{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T06:10:01Z","timestamp":1749622201242,"version":"3.41.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"AMD Center of Excellence and AMD HACC Initiative at UIUC and the Hewlett Packard Labs"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tc.2025.3558606","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T17:25:31Z","timestamp":1744133131000},"page":"2417-2430","source":"Crossref","is-referenced-by-count":0,"title":["MLCD: Machine Learning-Based Code Version and Device Selection for Heterogeneous Systems"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3764-4275","authenticated-orcid":false,"given":"Kaiwen","family":"Cao","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6646-8146","authenticated-orcid":false,"given":"Hanchen","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0524-6934","authenticated-orcid":false,"given":"Yihan","family":"Pang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3016-0270","authenticated-orcid":false,"given":"Deming","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Fast training of convolutional networks through FFTS","year":"2013","author":"Mathieu","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2017.7995254"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295701"},{"key":"ref6","article-title":"nvGraph"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3108140"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00052"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460359"},{"key":"ref10","first-page":"857","article-title":"Efficient and scalable graph pattern mining on $\\{${GPUs$\\}$}","volume-title":"Proc. 16th USENIX Symp. Oper. Syst. Des. Implementation (OSDI)","author":"Chen","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628088"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2903150.2903152"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.59"},{"key":"ref15","first-page":"45","article-title":"Qilin: Exploiting parallelism on heterogeneous multiprocessors with adaptive mapping","volume-title":"Proc. 42nd Annu. IEEE\/ACM Int. Symp. Microarchit.","author":"Luk","year":"2009"},{"key":"ref16","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Oper. Syst. Des. Implementation (OSDI)","author":"Chen","year":"2018"},{"key":"ref17","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. 14th USENIX Symp. Oper. Syst. Des. Implementation (OSDI)","author":"Zheng","year":"2020"},{"year":"2024","key":"ref18","article-title":"Introducing tvm auto-scheduler (a.k.a. ansor)"},{"key":"ref19","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1039\/C8SC04228D"},{"article-title":"Active learning literature survey","year":"2009","author":"Settles","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"volume-title":"Introduction to Algorithms","year":"2022","author":"Cormen","key":"ref23"},{"year":"2024","key":"ref24","article-title":"cuBLAS"},{"year":"2024","key":"ref25","article-title":"Intel BLAS level 3 routines."},{"year":"2024","key":"ref26","article-title":"cuSPARSE"},{"year":"2024","key":"ref27","article-title":"Intel sparse BLAS level 2 and level 3 routines."},{"year":"2024","key":"ref28","article-title":"Cutlass"},{"year":"2024","key":"ref29","article-title":"Intel oneAPI deep neural network library."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1993498.1993501"},{"year":"2024","key":"ref32","article-title":"Intel oneAPI base toolkit."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-384988-5.00006-1"},{"year":"2024","key":"ref34","article-title":"Fast N-body simulation with CUDA."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.14778\/3389133.3389137"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2827055"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2898361"},{"year":"2024","key":"ref38","article-title":"Benchmark specification"},{"article-title":"SNAP datasets: Stanford large network dataset collection","year":"2014","author":"Leskovec","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1186\/s40668-019-0032-1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1093\/mnras\/stt1154"},{"key":"ref42","article-title":"Optimizing operators with auto-scheduling."},{"year":"2024","key":"ref43","article-title":"Apache TVM"},{"article-title":"Semi-supervised classification with graph convolutional networks","year":"2016","author":"Kipf","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/11030070\/10955449.pdf?arnumber=10955449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T05:43:23Z","timestamp":1749620603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":45,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tc.2025.3558606","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"type":"print","value":"0018-9340"},{"type":"electronic","value":"1557-9956"},{"type":"electronic","value":"2326-3814"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}