":"Vijaykrishnan","family":"Narayanan","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, State College, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2023. Why AI Inference Will Remain Largely On the CPU. https:\/\/www.nextplatform.com\/2023\/04\/05\/why-ai-inference-will-remain-largely-on-the-cpu\/. Accessed: March 11 2025."},{"key":"e_1_3_3_1_3_2","unstructured":"Mart\u00edn Abadi Paul Barham Jianmin Chen Zhifeng Chen Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Geoffrey Irving Michael Isard Manjunath Kudlur Josh Levenberg Rajat Monga Sherry Moore Derek\u00a0G. Murray Benoit Steiner Paul Tucker Vijay Vasudevan Pete Warden Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2016. TensorFlow: A system for large-scale machine learning. arxiv:https:\/\/arXiv.org\/abs\/1605.08695\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/1605.08695"},{"key":"e_1_3_3_1_4_2","unstructured":"Inc. Advanced Micro\u00a0Devices. 2024. AMD uProf: AMD\u00ae Micro Profiler. https:\/\/www.amd.com\/en\/developer\/uprof.html Accessed: 2024-11-10."},{"key":"e_1_3_3_1_5_2","unstructured":"Entisar Alkayal. 2018. Optimizing resource allocation using multi-objective particle swarm optimization in cloud computing systems. Ph.\u00a0D. Dissertation. University of Southampton."},{"key":"e_1_3_3_1_6_2","unstructured":"Amazon Web Services. n. d.. Optimize cost by automating the start\/stop of resources in non-production environments. https:\/\/aws.amazon.com\/blogs\/architecture\/optimize-cost-by-automating-the-start-stop-of-resources-in-non-production-environments\/ Accessed: 2024-11-21."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267815"},{"key":"e_1_3_3_1_8_2","unstructured":"ARM. n. d.. ARM NEON Technology. https:\/\/www.arm.com\/technologies\/neon. Accessed: Month Day Year."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01741-4"},{"key":"e_1_3_3_1_10_2","unstructured":"BLS Strategies. [n. d.]. Power Requirements Energy Costs and Incentives for Data Centers. https:\/\/www.blsstrategies.com\/insights-press\/power-requirements-energy-costs-and-incentives-for-data-centers. Accessed: 2024-06-26."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCC53001.2021.9631464"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Vahid\u00a0Asadzadeh Chalack SN Razavi and SJ Gudakahriz. 2017. Resource allocation in cloud environment using approaches based particle swarm optimization. International Journal of Computer Applications Technology and Research 6 2 (2017) 87\u201390.","DOI":"10.7753\/IJCATR0602.1003"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Tejalal Choudhary Vipul Mishra Anurag Goswami and Jagannathan Sarangapani. 2022. Inference-aware convolutional neural network pruning. Future Generation Computer Systems 135 (2022) 44\u201356.","DOI":"10.1016\/j.future.2022.04.031"},{"key":"e_1_3_3_1_14_2","unstructured":"Compute Express Link Consortium. 2019. Compute Express Link (CXL) Specification 1.1. https:\/\/www.computeexpresslink.org\/."},{"key":"e_1_3_3_1_15_2","unstructured":"Intel Corporation. 2023. Running Average Power Limit (RAPL) Energy Reporting. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/software-security-guidance\/advisory-guidance\/running-average-power-limit-energy-reporting.html Accessed: 2024-11-22."},{"key":"e_1_3_3_1_16_2","unstructured":"Intel Corporation. 2024. Intel\u00ae Performance Counter Monitor (Intel\u00ae PCM). https:\/\/github.com\/intel\/pcm Accessed: 2024-11-10."},{"key":"e_1_3_3_1_17_2","unstructured":"Intel Corporation. 2024. MBA. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/introduction-to-memory-bandwidth-allocation.html Accessed: 2024-11-10."},{"key":"e_1_3_3_1_18_2","unstructured":"Compute Express\u00a0Link (CXL). 2024. Compute Express Link (CXL). https:\/\/computeexpresslink.org\/. Accessed: 2024-11-22."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Radosvet Desislavov Fernando Mart\u00ednez-Plumed and Jos\u00e9 Hern\u00e1ndez-Orallo. 2023. Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning. Sustainable Computing: Informatics and Systems 38 (2023) 100857.","DOI":"10.1016\/j.suscom.2023.100857"},{"key":"e_1_3_3_1_20_2","unstructured":"The Linux\u00a0Kernel Documentation. 2024. BPF Maps. https:\/\/docs.kernel.org\/bpf\/maps.html. Accessed: 2024-11-20."},{"key":"e_1_3_3_1_21_2","unstructured":"Inc. Draios. [n. d.]. Sysdig. https:\/\/github.com\/draios\/sysdig. Accessed: 15 March 2025."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCIS.2012.6664566"},{"key":"e_1_3_3_1_23_2","unstructured":"Anwar Ghani Afzal Badshah Saeedullah Jan Abdulrahman\u00a0A Alshdadi and Ali Daud. 2020. Issues and challenges in cloud storage architecture: a survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2004.06809 abs\/2004.06809 (2020) 16\u00a0pages."},{"key":"e_1_3_3_1_24_2","series-title":"JMLR Workshop and Conference Proceedings","first-page":"648","volume-title":"Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, AISTATS 2016, Cadiz, Spain, May 9-11, 2016","volume":"51","author":"Gonz\u00e1lez Javier","year":"2016","unstructured":"Javier Gonz\u00e1lez, Zhenwen Dai, Philipp Hennig, and Neil\u00a0D. Lawrence. 2016. Batch Bayesian Optimization via Local Penalization. In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, AISTATS 2016, Cadiz, Spain, May 9-11, 2016(JMLR Workshop and Conference Proceedings, Vol.\u00a051), Arthur Gretton and Christian\u00a0C. Robert (Eds.). JMLR.org, Cadiz, Spain, 648\u2013657. http:\/\/proceedings.mlr.press\/v51\/gonzalez16a.html"},{"key":"e_1_3_3_1_25_2","first-page":"443","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Gujarati Arpan","year":"2020","unstructured":"Arpan Gujarati, Reza Karimi, Safya Alzayat, Wei Hao, Antoine Kaufmann, Ymir Vigfusson, and Jonathan Mace. 2020. Serving DNNs like Clockwork: Performance Predictability from the Bottom Up. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, USA, 443\u2013462. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/gujarati"},{"key":"e_1_3_3_1_26_2","unstructured":"Udit Gupta Samuel Hsia Vikram Saraph Xiaodong Wang Brandon Reagen Gu-Yeon Wei Hsien-Hsin\u00a0S. Lee David Brooks and Carole-Jean Wu. 2020. DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference. arxiv:https:\/\/arXiv.org\/abs\/2001.02772\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2001.02772"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00047"},{"key":"e_1_3_3_1_28_2","volume-title":"Configure Linux Auditing (auditd)","author":"Hat Red","year":"2020","unstructured":"Red Hat. 2020. Configure Linux Auditing (auditd). https:\/\/www.redhat.com\/en\/blog\/configure-linux-auditing-auditd Accessed: 8 April 2025."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-32041-5_3"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Pingyi Huo Anusha Devulapally Hasan\u00a0Al Maruf Minseo Park Krishnakumar Nair Meena Arunachalam Gulsum Gudukbay\u00a0Akbulut Mahmut\u00a0Taylan Kandemir and Vijaykrishnan Narayanan. 2024. PIFS-Rec: Process-In-Fabric-Switch for Large-Scale Recommendation System Inferences. 15\u00a0pages.","DOI":"10.1109\/MICRO61859.2024.00052"},{"key":"e_1_3_3_1_32_2","unstructured":"Informatica. 2024. Recommendations for Batch Job Optimization. https:\/\/docs.informatica.com\/master-data-management\/multidomain-mdm\/10-4\/performance-tuning-guide\/recommendations\/recommendations-for-batch-job-optimization.html Accessed: 2024-11-10."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589112"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589112"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00019"},{"key":"e_1_3_3_1_36_2","unstructured":"Liu Ke Udit Gupta Mark Hempstead Carole-Jean Wu Hsien-Hsin\u00a0S. Lee and Xuan Zhang. 2022. Hercules: Heterogeneity-Aware Inference Serving for At-Scale Personalized Recommendation. arxiv:https:\/\/arXiv.org\/abs\/2203.07424\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2203.07424"},{"key":"e_1_3_3_1_37_2","unstructured":"Jesse\u00a0St. Laurent. 2016. Rejuvenate the Refresh Cycle. https:\/\/www.datacenterdynamics.com\/en\/opinions\/rejuvenate-the-refresh-cycle\/"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"e_1_3_3_1_39_2","volume-title":"2011 USENIX Annual Technical Conference (USENIX ATC 11)","author":"Lim Harold","year":"2011","unstructured":"Harold Lim, Aman Kansal, and Jie Liu. 2011. Power budgeting for virtualized data centers. In 2011 USENIX Annual Technical Conference (USENIX ATC 11)."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","unstructured":"Sudheer Mangalampalli Ganesh\u00a0Reddy Karri Mohit Kumar Osama\u00a0Ibrahim Khalaf Carlos Andres\u00a0Tavera Romero and GhaidaMuttashar\u00a0Abdul Sahib. 2023. DRLBTSA: Deep reinforcement learning based task-scheduling algorithm in cloud computing. Multimedia Tools Appl. 83 3 (June 2023) 8359\u20138387. 10.1007\/s11042-023-16008-2","DOI":"10.1007\/s11042-023-16008-2"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582063"},{"key":"e_1_3_3_1_42_2","unstructured":"Scott Matteson. 2020. 10 tips for planning a data center hardware refresh. https:\/\/www.techrepublic.com\/article\/ten-tips-for-planning-a-data-center-hardware-refresh\/ Accessed: 2024-11-10."},{"key":"e_1_3_3_1_43_2","unstructured":"Ioannis Mavromatis Kostas Katsaros and Aftab Khan. 2024. Computing Within Limits: An Empirical Study of Energy Consumption in ML Training and Inference. arxiv:https:\/\/arXiv.org\/abs\/2406.14328\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2406.14328"},{"key":"e_1_3_3_1_44_2","unstructured":"MemVerge. [n. d.]. CXL Use Case \/ Memory Costs and Expand Capacity. https:\/\/memverge.com\/cxl-use-case-slash-memory-costs-and-expand-capacity\/. Accessed: Month Day Year."},{"key":"e_1_3_3_1_45_2","unstructured":"Microsoft. 2024. How to use batching to improve application performance - Azure SQL. https:\/\/learn.microsoft.com\/en-us\/azure\/azure-sql\/performance-improve-use-batching?view=azuresql Accessed: 2024-11-10."},{"key":"e_1_3_3_1_46_2","unstructured":"Microsoft. 2024. Load-balancing options - Azure Architecture Center. https:\/\/learn.microsoft.com\/en-us\/azure\/architecture\/guide\/technology-choices\/load-balancing-overview Accessed: 2024-11-10."},{"key":"e_1_3_3_1_47_2","unstructured":"Microsoft Azure. [n. d.]. Linux Virtual Machines Pricing. https:\/\/azure.microsoft.com\/en-us\/pricing\/details\/virtual-machines\/linux\/#pricing. Accessed: Month Day Year."},{"key":"e_1_3_3_1_48_2","unstructured":"Microsoft Learn. n. d.. How do I set a automation to stop a VM on weekends & evenings. https:\/\/learn.microsoft.com\/en-us\/answers\/questions\/1301581\/how-do-i-set-a-automation-to-stop-a-vm-on-weekends\/ Accessed: 2024-11-21."},{"key":"e_1_3_3_1_49_2","unstructured":"Mindsight. 2017. Case Study: A Full Hardware Refresh Roadmap. https:\/\/gomindsight.com\/insights\/blog\/case-study-hardware-refresh\/"},{"key":"e_1_3_3_1_50_2","unstructured":"Krishnakumar Nair Avinash-Chandra Pandey Siddappa Karabannavar Meena Arunachalam John Kalamatianos Varun Agrawal Saurabh Gupta Ashish Sirasao Elliott Delaye Steve Reinhardt et\u00a0al. 2024. Parallelization strategies for dlrm embedding bag operator on amd cpus. IEEE Micro (2024)."},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"crossref","unstructured":"Efterpi Paraskevoulakou and Dimosthenis Kyriazis. 2023. Ml-faas: Toward exploiting the serverless paradigm to facilitate machine learning functions as a service. IEEE Transactions on Network and Service Management 20 3 (2023) 2110\u20132123.","DOI":"10.1109\/TNSM.2023.3239672"},{"key":"e_1_3_3_1_52_2","unstructured":"Jongsoo Park Maxim Naumov Protonu Basu Summer Deng Aravind Kalaiah Daya Khudia James Law Parth Malani Andrey Malevich Satish Nadathur Juan Pino Martin Schatz Alexander Sidorov Viswanath Sivakumar Andrew Tulloch Xiaodong Wang Yiming Wu Hector Yuen Utku Diril Dmytro Dzhulgakov Kim Hazelwood Bill Jia Yangqing Jia Lin Qiao Vijay Rao Nadav Rotem Sungjoo Yoo and Mikhail Smelyanskiy. 2018. Deep Learning Inference in Facebook Data Centers: Characterization Performance Optimizations and Hardware Implications. arxiv:https:\/\/arXiv.org\/abs\/1811.09886\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1811.09886"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10558132"},{"key":"e_1_3_3_1_54_2","unstructured":"David\u00a0A. Patterson Joseph Gonzalez Quoc\u00a0V. Le Chen Liang Lluis-Miquel Munguia Daniel Rothchild David\u00a0R. So Maud Texier and Jeff Dean. 2021. Carbon Emissions and Large Neural Network Training. CoRR abs\/2104.10350 (2021) 22\u00a0pages. arXiv:https:\/\/arXiv.org\/abs\/2104.10350https:\/\/arxiv.org\/abs\/2104.10350"},{"key":"e_1_3_3_1_55_2","unstructured":"puzl.ai. 2025. Pricing. https:\/\/puzl.cloud\/gpu-cloud Accessed: 2025-03-12."},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E59103.2023.00027"},{"key":"e_1_3_3_1_57_2","unstructured":"Rafael Ramos. 2025. Intel AMX Enables High-Efficiency CPU Inference for AI Workloads. https:\/\/openmetal.io\/resources\/blog\/intel-amx-ai-inference-performance\/. Accessed: 2025-06-19."},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391236"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"Gaith Rjoub Jamal Bentahar Omar Abdel\u00a0Wahab and Ahmed Saleh\u00a0Bataineh. 2021. Deep and reinforcement learning for automated task scheduling in large-scale cloud computing systems. Concurrency and Computation: Practice and Experience 33 23 (2021) e5919.","DOI":"10.1002\/cpe.5919"},{"key":"e_1_3_3_1_60_2","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2112.10752\u00a0[cs.CV]"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486972"},{"key":"e_1_3_3_1_63_2","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily Denton Seyed Kamyar\u00a0Seyed Ghasemipour Burcu\u00a0Karagol Ayan S.\u00a0Sara Mahdavi Rapha\u00a0Gontijo Lopes Tim Salimans Jonathan Ho David\u00a0J Fleet and Mohammad Norouzi. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. arxiv:https:\/\/arXiv.org\/abs\/2205.11487\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2205.11487"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00087"},{"key":"e_1_3_3_1_65_2","unstructured":"Sematext. [n. d.]. Auditd - Linux Audit Daemon. https:\/\/sematext.com\/glossary\/auditd\/. Accessed: 15 March 2025."},{"key":"e_1_3_3_1_66_2","unstructured":"Amazon\u00a0Web Services. n. d.. Amazon Rekognition User Guide. https:\/\/docs.aws.amazon.com\/managedservices\/latest\/userguide\/rekognition.html. Accessed: Month Day Year."},{"key":"e_1_3_3_1_67_2","unstructured":"Amazon\u00a0Web Services. n. d.. Choose the Best AI Accelerator and Model Compilation for Computer Vision Inference with Amazon SageMaker. https:\/\/aws.amazon.com\/blogs\/machine-learning\/choose-the-best-ai-accelerator-and-model-compilation-for-computer-vision-inference-with-amazon-sagemaker\/. Accessed: Month Day Year."},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"crossref","unstructured":"Husain Sharaf Imtiaz Ahmad and Tassos Dimitriou. 2022. Extended berkeley packet filter: An application perspective. IEEE Access 10 (2022) 126370\u2013126393.","DOI":"10.1109\/ACCESS.2022.3226269"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"crossref","unstructured":"Joseph\u00a0E Stiglitz. 1981. Pareto optimality and competition. The Journal of Finance 36 2 (1981) 235\u2013251.","DOI":"10.1111\/j.1540-6261.1981.tb00437.x"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614256"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","unstructured":"Shashank Swarup Elhadi\u00a0M. Shakshuki and Ansar Yasar. 2021. Task Scheduling in Cloud Using Deep Reinforcement Learning. Procedia Computer Science 184 (2021) 42\u201351. 10.1016\/j.procs.2021.03.016The 12th International Conference on Ambient Systems Networks and Technologies (ANT) \/ The 4th International Conference on Emerging Data and Industry 4.0 (EDI40) \/ Affiliated Workshops.","DOI":"10.1016\/j.procs.2021.03.016"},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","unstructured":"Fatma\u00a0M. Talaat Hesham\u00a0A. Ali Mohamed\u00a0S. Saraya and Ahmed\u00a0I. Saleh. 2022. Effective scheduling algorithm for load balancing in fog environment using CNN and MPSO. Knowl. Inf. Syst. 64 3 (March 2022) 773\u2013797. 10.1007\/s10115-021-01649-2","DOI":"10.1007\/s10115-021-01649-2"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624865"},{"key":"e_1_3_3_1_74_2","volume-title":"Twitter Stream Archive, April 2018","author":"Team Archive","year":"2018","unstructured":"Archive Team. 2018. Twitter Stream Archive, April 2018. Twitter. https:\/\/archive.org\/details\/archiveteam-twitter-stream-2018-04 Internet Archive."},{"key":"e_1_3_3_1_75_2","unstructured":"TechRadar. 2023. DDR5 vs DDR4 RAM: what\u2019s the difference?https:\/\/www.techradar.com\/features\/ddr5-vs-ddr4-ram-whats-the-difference. Accessed: 2024-11-22."},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"publisher","unstructured":"Zhao Tong Hongjian Chen Xiaomei Deng Kenli Li and Keqin Li. 2020. A scheduling scheme in the cloud computing environment using deep Q-learning. Inf. Sci. 512 C (Feb. 2020) 1170\u20131191. 10.1016\/j.ins.2019.10.035","DOI":"10.1016\/j.ins.2019.10.035"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/PIC.2017.8359556"},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00041"},{"key":"e_1_3_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621120"},{"key":"e_1_3_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446083"},{"key":"e_1_3_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2022-Spring54318.2022.9860395"},{"key":"e_1_3_3_1_82_2","first-page":"199","volume-title":"20th USENIX Conference on File and Storage Technologies (FAST 22)","author":"Yi Jifei","year":"2022","unstructured":"Jifei Yi, Benchao Dong, Mingkai Dong, Ruizhe Tong, and Haibo Chen. 2022. MT2: Memory Bandwidth Regulation on Hybrid NVMDRAM Platforms. In 20th USENIX Conference on File and Storage Technologies (FAST 22). USENIX Association, Santa Clara, CA, 199\u2013216. https:\/\/www.usenix.org\/conference\/fast22\/presentation\/yi-mt2"},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3686081.3686118"},{"key":"e_1_3_3_1_84_2","doi-asserted-by":"publisher","unstructured":"Miao Zhang Yifei Zhu Jiangchuan Liu Feng Wang and Fangxin Wang. 2022. CharmSeeker: Automated Pipeline Configuration for Serverless Video Processing. IEEE\/ACM Transactions on Networking 30 6 (2022) 2730\u20132743. 10.1109\/TNET.2022.3183231","DOI":"10.1109\/TNET.2022.3183231"},{"key":"e_1_3_3_1_85_2","doi-asserted-by":"crossref","unstructured":"Tianyi Zhang Jonah Yi Bowen Yao Zhaozhuo Xu and Anshumali Shrivastava. 2024. Nomad-attention: Efficient llm inference on cpus through multiply-add-free attention. Advances in Neural Information Processing Systems 37 (2024) 112706\u2013112730.","DOI":"10.52202\/079017-3581"},{"key":"e_1_3_3_1_86_2","first-page":"37","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhong Yuhong","year":"2024","unstructured":"Yuhong Zhong, Daniel\u00a0S. Berger, Carl Waldspurger, Ryan Wee, Ishwar Agarwal, Rajat Agarwal, Frank Hady, Karthik Kumar, Mark\u00a0D. Hill, Mosharaf Chowdhury, and Asaf Cidon. 2024. Managing Memory Tiers with CXL in Virtualized Environments. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 37\u201356. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/zhong-yuhong"},{"key":"e_1_3_3_1_87_2","unstructured":"Hongyu Zhu Mohamed Akrout Bojian Zheng Andrew Pelegris Amar Phanishayee Bianca Schroeder and Gennady Pekhimenko. 2018. TBD: Benchmarking and Analyzing Deep Neural Network Training. arxiv:https:\/\/arXiv.org\/abs\/1803.06905\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1803.06905"}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:46:33Z","timestamp":1769463993000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756088"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":86,"alternative-id":["10.1145\/3725843.3756088","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756088","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}