{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:54:01Z","timestamp":1774454041867,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2023,5,7]],"date-time":"2023-05-07T00:00:00Z","timestamp":1683417600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,7]],"date-time":"2023-05-07T00:00:00Z","timestamp":1683417600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Key Research and Development Program of China","award":["No. 2021ZD0110202"],"award-info":[{"award-number":["No. 2021ZD0110202"]}]},{"name":"National Key Research and Development Program of China","award":["No. 2021ZD0110202"],"award-info":[{"award-number":["No. 2021ZD0110202"]}]},{"name":"National Key Research and Development Program of China","award":["No. 2021ZD0110202"],"award-info":[{"award-number":["No. 2021ZD0110202"]}]},{"name":"National Key Research and Development Program of China","award":["No. 2021ZD0110202"],"award-info":[{"award-number":["No. 2021ZD0110202"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11227-023-05298-w","type":"journal-article","created":{"date-parts":[[2023,5,7]],"date-time":"2023-05-07T16:01:10Z","timestamp":1683475270000},"page":"17419-17444","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["PCGC: a performance compact graph compiler based on multilevel fusion-splitting rules"],"prefix":"10.1007","volume":"79","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6018-0379","authenticated-orcid":false,"given":"Dong","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanqun","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanfei","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,7]]},"reference":[{"issue":"9","key":"5298_CR1","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1145\/3154484","volume":"61","author":"NP Jouppi","year":"2018","unstructured":"Jouppi NP, Young C, Patil N et al (2018) A domain-specific architecture for deep neural networks. Commun ACM 61(9):50\u201359","journal-title":"Commun ACM"},{"key":"5298_CR2","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R et al (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"5298_CR3","unstructured":"Devlin J, Chang M W, Lee K et al (2018) Bert: pre-training of deep bidirectional transformers for language understanding. Preprint http:\/\/arxiv.org\/abs\/1810.04805"},{"issue":"4","key":"5298_CR4","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","volume":"30","author":"L Floridi","year":"2020","unstructured":"Floridi L, Chiriatti M (2020) GPT-3: its nature, scope, limits, and consequences. Mind Mach 30(4):681\u2013694","journal-title":"Mind Mach"},{"key":"5298_CR5","unstructured":"Looks M, Herreshoff M, Hutchins DL et al (2017) Deep learning with dynamic computation graphs. Preprint http:\/\/arxiv.org\/abs\/1702.02181"},{"issue":"6","key":"5298_CR6","doi-asserted-by":"publisher","first-page":"1329","DOI":"10.1162\/neco_a_01497","volume":"34","author":"B Millidge","year":"2022","unstructured":"Millidge B, Tschantz A, Buckley CL (2022) Predictive coding approximates backprop along arbitrary computation graphs. Neural Comput 34(6):1329\u20131368","journal-title":"Neural Comput"},{"issue":"4","key":"5298_CR7","doi-asserted-by":"publisher","first-page":"653","DOI":"10.26599\/TST.2021.9010058","volume":"27","author":"Y Duan","year":"2022","unstructured":"Duan Y, Wang J, Ma H et al (2022) Residual convolutional graph neural network with subgraph attention pooling. Tsinghua Sci Technol 27(4):653\u2013663","journal-title":"Tsinghua Sci Technol"},{"key":"5298_CR8","doi-asserted-by":"crossref","unstructured":"Ingolfsson TM, Vero M, Wang X et al (2022) Reducing neural architecture search spaces with training-free statistics and computational graph clustering. In: Proceedings of the 19th ACM International Conference on Computing Frontiers, pp 213\u2013214","DOI":"10.1145\/3528416.3530873"},{"key":"5298_CR9","doi-asserted-by":"crossref","unstructured":"Chhabra A, Huang KC, Bacanin N et al (2022) Optimizing bag-of-tasks scheduling on cloud data centers using hybrid swarm-intelligence meta-heuristic. J Supercomput 1\u201363","DOI":"10.1007\/s11227-021-04199-0"},{"key":"5298_CR10","doi-asserted-by":"publisher","first-page":"108146","DOI":"10.1016\/j.knosys.2022.108146","volume":"240","author":"Y Liu","year":"2022","unstructured":"Liu Y, Zhang H, Xu D et al (2022) Graph transformer network with temporal kernel attention for skeleton-based action recognition. Knowl-Based Syst 240:108146","journal-title":"Knowl-Based Syst"},{"key":"5298_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2022.101585","volume":"69","author":"S Ganguly","year":"2022","unstructured":"Ganguly S, Bhowal P, Oliva D et al (2022) BLeafNet: a Bonferroni mean operator based fusion of CNN models for plant identification using leaf image classification[J]. Ecol Inform 69:101585","journal-title":"Ecol Inform"},{"key":"5298_CR12","doi-asserted-by":"crossref","unstructured":"Niu W, Guan J, Wang Y et al (2021) DNNFusion: accelerating deep neural networks execution with advanced operator fusion. In: Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, pp 883\u2013898","DOI":"10.1145\/3453483.3454083"},{"key":"5298_CR13","doi-asserted-by":"publisher","first-page":"116632","DOI":"10.1016\/j.image.2022.116632","volume":"103","author":"C Zhang","year":"2022","unstructured":"Zhang C, Feng Z (2022) Convolutional analysis operator learning for multifocus image fusion. Signal Process Image Commun 103:116632","journal-title":"Signal Process Image Commun"},{"issue":"6","key":"5298_CR14","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1145\/3140587.3062366","volume":"52","author":"S Schneider","year":"2017","unstructured":"Schneider S, Wu KL (2017) Low-synchronization, mostly lock-free, elastic scheduling for streaming runtimes. Acm Sigplan Notices 52(6):648\u2013661","journal-title":"Acm Sigplan Notices"},{"issue":"1","key":"5298_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.14778\/3151113.3151114","volume":"11","author":"P Menon","year":"2017","unstructured":"Menon P, Mowry TC, Pavlo A (2017) Relaxed operator fusion for in-memory databases. Proc Vldb Endow 11(1):1\u201313","journal-title":"Proc Vldb Endow"},{"key":"5298_CR16","unstructured":"Chen T, Moreau T, Jiang Z et al (2018) {TVM}: An automated {End-to-End} optimizing compiler for deep learning. In: 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18), pp 578\u2013594"},{"issue":"6","key":"5298_CR17","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1145\/2499370.2462176","volume":"48","author":"J Ragan-Kelley","year":"2013","unstructured":"Ragan-Kelley J, Barnes C, Adams A et al (2013) Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines. Acm Sigplan Notices 48(6):519\u2013530","journal-title":"Acm Sigplan Notices"},{"issue":"5","key":"5298_CR18","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MM.2019.2928962","volume":"39","author":"T Moreau","year":"2019","unstructured":"Moreau T, Chen T, Vega L et al (2019) A hardware\u2013software blueprint for flexible deep learning specialization. IEEE Micro 39(5):8\u201316","journal-title":"IEEE Micro"},{"key":"5298_CR19","first-page":"27","volume":"1","author":"Z Jia","year":"2019","unstructured":"Jia Z, Thomas J, Warszawski T et al (2019) Optimizing DNN computation with relaxed graph substitutions. Proc Mach Learn Syst 1:27\u201339","journal-title":"Proc Mach Learn Syst"},{"key":"5298_CR20","doi-asserted-by":"crossref","unstructured":"Jia Z, Padon O, Thomas J et al (2019) TASO: optimizing deep learning computation with automatic generation of graph substitutions. In: Proceedings of the 27th ACM Symposium on Operating Systems Principles, pp 47\u201362","DOI":"10.1145\/3341301.3359630"},{"key":"5298_CR21","unstructured":"Ma L, Xie Z, Yang Z et al (2020) Rammer: enabling holistic deep learning compiler optimizations with {rTasks}. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pp 881\u2013897"},{"key":"5298_CR22","first-page":"1","volume":"4","author":"J Zhao","year":"2022","unstructured":"Zhao J, Gao X, Xia R et al (2022) Apollo: automatic partition-based operator fusion through layer by layer optimization. Proc Mach Learn Syst 4:1\u201319","journal-title":"Proc Mach Learn Syst"},{"key":"5298_CR23","first-page":"167","volume":"3","author":"Y Ding","year":"2021","unstructured":"Ding Y, Zhu L, Jia Z et al (2021) Ios: inter-operator scheduler for CNN acceleration. Proc Mach Learn Syst 3:167\u2013180","journal-title":"Proc Mach Learn Syst"},{"key":"5298_CR24","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1023\/B:STCO.0000035301.49549.88","volume":"14","author":"AJ Smola","year":"2004","unstructured":"Smola AJ, Sch\u00f6lkopf B (2004) A tutorial on support vector regression. Stat Comput 14:199\u2013222","journal-title":"Stat Comput"},{"key":"5298_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"5298_CR26","unstructured":"Chetlur S, Woolley C, Vandermersch P et al (2014) cudnn: efficient primitives for deep learning. Preprint http:\/\/arxiv.org\/abs\/1410.0759"},{"key":"5298_CR27","unstructured":"Vanholder H (2016) Efficient inference with tensorrt. In: GPU Technology Conference, vol 1, p 2"},{"key":"5298_CR28","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"5298_CR29","doi-asserted-by":"crossref","unstructured":"Koonce B (2021) ResNet 34. Convolutional neural networks with swift for tensorflow, Apress, Berkeley, CA, pp 51\u201361","DOI":"10.1007\/978-1-4842-6168-2_5"},{"key":"5298_CR30","unstructured":"Sabne A (2020) Xla: compiling machine learning for peak performance"},{"key":"5298_CR31","doi-asserted-by":"crossref","unstructured":"Zhao J, Li B, Nie W et al (2021) AKG: automatic kernel generation for neural processing units using polyhedral transformations. In: Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, pp 1233\u20131248","DOI":"10.1145\/3453483.3454106"},{"key":"5298_CR32","unstructured":"Zheng L, Jia C, Sun M et al (2020) Ansor: generating {High-Performance} tensor programs for deep learning. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pp 863\u2013879"},{"key":"5298_CR33","doi-asserted-by":"crossref","unstructured":"Barrachina S, Castillo M, Igual FD et al (2008) Evaluation and tuning of the level 3 CUBLAS for graphics processors. In: 2008 IEEE International Symposium on Parallel and Distributed Processing, IEEE, pp 1\u20138","DOI":"10.1109\/IPDPS.2008.4536485"},{"key":"5298_CR34","unstructured":"Parmar N, Vaswani A, Uszkoreit J et al (2018) Image transformer. In: International Conference on Machine Learning, PMLR, pp 4055\u20134064"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05298-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-023-05298-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05298-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T15:21:00Z","timestamp":1693408860000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-023-05298-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,7]]},"references-count":34,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["5298"],"URL":"https:\/\/doi.org\/10.1007\/s11227-023-05298-w","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,7]]},"assertion":[{"value":"12 April 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors disclosed no relevant relationships.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Written informed consent was obtained from all the participants prior to the enrollment (or for the publication) of this study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}