{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:20:34Z","timestamp":1772695234757,"version":"3.50.1"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022YFB4501300"],"award-info":[{"award-number":["2022YFB4501300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272185"],"award-info":[{"award-number":["62272185"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408557","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-14","source":"Crossref","is-referenced-by-count":0,"title":["SpotCC: Facilitating Coded Computation for Prediction Serving Systems on Spot Instances"],"prefix":"10.1109","author":[{"given":"Lin","family":"Wang","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchong","family":"Hu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziling","family":"Duan","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingqi","family":"Li","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenxuan","family":"Yao","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feifan","family":"Liu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolu","family":"Li","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leihua","family":"Qin","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Feng","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref2","volume-title":"Alibaba Cloud Pricing"},{"key":"ref3","volume-title":"Google Lens: real-time answers to questions about the world around you"},{"key":"ref4","volume-title":"Machine learning on aws"},{"key":"ref6","volume-title":"iOS Siri"},{"key":"ref7","volume-title":"Load Balancer of AWS"},{"key":"ref13","volume-title":"AWS Spot Instances"},{"key":"ref15","article-title":"Invertible residual networks","author":"Behrmann","year":"2019","journal-title":"Proc. of ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1147\/sj.52.0078"},{"key":"ref18","article-title":"Clipper: A Low-Latency online prediction serving system","author":"Crankshaw","year":"2017","journal-title":"Proc. of USENIX NSDI"},{"key":"ref19","article-title":"Coded-invnet for resilient prediction serving systems","author":"Dinh","year":"2021","journal-title":"Proc. of ICML. PMLR"},{"key":"ref20","article-title":"Parcae: Proactive,Liveput-Optimized DNN training on preemptible instances","author":"Duan","year":"2024","journal-title":"Proc. of USENIX NSDI"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-64171-8_26"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1165389.945450"},{"key":"ref24","volume-title":"Google Cloud AI"},{"key":"ref26","article-title":"Cocktail: A multidimensional optimization for model serving in cloud","author":"Gunasekaran","year":"2022","journal-title":"Proc. of USENIX NSDI"},{"key":"ref27","article-title":"Tributary: spot-dancing for elastic services with latency SLOs","author":"Harlap","year":"2018","journal-title":"Proc. of USENIX ATC"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","volume-title":"How To Reduce Cold Start Times For LLM Inference"},{"key":"ref30","article-title":"Erasure coding in windows azure storage","author":"Huang","year":"2012","journal-title":"Proc. of USENIX ATC"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3151434"},{"key":"ref32","article-title":"Invertible convolutional flow","volume":"32","author":"Karami","year":"2019","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00090"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359654"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2983165"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2736066"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2017.21"},{"key":"ref38","article-title":"AlpaServe: Statistical multiplexing with model parallelism for deep learning serving","author":"Li","year":"2023","journal-title":"Proc. of USENIX OSDI"},{"key":"ref39","volume-title":"Loading Llama-2 70b 20x faster"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717459"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640411"},{"key":"ref42","volume-title":"Azure machine learning studio"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.13"},{"key":"ref44","volume-title":"Triton Inference Server"},{"key":"ref46","article-title":"A cost-benefit analysis of on-premise large language model deployment: Breaking even with commercial 11 m services","author":"Pan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3328740"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1137\/0108018"},{"key":"ref50","article-title":"Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider","author":"Shahrad","year":"2020","journal-title":"Proc. of USENIX ATC"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741953"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3708994"},{"key":"ref53","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20809"},{"key":"ref55","article-title":"Bamboo: Making preemptible instances resilient for affordable training of large DNNs","author":"Thorpe","year":"2023","journal-title":"Proc. of USENIX NSDI"},{"key":"ref57","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning. PMLR","author":"Touvron"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1002\/9780470940105.ch18"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-69766-1_33"},{"key":"ref60","first-page":"5152","article-title":"Coded sparse matrix multiplication","author":"Wang","year":"2018","journal-title":"Proc. of ICML. PMLR"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref62","article-title":"Can\u2019t be late: optimizing spot instance savings under deadlines","author":"Wu","year":"2024","journal-title":"Proc. of USENIX NSDI"},{"key":"ref63","article-title":"Polynomial codes: an optimal design for high-dimensional coded matrix multiplication","volume":"30","author":"Yu","year":"2017","journal-title":"Proc. of NeurIPS"},{"key":"ref64","article-title":"MArk: Exploiting cloud services for Cost-Effective,SLO-Aware machine learning inference serving","author":"Zhang","year":"2019","journal-title":"Proc. of USENIX ATC"},{"key":"ref65","article-title":"Beyond benchmarks: The economics of ai inference","author":"Zhuang","year":"2025","journal-title":"arXiv preprint"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408557.pdf?arnumber=11408557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:48:52Z","timestamp":1772693332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408557","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}