{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:07:22Z","timestamp":1778760442394,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:00:00Z","timestamp":1776902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,23]]},"DOI":"10.1145\/3746467.3801520","type":"proceedings-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:06:32Z","timestamp":1778756792000},"page":"276-280","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Deep Learning Inference on Multi-Core Laptop CPUs with Scheduling and Thread Affinity Strategies"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1517-5319","authenticated-orcid":false,"given":"Mohammod Akib","family":"Khan","sequence":"first","affiliation":[{"name":"Computer Science, Kennesaw State University, MARIETTA, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4488-8182","authenticated-orcid":false,"given":"Sahidul","family":"Islam","sequence":"additional","affiliation":[{"name":"Computer Science, Kennesaw State University, MARIETTA, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3691938.3691945"},{"key":"e_1_3_2_1_2_1","volume-title":"Packrat: Automatic Reconfiguration for Latency Minimization in CPU-based DNN Serving. ArXiv abs\/2311.18174","author":"Bhardwaj Ankit","year":"2023","unstructured":"Ankit Bhardwaj, Amar Phanishayee, Deepak Narayanan, Mihail Tarta, and Ryan Stutsman. 2023. Packrat: Automatic Reconfiguration for Latency Minimization in CPU-based DNN Serving. ArXiv abs\/2311.18174 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265506613"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68035-0_5"},{"key":"e_1_3_2_1_4_1","volume-title":"High Performance and Energy Efficient Inference for Deep Learning on ARM Processors. arXiv preprint arXiv:2105.09187","author":"Castell\u00f3 Adri\u00e1n","year":"2021","unstructured":"Adri\u00e1n Castell\u00f3, Sergio Barrachina, Manuel F. Dolz, Enrique S. Quintana-Ort\u00ed, and Pau San Juan. 2021. High Performance and Energy Efficient Inference for Deep Learning on ARM Processors. arXiv preprint arXiv:2105.09187 (2021). https:\/\/arxiv.org\/abs\/2105.09187"},{"key":"e_1_3_2_1_5_1","volume-title":"IOS: Inter-Operator Scheduler for CNN Acceleration. CoRR abs\/2011.01302","author":"Ding Yaoyao","year":"2020","unstructured":"Yaoyao Ding, Ligeng Zhu, Zhihao Jia, Gennady Pekhimenko, and Song Han. 2020. IOS: Inter-Operator Scheduler for CNN Acceleration. CoRR abs\/2011.01302 (2020). arXiv:2011.01302 https:\/\/arxiv.org\/abs\/2011.01302"},{"key":"e_1_3_2_1_6_1","volume-title":"Imagenette: A Smaller Subset of 10 Easily Classified Classes from ImageNet. https:\/\/github.com\/fastai\/imagenette","author":"Howard Jeremy","year":"2019","unstructured":"Jeremy Howard. 2019. Imagenette: A Smaller Subset of 10 Easily Classified Classes from ImageNet. https:\/\/github.com\/fastai\/imagenette"},{"key":"e_1_3_2_1_7_1","unstructured":"Microsoft ONNX Runtime Team. 2025. Thread Management (Intra- and Inter-Op) in ONNX Runtime. https:\/\/onnxruntime.ai\/docs\/performance\/tune-performance\/threading.html"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071762"},{"key":"e_1_3_2_1_9_1","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Qiu Haoran","unstructured":"Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Saurabh Jha, Chen Wang, Hubertus Franke, Zbigniew Kalbarczyk, Tamer Ba\u015far, and Ravishankar K. Iyer. 2024. Power-aware Deep Learning Model Serving with \u03bc-Serve. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, USA, 75\u201393. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/qiu"},{"key":"e_1_3_2_1_10_1","volume-title":"Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. CoRR abs\/1801.04381","author":"Sandler Mark","year":"2018","unstructured":"Mark Sandler, Andrew G. Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation. CoRR abs\/1801.04381 (2018). arXiv:1801.04381 http:\/\/arxiv.org\/abs\/1801.04381"},{"key":"e_1_3_2_1_11_1","volume-title":"Faster, Cheaper and Lighter. CoRR abs\/1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a Distilled Version of BERT: Smaller, Faster, Cheaper and Lighter. CoRR abs\/1910.01108 (2019). arXiv:1910.01108 http:\/\/arxiv.org\/abs\/1910.01108"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP. Association for Computational Linguistics","author":"Wang Alex","year":"2018","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2018. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP. Association for Computational Linguistics, Brussels, Belgium."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448625"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2944584"},{"key":"e_1_3_2_1_16_1","unstructured":"Wikipedia contributors. 2025. Processor Affinity. https:\/\/en.wikipedia.org\/wiki\/Processor_affinity"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3529706.3529712"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604930.3605706"},{"key":"e_1_3_2_1_19_1","volume-title":"Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph E. Gonzalez, and Ion Stoica. 2020. Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, Berkeley, USA, 863\u2013879. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/zheng"}],"event":{"name":"ACMSE 2026: 2026 ACM Southeast Conference","location":"Troy University Troy AL USA","acronym":"ACMSE 2026"},"container-title":["Proceedings of the 2026 ACM Southeast Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746467.3801520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:08:23Z","timestamp":1778756903000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746467.3801520"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,23]]},"references-count":19,"alternative-id":["10.1145\/3746467.3801520","10.1145\/3746467"],"URL":"https:\/\/doi.org\/10.1145\/3746467.3801520","relation":{},"subject":[],"published":{"date-parts":[[2026,4,23]]},"assertion":[{"value":"2026-05-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}