{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T13:13:32Z","timestamp":1776950012353,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":10,"publisher":"ACM","funder":[{"name":"NSF (National Science Foundation)","award":["CNS-1816887, CCF-1763747"],"award-info":[{"award-number":["CNS-1816887, CCF-1763747"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,4]]},"DOI":"10.1145\/3777884.3797813","type":"proceedings-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T12:27:26Z","timestamp":1776947246000},"page":"1-2","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Systems for AI: Predicting Performance of Machine Learning Workloads"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8308-0231","authenticated-orcid":false,"given":"Zhuojin","family":"Li","sequence":"first","affiliation":[{"name":"University of Southern California, Los Angeles, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5110-203X","authenticated-orcid":false,"given":"Marco","family":"Paolieri","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8353-5040","authenticated-orcid":false,"given":"Leana","family":"Golubchik","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, USA"}]}],"member":"320","published-online":{"date-parts":[[2026,5,3]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"3634","article-title":"NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size","volume":"44","author":"Dong X.","year":"2021","unstructured":"X. Dong, L. Liu, K. Musial, and B. Gabrys. 2021. NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size. IEEE Trans. Pattern Anal. Mach. Intell. 44, 7 (2021), 3634-3646.","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_1_2_1","unstructured":"Y. Gao et al. 2021. Runtime Performance Prediction for Deep Learning Models with Graph Neural Network. Technical Report. MSR-TR-2021-3 Microsoft."},{"key":"e_1_3_2_1_3_1","first-page":"31","article-title":"A Benchmark for ML Inference Latency on Mobile Devices","author":"Li Z.","year":"2024","unstructured":"Z. Li, M. Paolieri, and L. Golubchik. 2024. A Benchmark for ML Inference Latency on Mobile Devices. In Proceedings of EdgeSys. ACM, 31-36.","journal-title":"Proceedings of EdgeSys. ACM"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Z. Li M. Paolieri and L. Golubchik. 2024. Inference Latency Prediction for CNNs on Heterogeneous Mobile Devices and ML frameworks. Perform. Eval. 165 (2024).","DOI":"10.1016\/j.peva.2024.102429"},{"key":"e_1_3_2_1_5_1","first-page":"41","article-title":"Accelerating Mobile Inference through Fine-Grained CPU-GPU Co-Execution. In Proceedings of EPEW 2025 (Lecture Notes in Computer Science, Vol. 15657)","author":"Li Z.","year":"2026","unstructured":"Z. Li, M. Paolieri, and L. Golubchik. 2026. Accelerating Mobile Inference through Fine-Grained CPU-GPU Co-Execution. In Proceedings of EPEW 2025 (Lecture Notes in Computer Science, Vol. 15657). Springer, 41-55.","journal-title":"Springer"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of VALUETOOLS 2024 (LNICST","volume":"251","author":"Li Z.","unstructured":"Z. Li, M. Paolieri, and L. Golubchik. 2026. A Study on Inference Latency for Vision Transformers on Mobile Devices. In Proceedings of VALUETOOLS 2024 (LNICST, Vol. 663). Springer, 229-251."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3151739"},{"key":"e_1_3_2_1_8_1","first-page":"1","article-title":"Optimus: an Efficient Dynamic Resource Scheduler for Deep Learning Clusters","volume":"3","year":"2018","unstructured":"Yanghua Peng et al. 2018. Optimus: an Efficient Dynamic Resource Scheduler for Deep Learning Clusters. In Proceedings of EuroSys. 3:1-3:14.","journal-title":"Proceedings of EuroSys."},{"key":"e_1_3_2_1_9_1","first-page":"6105","article-title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","author":"Tan M.","year":"2019","unstructured":"M. Tan and Q. Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Proceedings of ICML. PMLR, 6105-6114.","journal-title":"Proceedings of ICML. PMLR"},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Cynthia: Cost-Efficient Cloud Resource Provisioning for Predictable Distributed Deep Neural Network Training","volume":"86","author":"Zheng H.","year":"2019","unstructured":"H. Zheng et al. 2019. Cynthia: Cost-Efficient Cloud Resource Provisioning for Predictable Distributed Deep Neural Network Training. In Proceedings of ICPP. 86:1-86:11.","journal-title":"Proceedings of ICPP."}],"event":{"name":"ICPE '26: 17th ACM\/SPEC International Conference on Performance Engineering","location":"Florence Italy","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SPEC"]},"container-title":["Proceedings of the 17th ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T12:27:29Z","timestamp":1776947249000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3777884.3797813"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,3]]},"references-count":10,"alternative-id":["10.1145\/3777884.3797813","10.1145\/3777884"],"URL":"https:\/\/doi.org\/10.1145\/3777884.3797813","relation":{},"subject":[],"published":{"date-parts":[[2026,5,3]]},"assertion":[{"value":"2026-05-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}