{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:09:58Z","timestamp":1743131398224,"version":"3.40.3"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030727888"},{"type":"electronic","value":"9783030727895"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-72789-5_9","type":"book-chapter","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T22:48:05Z","timestamp":1616712485000},"page":"108-126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["SWIRL ++ : Evaluating Performance Models to Guide Code Transformation in Convolutional Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5052-8183","authenticated-orcid":false,"given":"Tharindu R.","family":"Patabandi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4167-4525","authenticated-orcid":false,"given":"Anand","family":"Venkat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4779-1391","authenticated-orcid":false,"given":"Rajkishore","family":"Barik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3058-7573","authenticated-orcid":false,"given":"Mary","family":"Hall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,26]]},"reference":[{"key":"9_CR1","unstructured":"NVIDIA GPU Inference Engine (2016). https:\/\/devblogs.nvidia.com\/parallelforall\/production-deep-learning-nvidia-gpu-inference-engine\/. Accessed 6 July 2020"},{"key":"9_CR2","unstructured":"Abadi, M., et al.: TensorFlow: Large-scale machine learning on heterogeneous systems (2015). http:\/\/tensorflow.org\/"},{"key":"9_CR3","unstructured":"Agarwal, A., et al.: An introduction to computational networks and the computational network toolkit. Technical Report MSR-TR-2014-112 (2014). http:\/\/research.microsoft.com\/apps\/pubs\/default.aspx?id=226641"},{"key":"9_CR4","unstructured":"Ansel, J., et al.: Opentuner: an extensible framework for program autotuning. In: International Conference on Parallel Architectures and Compilation Techniques. Edmonton, Canada (2014). http:\/\/groups.csail.mit.edu\/commit\/papers\/2014\/ansel-pact14-opentuner.pdf"},{"key":"9_CR5","unstructured":"Baghdadi, R., et al.: Tiramisu: a code optimization framework for high performance systems. arXiv preprint arXiv:1804.10694 (2018)"},{"issue":"11","key":"9_CR6","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.1109\/JPROC.2018.2841200","volume":"106","author":"P Balaprakash","year":"2018","unstructured":"Balaprakash, P., et al.: Autotuning in high-performance computing applications. Proc. IEEE 106(11), 2068\u20132083 (2018). https:\/\/doi.org\/10.1109\/JPROC.2018.2841200","journal-title":"Proc. IEEE"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Bergstra, J., et al.: Theano: a CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference (SciPy) (2010)","DOI":"10.25080\/Majora-92bf1922-003"},{"key":"9_CR8","unstructured":"Chen, C., Chame, J., Hall, M.: Combining models and guided empirical search to optimize for multiple levels of the memory hierarchy. In: International Symposium on Code Generation and Optimization. CGO 2005, pp. 111\u2013122. IEEE (2005)"},{"key":"9_CR9","unstructured":"Chen, T., et al.: Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274 (2015)"},{"key":"9_CR10","unstructured":"Chen, T., et al.: TVM: an automated end-to-end optimizing compiler for deep learning. In: 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2018), pp. 578\u2013594 (2018)"},{"key":"9_CR11","unstructured":"Chetlur, S., et al.: cuDNN: Efficient Primitives for Deep Learning. CoRR abs\/1410.0759 (2014). http:\/\/arxiv.org\/abs\/1410.0759"},{"key":"9_CR12","unstructured":"Chintala, S.: Convnet Benchmarks (2015). https:\/\/github.com\/soumith\/convnet-benchmarks. Accessed 6 July 2020"},{"key":"9_CR13","unstructured":"Collobert, R., Kavukcuoglu, K., Farabet, C.: Torch7: A MATLAB-like environment for machine learning. In: BigLearn, NIPS Workshop. No. EPFL-CONF-192376 (2011)"},{"key":"9_CR14","unstructured":"Cyphers, S., et al.: Intel\u00ae nGraph\u2122: an intermediate representation, compiler, and executor for deep learning. arXiv preprint arXiv:1801.08058 (2018)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Donadio, S., et al.: A language for the compact representation of multiple program versions. In: Workshop on Languages and Compilers for Parallel Computing (LCPC) (2005)","DOI":"10.1007\/978-3-540-69330-7_10"},{"key":"9_CR16","unstructured":"Dukhan, M.: NNPACK (2016). https:\/\/github.com\/Maratyszcza\/NNPACK. Accessed 6 July 2020"},{"key":"9_CR17","unstructured":"Google: TensorFlow XLA (2016). https:\/\/www.tensorflow.org\/xla\/. Accessed 6 July 2020"},{"key":"9_CR18","unstructured":"Google: Improving the speed of neural networks on CPUs (2011). https:\/\/research.google.com\/pubs\/pub37631.html. Accessed 6 July 2020"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Hall, M.W., Chame, J., Chen, C., Shin, J., Rudy, G., Khan, M.M.: Loop transformation recipes for code generation and auto-tuning. In: Proceedings of the 22nd International Workshop on Languages and Compilers for Parallel Computing (2009)","DOI":"10.1007\/978-3-642-13374-9_4"},{"key":"9_CR20","doi-asserted-by":"publisher","unstructured":"Hartono, A., Norris, B., Sadayappan, P.: Annotation-based empirical performance tuning using orio. In: 2009 IEEE International Symposium on Parallel Distributed Processing, pp. 1\u201311 (2009). https:\/\/doi.org\/10.1109\/IPDPS.2009.5161004","DOI":"10.1109\/IPDPS.2009.5161004"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Hartono, A., Norris, B., Sadayappan, P.: Annotation-based empirical performance tuning using Orio. In: IPDPS (2009)","DOI":"10.1109\/IPDPS.2009.5161004"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Hezaveh, Y.D., Levasseur, L.P., Marshall, P.J.: Fast automated analysis of strong gravitational lenses with convolutional neural networks. Nature 548 (2017)","DOI":"10.1038\/nature23463"},{"key":"9_CR23","unstructured":"Intel: Intel MKL-DNN. https:\/\/github.com\/01org\/mkl-dnn. Accessed 6 July 2020"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"9_CR25","doi-asserted-by":"publisher","unstructured":"Jin, L., Wang, Z., Gu, R., Yuan, C., Huang, Y.: Training large scale deep neural networks on the intel xeon phi many-core coprocessor. In: 2014 IEEE International Parallel Distributed Processing Symposium Workshops, pp. 1622\u20131630 (2014). https:\/\/doi.org\/10.1109\/IPDPSW.2014.194","DOI":"10.1109\/IPDPSW.2014.194"},{"key":"9_CR26","doi-asserted-by":"publisher","unstructured":"Khan, M., Basu, P., Rudy, G., Hall, M., Chen, C., Chame, J.: A script-based autotuning compiler system to generate high-performance CUDA code. ACM Trans. Archit. Code Optim. 9(4), 31:1\u201331:25 (2013). https:\/\/doi.org\/10.1145\/2400682.2400690","DOI":"10.1145\/2400682.2400690"},{"key":"9_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"9_CR28","doi-asserted-by":"publisher","unstructured":"Kurth, T., et al.: Deep learning at 15PF: supervised and semi-supervised classification for scientific data. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, New York, NY, pp. 7:1\u20137:11. SC 2017, ACM (2017). https:\/\/doi.org\/10.1145\/3126908.3126916","DOI":"10.1145\/3126908.3126916"},{"key":"9_CR29","unstructured":"Liu, Y., et al.: Application of deep convolutional neural networks for detecting extreme weather in climate datasets. CoRR abs\/1605.01156 (2016). http:\/\/arxiv.org\/abs\/1605.01156"},{"key":"9_CR30","doi-asserted-by":"publisher","unstructured":"Milova, E., Sveshnikova, S., Gankevich, I.: Speedup of deep neural network learning on the mic-architecture. In: 2016 International Conference on High Performance Computing Simulation (HPCS), pp. 989\u2013992 (2016). https:\/\/doi.org\/10.1109\/HPCSim.2016.7568443","DOI":"10.1109\/HPCSim.2016.7568443"},{"key":"9_CR31","doi-asserted-by":"publisher","unstructured":"Mullapudi, R.T., Adams, A., Sharlet, D., Ragan-Kelley, J., Fatahalian, K.: Automatically scheduling halide image processing pipelines. ACM Trans. Graph. 35(4), 83:1\u201383:11 (2016). https:\/\/doi.org\/10.1145\/2897824.2925952","DOI":"10.1145\/2897824.2925952"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Nelson, T., et al.: Generating efficient tensor contractions for GPUs. In: 2015 44th International Conference on Parallel Processing, pp. 969\u2013978. IEEE (2015)","DOI":"10.1109\/ICPP.2015.106"},{"key":"9_CR33","unstructured":"Palkar, S., et al: Weld: a common runtime for high performance data analytics. In: Biennial Conference on Innovative Data Systems Research (CIDR). CIDR 2017 (2017)"},{"key":"9_CR34","unstructured":"Qi, H., Sparks, E.R., Talwalkar, A.: Paleo: a performance model for deep neural networks (2016)"},{"issue":"6","key":"9_CR35","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., Paris, S., Durand, F., Amarasinghe, S.: Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines. ACM SIGPLAN Notices 48(6), 519\u2013530 (2013)","journal-title":"ACM SIGPLAN Notices"},{"key":"9_CR36","unstructured":"Rotem, N., et al.: Glow: Graph lowering compiler techniques for neural networks. arXiv preprint arXiv:1805.00907 (2018)"},{"issue":"3","key":"9_CR37","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"9_CR38","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks. CoRR abs\/1312.6229 (2013). http:\/\/arxiv.org\/abs\/1312.6229"},{"key":"9_CR39","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.matchar.2018.05.053","volume":"142","author":"C Shashank Kaira","year":"2018","unstructured":"Shashank Kaira, C., et al.: Automated correlative segmentation of large transmission x-ray microscopy (TXM) tomograms using deep learning. Mater. Characterization 142, 203\u2013210 (2018). https:\/\/doi.org\/10.1016\/j.matchar.2018.05.053","journal-title":"Mater. Characterization"},{"issue":"7587","key":"9_CR40","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016). https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"9_CR41","unstructured":"Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556 (2014)"},{"key":"9_CR42","unstructured":"Systems, N.: NEON (2016). https:\/\/github.com\/NervanaSystems\/neon. Accessed 6 July 2020"},{"key":"9_CR43","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. CoRR abs\/1409.4842 (2014). http:\/\/arxiv.org\/abs\/1409.4842"},{"key":"9_CR44","doi-asserted-by":"publisher","unstructured":"Tapus, C., I-Hsin Chung, Hollingsworth, J.K.: Active harmony: towards automated performance tuning. In: SC 2002: Proceedings of the 2002 ACM\/IEEE Conference on Supercomputing, pp. 44\u201344 (2002). https:\/\/doi.org\/10.1109\/SC.2002.10062","DOI":"10.1109\/SC.2002.10062"},{"key":"9_CR45","doi-asserted-by":"publisher","unstructured":"Truong, L., et al.: Latte: A language, compiler, and runtime for elegant and efficient deep neural networks. In: Proceedings of the 37th ACM SIGPLAN Conference on Programming Language Design and Implementation, New York, NY, pp. 209\u2013223. PLDI 2016. ACM (2016). https:\/\/doi.org\/10.1145\/2908080.2908105","DOI":"10.1145\/2908080.2908105"},{"key":"9_CR46","doi-asserted-by":"publisher","unstructured":"Venkat, A., Rusira, T., Barik, R., Hall, M., Truong, L.: SWIRL: high-performance many-core CPU code generation for deep neural networks. Int. J. High Perform. Comput. Appl. 1094342019866247. https:\/\/doi.org\/10.1177\/1094342019866247","DOI":"10.1177\/1094342019866247"},{"key":"9_CR47","unstructured":"Whaley, R.C., Dongarra, J.J.: Automatically tuned linear algebra software. In: Proceedings of the 1998 ACM\/IEEE Conference on Supercomputing, Washington, DC. SC 1998, pp. 1\u201327. IEEE Computer Society (1998). http:\/\/dl.acm.org\/citation.cfm?id=509058.509096"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Wolf, M.E., Lam, M.S.: A data locality optimizing algorithm. In: ACM SIGPLAN Notices, vol. 26, pp. 30\u201344. ACM (1991)","DOI":"10.1145\/113446.113449"},{"key":"9_CR49","doi-asserted-by":"publisher","unstructured":"Yotov, K., et al.: A comparison of empirical and model-driven optimization. In: Proceedings of the ACM SIGPLAN 2003 Conference on Programming Language Design and Implementation, New York, NY. PLDI 2003, pp. 63\u201376. ACM (2003). https:\/\/doi.org\/10.1145\/781131.781140","DOI":"10.1145\/781131.781140"},{"issue":"2","key":"9_CR50","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1109\/JPROC.2004.840444","volume":"93","author":"K Yotov","year":"2005","unstructured":"Yotov, K., et al.: Is search really necessary to generate high-performance blas? Proc. IEEE 93(2), 358\u2013386 (2005)","journal-title":"Proc. IEEE"},{"key":"9_CR51","unstructured":"Zlateski, A., Lee, K., Seung, H.S.: ZNN - A fast and scalable algorithm for training 3D convolutional networks on multi-core and many-core shared memory machines. CoRR abs\/1510.06706 (2015). http:\/\/arxiv.org\/abs\/1510.06706"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-72789-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T22:53:23Z","timestamp":1616712803000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-72789-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030727888","9783030727895"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-72789-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"26 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LCPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Languages and Compilers for Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Atlanta, GA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"lcpc2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lcpc19.cc.gatech.edu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Hotcrp","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"8","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}