{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T21:47:25Z","timestamp":1764020845209,"version":"3.40.3"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"industry, government, and institute members of the NSF Space, High-Performance, and Resilient Computing (SHREC) Center"},{"name":"Industry-University Cooperative Research Centers (IUCRC) Program of the National Science Foundation"},{"DOI":"10.13039\/100016300","name":"Center for Research Computing, University of Pittsburgh","doi-asserted-by":"publisher","award":["RRID:SCR_022735"],"award-info":[{"award-number":["RRID:SCR_022735"]}],"id":[{"id":"10.13039\/100016300","id-type":"DOI","asserted-by":"publisher"}]},{"name":"H2P cluster"},{"name":"NSF","award":["OAC-2117681"],"award-info":[{"award-number":["OAC-2117681"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3553071","type":"journal-article","created":{"date-parts":[[2025,3,21]],"date-time":"2025-03-21T19:23:42Z","timestamp":1742585022000},"page":"53420-53432","source":"Crossref","is-referenced-by-count":1,"title":["SPOC: Model Metrics and Inference Scalability"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1173-0378","authenticated-orcid":false,"given":"Calvin B.","family":"Gealy","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8777-4655","authenticated-orcid":false,"given":"David","family":"Langerman","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9270-8502","authenticated-orcid":false,"given":"Marika E.","family":"Schubert","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9665-2879","authenticated-orcid":false,"given":"Alan D.","family":"George","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Models and Pre-Trained Weights\u2014Torchvision Documentation","year":"2023","key":"ref1"},{"volume-title":"PyTorch Image Models","year":"2019","author":"Wightman","key":"ref2"},{"volume-title":"Papers With Code\u2014ImageNet Benchmark (Image Classification)","year":"2024","key":"ref3"},{"key":"ref4","first-page":"4510","article-title":"MobileNetV2: Inverted residuals and linear bottlenecks","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Sandler"},{"key":"ref5","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref7","article-title":"Applying the roofline model for deep learning performance optimizations","author":"Czaja","year":"2020","journal-title":"arXiv:2009.11224"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s42514-019-00018-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-80126-7_35"},{"key":"ref10","first-page":"10","article-title":"Time-based roofline for deep learning performance analysis","volume-title":"Proc. IEEE\/ACM 4th Workshop Deep Learn. Supercomput. (DLS)","author":"Wang"},{"key":"ref11","first-page":"10480","article-title":"BRP-NAS: Prediction-based NAS using GCNs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Dudziak"},{"key":"ref12","first-page":"27016","article-title":"Hardware-adaptive efficient latency prediction for NAS via meta-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lee"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467882"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3578244.3583735"},{"key":"ref15","first-page":"2746","article-title":"MAPLE: Microprocessor a priori for latency estimation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW)","author":"Abbasi"},{"key":"ref16","first-page":"3659","article-title":"MAPLE-edge: A runtime latency predictor for edge devices","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW)","author":"Nair"},{"volume-title":"ONNX Runtime","year":"2021","key":"ref17"},{"volume-title":"CS231n: Deep Learning for Computer Vision | Lecture 11","year":"2016","author":"Li","key":"ref18"},{"key":"ref19","first-page":"4013","article-title":"Fast algorithms for convolutional neural networks","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Lavin"},{"key":"ref20","first-page":"1","article-title":"ModelGauge: Inference profiling of deep-learning models","volume-title":"Proc. IEEE High Perform. Extreme Comput. Conf.","author":"Gealy"},{"volume-title":"ONNX: Open Neural Network Exchange","year":"2019","key":"ref21"},{"volume-title":"NVIDIA TensorRT","year":"2023","key":"ref22"},{"volume-title":"CuDNN | Convolutional Layers User\u2019s Guide","year":"2023","key":"ref23"},{"volume-title":"Valgrind","year":"2023","key":"ref24"},{"volume-title":"Nsight Systems","year":"2023","key":"ref25"},{"key":"ref26","first-page":"1","article-title":"Beyond floating-point ops: CNN performance prediction with critical datapath length","volume-title":"Proc. IEEE High Perform. Extreme Comput. Conf. (HPEC)","author":"Langerman"},{"article-title":"In pursuit of graph analysis for neural-network performance evaluation","year":"2022","author":"Langerman","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"volume-title":"PyTorch-OpCounter","year":"2022","author":"Zhu","key":"ref29"},{"volume-title":"ONNX Simplifier","year":"2024","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","first-page":"87.1","article-title":"Wide residual networks","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zagoruyko"},{"key":"ref33","first-page":"1","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mehta"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/10820123\/10934997-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10934997.pdf?arnumber=10934997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T00:22:40Z","timestamp":1743639760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10934997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3553071","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}