{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:58:18Z","timestamp":1764014298683,"version":"3.45.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore under its Competitive Research Program","doi-asserted-by":"publisher","award":["NRF-CRP23-2019-0003"],"award-info":[{"award-number":["NRF-CRP23-2019-0003"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"gift from Black Sesame Technologies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcad.2025.3568348","type":"journal-article","created":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T13:38:49Z","timestamp":1746711529000},"page":"4472-4485","source":"Crossref","is-referenced-by-count":0,"title":["Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCs"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8982-4084","authenticated-orcid":false,"given":"Yujie","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore, Queenstown, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3120-5773","authenticated-orcid":false,"given":"Huiying","family":"Lan","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Queenstown, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0291-7555","authenticated-orcid":false,"given":"Ehsan","family":"Aghapour","sequence":"additional","affiliation":[{"name":"Department of Parallel Computer Systems, University of Amsterdam, Amsterdam, The Netherlands"}]},{"given":"Zhiyuan","family":"Ning","sequence":"additional","affiliation":[{"name":"Information Technology Department, Black Sesame Technologies, San Jose, CA, USA"}]},{"given":"Peng","family":"Zan","sequence":"additional","affiliation":[{"name":"Information Technology Department, Black Sesame Technologies, San Jose, CA, USA"}]},{"given":"Weidong","family":"Shao","sequence":"additional","affiliation":[{"name":"Information Technology Department, Black Sesame Technologies, San Jose, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5813-7021","authenticated-orcid":false,"given":"Anuj","family":"Pathania","sequence":"additional","affiliation":[{"name":"Department of Parallel Computer Systems, University of Amsterdam, Amsterdam, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4136-4188","authenticated-orcid":false,"given":"Tulika","family":"Mitra","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Queenstown, Singapore"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","first-page":"383","article-title":"Heterogeneous multi-core architectures","volume":"10","author":"Mitra","year":"2015","journal-title":"Inf. Media Technol."},{"key":"ref2","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref3","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Chen"},{"volume-title":"Compute Library: A Software Library for Machine Learning","year":"2023","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2944584"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS48895.2020.9073977"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60939-9_2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3656472"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120984"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-39932-9_16"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2825478"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/FI11040094"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSAMOS.2008.4664857"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/EURDAC.1996.558204"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/71.993206"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.02.023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2017.11.011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3081254"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2019.2909473"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247722"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2023.103051"},{"volume-title":"Amlogic AI processor A311D datasheet","year":"2023","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"volume-title":"Gurobi Optimizer Reference Manual","year":"2022","key":"ref28"},{"volume-title":"TinyMemBench.","year":"2019","author":"Siamashka","key":"ref29"},{"volume-title":"clpeak.","year":"2015","author":"Bhat","key":"ref30"},{"volume-title":"Black Sesame Technologies","year":"2024","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744894"},{"volume-title":"UM25C","year":"2023","key":"ref33"},{"key":"ref34","first-page":"313","article-title":"The sysfs filesystem","volume-title":"Proc. Linux Symp.","author":"Mochel"},{"volume-title":"Khadas Vim3 Pro","year":"2023","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/DSD57027.2022.00051"},{"key":"ref38","article-title":"Model parallelism on distributed infrastructure: A literature review from theory to LLM case-studies","author":"Brakel","year":"2024","journal-title":"arXiv:2403.03699"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-022-01814-y"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3564121.3564796"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LES.2021.3087707"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3301278"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3218991"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE59016.2024.10444298"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538948"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/11263962\/10993487.pdf?arnumber=10993487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:00:28Z","timestamp":1764010828000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10993487\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":45,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2025.3568348","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"type":"print","value":"0278-0070"},{"type":"electronic","value":"1937-4151"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}