{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T04:02:52Z","timestamp":1793937772806,"version":"4.8.0"},"publisher-location":"New York, NY, USA","reference-count":138,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSERC grant"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,28]]},"DOI":"10.1145\/3613424.3614248","type":"proceedings-article","created":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T12:22:15Z","timestamp":1702038135000},"page":"1364-1380","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Grape: Practical and Efficient Graphed Execution for Dynamic Deep Neural Networks on GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1999-2359","authenticated-orcid":false,"given":"Bojian","family":"Zheng","sequence":"first","affiliation":[{"name":"University of Toronto \/ CentML \/ Vector Institute, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9298-6254","authenticated-orcid":false,"given":"Cody Hao","family":"Yu","sequence":"additional","affiliation":[{"name":"Amazon, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2133-7943","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9801-6080","authenticated-orcid":false,"given":"Yaoyao","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Toronto \/ CentML \/ Vector Institute, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8723-451X","authenticated-orcid":false,"given":"Yizhi","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-840X","authenticated-orcid":false,"given":"Yida","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3839-0919","authenticated-orcid":false,"given":"Gennady","family":"Pekhimenko","sequence":"additional","affiliation":[{"name":"University of Toronto \/ CentML \/ Vector Institute, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,12,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Wilson Wai\u00a0Lun Fung, and Timothy\u00a0G. Rogers","author":"Aamodt M.","year":"2018","unstructured":"Tor\u00a0 M. Aamodt , Wilson Wai\u00a0Lun Fung, and Timothy\u00a0G. Rogers . 2018 . General-Purpose Graphics Processor Architectures. Morgan & Claypool Publishers . Tor\u00a0M. Aamodt, Wilson Wai\u00a0Lun Fung, and Timothy\u00a0G. Rogers. 2018. General-Purpose Graphics Processor Architectures. Morgan & Claypool Publishers."},{"key":"e_1_3_2_1_2_1","volume-title":"TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi , Paul Barham , Jianmin Chen , Zhifeng Chen , Andy Davis , Jeffrey Dean , Matthieu Devin , Sanjay Ghemawat , Geoffrey Irving , Michael Isard , Manjunath Kudlur , Josh Levenberg , Rajat Monga , Sherry Moore , Derek\u00a0Gordon Murray , Benoit Steiner , Paul\u00a0 A. Tucker , Vijay Vasudevan , Pete Warden , Martin Wicke , Yuan Yu , and Xiaoqiang Zheng . 2016 . TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016 , Savannah, GA, USA , November 2-4, 2016, Kimberly Keeton and Timothy Roscoe (Eds.). USENIX Association, 265\u2013283. https:\/\/www.usenix.org\/conference\/osdi16\/technical-sessions\/presentation\/abadi Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek\u00a0Gordon Murray, Benoit Steiner, Paul\u00a0A. Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A System for Large-Scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, Savannah, GA, USA, November 2-4, 2016, Kimberly Keeton and Timothy Roscoe (Eds.). USENIX Association, 265\u2013283. https:\/\/www.usenix.org\/conference\/osdi16\/technical-sessions\/presentation\/abadi"},{"key":"e_1_3_2_1_3_1","volume-title":"AMD Ryzen\u2122 Threadripper\u2122 2920X Drivers & Support. https:\/\/www.amd.com\/en\/support\/cpu\/amd-ryzen-processors\/amd-ryzen-threadripper-processors\/amd-ryzen-threadripper-2920x Accessed on","author":"AMD.","year":"2023","unstructured":"AMD. 2022. AMD Ryzen\u2122 Threadripper\u2122 2920X Drivers & Support. https:\/\/www.amd.com\/en\/support\/cpu\/amd-ryzen-processors\/amd-ryzen-threadripper-processors\/amd-ryzen-threadripper-2920x Accessed on April 28 2023 . AMD. 2022. AMD Ryzen\u2122 Threadripper\u2122 2920X Drivers & Support. https:\/\/www.amd.com\/en\/support\/cpu\/amd-ryzen-processors\/amd-ryzen-threadripper-processors\/amd-ryzen-threadripper-2920x Accessed on April 28 2023."},{"key":"e_1_3_2_1_4_1","unstructured":"AMD. 2023. Graph Management. https:\/\/rocm.docs.amd.com\/projects\/HIP\/en\/docs-5.6.0\/.doxygen\/docBin\/html\/group___graph.html#graph-management  AMD. 2023. Graph Management. https:\/\/rocm.docs.amd.com\/projects\/HIP\/en\/docs-5.6.0\/.doxygen\/docBin\/html\/group___graph.html#graph-management"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016(JMLR Workshop and Conference Proceedings, Vol.\u00a048)","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei , Sundaram Ananthanarayanan , Rishita Anubhai , Jingliang Bai , Eric Battenberg , Carl Case , Jared Casper , Bryan Catanzaro , Jingdong Chen , Mike Chrzanowski , Adam Coates , Greg Diamos , Erich Elsen , Jesse\u00a0 H. Engel , Linxi Fan , Christopher Fougner , Awni\u00a0 Y. Hannun , Billy Jun , Tony Han , Patrick LeGresley , Xiangang Li , Libby Lin , Sharan Narang , Andrew\u00a0 Y. Ng , Sherjil Ozair , Ryan Prenger , Sheng Qian , Jonathan Raiman , Sanjeev Satheesh , David Seetapun , Shubho Sengupta , Chong Wang , Yi Wang , Zhiqian Wang , Bo Xiao , Yan Xie , Dani Yogatama , Jun Zhan , and Zhenyao Zhu . 2016 . Deep Speech 2: End-to-End Speech Recognition in English and Mandarin . In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016(JMLR Workshop and Conference Proceedings, Vol.\u00a048) , Maria-Florina Balcan and Kilian\u00a0Q. Weinberger (Eds.). JMLR.org, 173\u2013182. http:\/\/proceedings.mlr.press\/v48\/amodei16.html Dario Amodei, Sundaram Ananthanarayanan, Rishita Anubhai, Jingliang Bai, Eric Battenberg, Carl Case, Jared Casper, Bryan Catanzaro, Jingdong Chen, Mike Chrzanowski, Adam Coates, Greg Diamos, Erich Elsen, Jesse\u00a0H. Engel, Linxi Fan, Christopher Fougner, Awni\u00a0Y. Hannun, Billy Jun, Tony Han, Patrick LeGresley, Xiangang Li, Libby Lin, Sharan Narang, Andrew\u00a0Y. Ng, Sherjil Ozair, Ryan Prenger, Sheng Qian, Jonathan Raiman, Sanjeev Satheesh, David Seetapun, Shubho Sengupta, Chong Wang, Yi Wang, Zhiqian Wang, Bo Xiao, Yan Xie, Dani Yogatama, Jun Zhan, and Zhenyao Zhu. 2016. Deep Speech 2: End-to-End Speech Recognition in English and Mandarin. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016(JMLR Workshop and Conference Proceedings, Vol.\u00a048), Maria-Florina Balcan and Kilian\u00a0Q. Weinberger (Eds.). JMLR.org, 173\u2013182. http:\/\/proceedings.mlr.press\/v48\/amodei16.html"},{"key":"e_1_3_2_1_6_1","unstructured":"Muralidhar Andoorveedu Zhanda Zhu Bojian Zheng and Gennady Pekhimenko. 2022. Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction. In Advances in Neural Information Processing Systems Alice\u00a0H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=xqyEG7EhTZ  Muralidhar Andoorveedu Zhanda Zhu Bojian Zheng and Gennady Pekhimenko. 2022. Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction. In Advances in Neural Information Processing Systems Alice\u00a0H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=xqyEG7EhTZ"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/197405.197406"},{"key":"e_1_3_2_1_8_1","volume-title":"Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski , Yuhao Zhou , Abdelrahman Mohamed , and Michael Auli . 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations . In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates , Inc ., 12449\u201312460. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/ 2020 \/file\/92d1e1eb1cd6f9fba3227870bb6d7f07-Paper.pdf Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates, Inc., 12449\u201312460. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/92d1e1eb1cd6f9fba3227870bb6d7f07-Paper.pdf"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661197"},{"key":"e_1_3_2_1_10_1","volume-title":"2021 2020 Deep Learning Benchmarks Comparison: NVIDIA RTX 3090 vs NVIDIA A100 40 GB (PCIe). https:\/\/bizon-tech.com\/gpu-benchmarks\/NVIDIA-RTX-3090-vs-NVIDIA-A100-40-GB-(PCIe)\/579vs592 Accessed on","author":"BIZON.","year":"2023","unstructured":"BIZON. 2023. 2021 2020 Deep Learning Benchmarks Comparison: NVIDIA RTX 3090 vs NVIDIA A100 40 GB (PCIe). https:\/\/bizon-tech.com\/gpu-benchmarks\/NVIDIA-RTX-3090-vs-NVIDIA-A100-40-GB-(PCIe)\/579vs592 Accessed on April 28 2023 . BIZON. 2023. 2021 2020 Deep Learning Benchmarks Comparison: NVIDIA RTX 3090 vs NVIDIA A100 40 GB (PCIe). https:\/\/bizon-tech.com\/gpu-benchmarks\/NVIDIA-RTX-3090-vs-NVIDIA-A100-40-GB-(PCIe)\/579vs592 Accessed on April 28 2023."},{"key":"e_1_3_2_1_11_1","volume-title":"Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates","author":"Brown Tom","year":"1877","unstructured":"Tom Brown , Benjamin Mann , Nick Ryder , Melanie Subbiah , Jared\u00a0 D Kaplan , Prafulla Dhariwal , Arvind Neelakantan , Pranav Shyam , Girish Sastry , Amanda Askell , Sandhini Agarwal , Ariel Herbert-Voss , Gretchen Krueger , Tom Henighan , Rewon Child , Aditya Ramesh , Daniel Ziegler , Jeffrey Wu , Clemens Winter , Chris Hesse , Mark Chen , Eric Sigler , Mateusz Litwin , Scott Gray , Benjamin Chess , Jack Clark , Christopher Berner , Sam McCandlish , Alec Radford , Ilya Sutskever , and Dario Amodei . 2020. Language Models are Few-Shot Learners . In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates , Inc ., 1877 \u20131901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates, Inc., 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_12_1","volume-title":"https:\/\/docs.centml.ai\/deepview\/index.html Accessed on September 18th","author":"DeepView ML.","year":"2023","unstructured":"Cent ML. 2023. CentML DeepView . https:\/\/docs.centml.ai\/deepview\/index.html Accessed on September 18th , 2023 . CentML. 2023. CentML DeepView. https:\/\/docs.centml.ai\/deepview\/index.html Accessed on September 18th, 2023."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18)","author":"Chang Bo","year":"2018","unstructured":"Bo Chang , Lili Meng , Eldad Haber , Lars Ruthotto , David Begert , and Elliot Holtham . 2018 . Reversible Architectures for Arbitrarily Deep Residual Neural Networks . In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18) , the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA , February 2-7, 2018, Sheila\u00a0A. McIlraith and Kilian\u00a0Q. Weinberger (Eds.). AAAI Press, 2811\u20132818. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16517 Bo Chang, Lili Meng, Eldad Haber, Lars Ruthotto, David Begert, and Elliot Holtham. 2018. Reversible Architectures for Arbitrarily Deep Residual Neural Networks. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018, Sheila\u00a0A. McIlraith and Kilian\u00a0Q. Weinberger (Eds.). AAAI Press, 2811\u20132818. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16517"},{"key":"e_1_3_2_1_14_1","volume-title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen , Thierry Moreau , Ziheng Jiang , Lianmin Zheng , Eddie\u00a0 Q. Yan , Haichen Shen , Meghan Cowan , Leyuan Wang , Yuwei Hu , Luis Ceze , Carlos Guestrin , and Arvind Krishnamurthy . 2018 . TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018 , Carlsbad, CA, USA , October 8-10, 2018, Andrea\u00a0C. Arpaci-Dusseau and Geoff Voelker (Eds.). USENIX Association, 578\u2013594. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie\u00a0Q. Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018, Carlsbad, CA, USA, October 8-10, 2018, Andrea\u00a0C. Arpaci-Dusseau and Geoff Voelker (Eds.). USENIX Association, 578\u2013594. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen"},{"key":"e_1_3_2_1_15_1","volume-title":"Training Deep Nets with Sublinear Memory Cost. CoRR abs\/1604.06174","author":"Chen Tianqi","year":"2016","unstructured":"Tianqi Chen , Bing Xu , Chiyuan Zhang , and Carlos Guestrin . 2016. Training Deep Nets with Sublinear Memory Cost. CoRR abs\/1604.06174 ( 2016 ). arXiv:1604.06174http:\/\/arxiv.org\/abs\/1604.06174 Tianqi Chen, Bing Xu, Chiyuan Zhang, and Carlos Guestrin. 2016. Training Deep Nets with Sublinear Memory Cost. CoRR abs\/1604.06174 (2016). arXiv:1604.06174http:\/\/arxiv.org\/abs\/1604.06174"},{"key":"e_1_3_2_1_16_1","volume-title":"cuDNN: Efficient Primitives for Deep Learning. CoRR abs\/1410.0759","author":"Chetlur Sharan","year":"2014","unstructured":"Sharan Chetlur , Cliff Woolley , Philippe Vandermersch , Jonathan Cohen , John Tran , Bryan Catanzaro , and Evan Shelhamer . 2014. cuDNN: Efficient Primitives for Deep Learning. CoRR abs\/1410.0759 ( 2014 ). arXiv:1410.0759http:\/\/arxiv.org\/abs\/1410.0759 Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cuDNN: Efficient Primitives for Deep Learning. CoRR abs\/1410.0759 (2014). arXiv:1410.0759http:\/\/arxiv.org\/abs\/1410.0759"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00080"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352020.3352024"},{"key":"e_1_3_2_1_19_1","volume-title":"likely, unlikely (since C++20). https:\/\/en.cppreference.com\/w\/cpp\/language\/attributes\/likely Accessed on","year":"2023","unstructured":"cppreference.com. 2022. C++ attribute : likely, unlikely (since C++20). https:\/\/en.cppreference.com\/w\/cpp\/language\/attributes\/likely Accessed on April 28 2023 . cppreference.com. 2022. C++ attribute: likely, unlikely (since C++20). https:\/\/en.cppreference.com\/w\/cpp\/language\/attributes\/likely Accessed on April 28 2023."},{"key":"e_1_3_2_1_20_1","volume-title":"Intel Xeon 8273CL specifications. https:\/\/www.cpu-world.com\/CPUs\/Xeon\/Intel-Xeon%208273CL.html Accessed on","author":"World CPU","year":"2023","unstructured":"CPU World . 2023. Intel Xeon 8273CL specifications. https:\/\/www.cpu-world.com\/CPUs\/Xeon\/Intel-Xeon%208273CL.html Accessed on April 28 2023 . CPU World. 2023. Intel Xeon 8273CL specifications. https:\/\/www.cpu-world.com\/CPUs\/Xeon\/Intel-Xeon%208273CL.html Accessed on April 28 2023."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575702"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835936"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407857"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of Machine Learning and Systems 2021","author":"Fegade Pratik","year":"2021","unstructured":"Pratik Fegade , Tianqi Chen , Phillip\u00a0 B. Gibbons , and Todd\u00a0 C. Mowry . 2021 . Cortex: A Compiler for Recursive Deep Learning Models . In Proceedings of Machine Learning and Systems 2021 , MLSys 2021, virtual, April 5-9, 2021, Alex Smola, Alex Dimakis, and Ion Stoica (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/ 2021\/hash\/182be0c5cdcd5072bb1864cdee4d3d6e-Abstract.html Pratik Fegade, Tianqi Chen, Phillip\u00a0B. Gibbons, and Todd\u00a0C. Mowry. 2021. Cortex: A Compiler for Recursive Deep Learning Models. In Proceedings of Machine Learning and Systems 2021, MLSys 2021, virtual, April 5-9, 2021, Alex Smola, Alex Dimakis, and Ion Stoica (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/2021\/hash\/182be0c5cdcd5072bb1864cdee4d3d6e-Abstract.html"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of Machine Learning and Systems 2022","author":"Fegade Pratik","year":"2022","unstructured":"Pratik Fegade , Tianqi Chen , Phillip\u00a0 B. Gibbons , and Todd\u00a0 C. Mowry . 2022 . The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Padding . In Proceedings of Machine Learning and Systems 2022 , MLSys 2022, Santa Clara, CA, USA, August 29 - September 1, 2022, Diana Marculescu, Yuejie Chi, and Carole-Jean Wu (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/2022\/hash\/d3d9446802a44259755d38e6d163e820-Abstract.html Pratik Fegade, Tianqi Chen, Phillip\u00a0B. Gibbons, and Todd\u00a0C. Mowry. 2022. The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Padding. In Proceedings of Machine Learning and Systems 2022, MLSys 2022, Santa Clara, CA, USA, August 29 - September 1, 2022, Diana Marculescu, Yuejie Chi, and Carole-Jean Wu (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/2022\/hash\/d3d9446802a44259755d38e6d163e820-Abstract.html"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3576933"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749714"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.30"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1543753.1543756"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.35111\/17gk-bn40"},{"key":"e_1_3_2_1_31_1","volume-title":"Run Length Encoding and Decoding. https:\/\/www.geeksforgeeks.org\/run-length-encoding\/ Accessed on","year":"2023","unstructured":"GeeksforGeeks. 2022. Run Length Encoding and Decoding. https:\/\/www.geeksforgeeks.org\/run-length-encoding\/ Accessed on April 28 2023 . GeeksforGeeks. 2022. Run Length Encoding and Decoding. https:\/\/www.geeksforgeeks.org\/run-length-encoding\/ Accessed on April 28 2023."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of Machine Learning and Systems 2021","author":"Gleeson James","year":"2021","unstructured":"James Gleeson , Moshe Gabel , Gennady Pekhimenko , Eyal de Lara , Srivatsan Krishnan , and Vijay\u00a0Janapa Reddi . 2021 . RL-Scope: Cross-stack Profiling for Deep Reinforcement Learning Workloads . In Proceedings of Machine Learning and Systems 2021 , MLSys 2021, virtual, April 5-9, 2021, Alex Smola, Alex Dimakis, and Ion Stoica (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/ 2021\/hash\/676638b91bc90529e09b22e58abb01d6-Abstract.html James Gleeson, Moshe Gabel, Gennady Pekhimenko, Eyal de Lara, Srivatsan Krishnan, and Vijay\u00a0Janapa Reddi. 2021. RL-Scope: Cross-stack Profiling for Deep Reinforcement Learning Workloads. In Proceedings of Machine Learning and Systems 2021, MLSys 2021, virtual, April 5-9, 2021, Alex Smola, Alex Dimakis, and Ion Stoica (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2021\/hash\/676638b91bc90529e09b22e58abb01d6-Abstract.html"},{"key":"e_1_3_2_1_33_1","volume-title":"The Reversible Residual Network: Backpropagation Without Storing Activations. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Gomez N.","year":"2017","unstructured":"Aidan\u00a0 N. Gomez , Mengye Ren , Raquel Urtasun , and Roger\u00a0 B. Grosse . 2017 . The Reversible Residual Network: Backpropagation Without Storing Activations. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017 , December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna\u00a0M. Wallach, Rob Fergus, S.\u00a0V.\u00a0N. Vishwanathan, and Roman Garnett (Eds.). 2214\u20132224. https:\/\/proceedings.neurips.cc\/paper\/ 2017\/hash\/f9be311e65d81a9ad8150a60844bb94c-Abstract.html Aidan\u00a0N. Gomez, Mengye Ren, Raquel Urtasun, and Roger\u00a0B. Grosse. 2017. The Reversible Residual Network: Backpropagation Without Storing Activations. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna\u00a0M. Wallach, Rob Fergus, S.\u00a0V.\u00a0N. Vishwanathan, and Roman Garnett (Eds.). 2214\u20132224. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/f9be311e65d81a9ad8150a60844bb94c-Abstract.html"},{"key":"e_1_3_2_1_34_1","unstructured":"Google Cloud. 2023. Accelerator-optimized machine family. Accessed on April 28 2023.  Google Cloud. 2023. Accelerator-optimized machine family. Accessed on April 28 2023."},{"key":"e_1_3_2_1_35_1","unstructured":"Alan Gray. 2019. Getting Started with CUDA Graphs. https:\/\/developer.nvidia.com\/blog\/cuda-graphs\/  Alan Gray. 2019. Getting Started with CUDA Graphs. https:\/\/developer.nvidia.com\/blog\/cuda-graphs\/"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582018"},{"key":"e_1_3_2_1_38_1","volume-title":"Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. In 4th International Conference on Learning Representations, ICLR","author":"Han Song","year":"2016","unstructured":"Song Han , Huizi Mao , and William\u00a0 J. Dally . 2016 . Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico , May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds .). http:\/\/arxiv.org\/abs\/1510.00149 Song Han, Huizi Mao, and William\u00a0J. Dally. 2016. Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1510.00149"},{"key":"e_1_3_2_1_39_1","unstructured":"Mark Harris and Ian Buck. 2005. Chapter 34. GPU Flow-Control Idioms. https:\/\/developer.nvidia.com\/gpugems\/gpugems2\/part-iv-general-purpose-computation-gpus-primer\/chapter-34-gpu-flow-control-idioms  Mark Harris and Ian Buck. 2005. Chapter 34. GPU Flow-Control Idioms. https:\/\/developer.nvidia.com\/gpugems\/gpugems2\/part-iv-general-purpose-computation-gpus-primer\/chapter-34-gpu-flow-control-idioms"},{"key":"e_1_3_2_1_40_1","unstructured":"Horace He. 2022. PyTorch 2.0: Dynamic Shapes Support. https:\/\/youtu.be\/rn-kJQ-7JmQ  Horace He. 2022. PyTorch 2.0: Dynamic Shapes Support. https:\/\/youtu.be\/rn-kJQ-7JmQ"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_42_1","volume-title":"Computer Architecture","author":"Hennessy L.","unstructured":"John\u00a0 L. Hennessy and David\u00a0 A. Patterson . 2017. Computer Architecture , Sixth Edition : A Quantitative Approach (6th ed.). Morgan Kaufmann Publishers Inc . John\u00a0L. Hennessy and David\u00a0A. Patterson. 2017. Computer Architecture, Sixth Edition: A Quantitative Approach (6th ed.). Morgan Kaufmann Publishers Inc."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_44_1","article-title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","volume":"18","author":"Hubara Itay","year":"2017","unstructured":"Itay Hubara , Matthieu Courbariaux , Daniel Soudry , Ran El-Yaniv , and Yoshua Bengio . 2017 . Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations . Journal of Machine Learning Research 18 (2017), 187:1\u2013187:30. http:\/\/jmlr.org\/papers\/v18\/16-456.html Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2017. Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. Journal of Machine Learning Research 18 (2017), 187:1\u2013187:30. http:\/\/jmlr.org\/papers\/v18\/16-456.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.877947"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00070"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of Machine Learning and Systems 2020","author":"Jain Paras","year":"2020","unstructured":"Paras Jain , Ajay Jain , Aniruddha Nrusimha , Amir Gholami , Pieter Abbeel , Kurt Keutzer , Ion Stoica , and Joseph Gonzalez . 2020 . Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization . In Proceedings of Machine Learning and Systems 2020 , MLSys 2020, Austin, TX, USA , March 2-4, 2020, Inderjit\u00a0S. Dhillon, Dimitris\u00a0S. Papailiopoulos, and Vivienne Sze (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/book\/320.pdf Paras Jain, Ajay Jain, Aniruddha Nrusimha, Amir Gholami, Pieter Abbeel, Kurt Keutzer, Ion Stoica, and Joseph Gonzalez. 2020. Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization. In Proceedings of Machine Learning and Systems 2020, MLSys 2020, Austin, TX, USA, March 2-4, 2020, Inderjit\u00a0S. Dhillon, Dimitris\u00a0S. Papailiopoulos, and Vivienne Sze (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/book\/320.pdf"},{"key":"e_1_3_2_1_48_1","volume-title":"Main Memory: DDR4 and DDR5 SDRAM. https:\/\/www.jedec.org\/category\/technology-focus-area\/main-memory-ddr3-ddr4-sdram","author":"JEDEC.","year":"2017","unstructured":"JEDEC. 2017 . Main Memory: DDR4 and DDR5 SDRAM. https:\/\/www.jedec.org\/category\/technology-focus-area\/main-memory-ddr3-ddr4-sdram JEDEC. 2017. Main Memory: DDR4 and DDR5 SDRAM. https:\/\/www.jedec.org\/category\/technology-focus-area\/main-memory-ddr3-ddr4-sdram"},{"key":"e_1_3_2_1_49_1","unstructured":"JEDEC. 2021. GRAPHICS DOUBLE DATA RATE 6 (GDDR6) SGRAM STANDARD. https:\/\/www.jedec.org\/standards-documents\/docs\/jesd250c  JEDEC. 2021. GRAPHICS DOUBLE DATA RATE 6 (GDDR6) SGRAM STANDARD. https:\/\/www.jedec.org\/standards-documents\/docs\/jesd250c"},{"key":"e_1_3_2_1_50_1","unstructured":"JEDEC. 2021. HIGH BANDWIDTH MEMORY (HBM) DRAM. https:\/\/www.jedec.org\/standards-documents\/docs\/jesd235a  JEDEC. 2021. HIGH BANDWIDTH MEMORY (HBM) DRAM. https:\/\/www.jedec.org\/standards-documents\/docs\/jesd235a"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"e_1_3_2_1_52_1","volume-title":"Arbitor: A Numerically Accurate Hardware Emulation Tool for DNN Accelerators. In 2023 USENIX Annual Technical Conference, USENIX ATC 2023","author":"Jiang Chenhao","year":"2023","unstructured":"Chenhao Jiang , Anand Jayarajan , Hao Lu , and Gennady Pekhimenko . 2023 . Arbitor: A Numerically Accurate Hardware Emulation Tool for DNN Accelerators. In 2023 USENIX Annual Technical Conference, USENIX ATC 2023 , Boston, MA, USA , July 10-12, 2023, Julia Lawall and Dan Williams (Eds.). USENIX Association, 519\u2013536. https:\/\/www.usenix.org\/conference\/atc23\/presentation\/jiang-chenhao Chenhao Jiang, Anand Jayarajan, Hao Lu, and Gennady Pekhimenko. 2023. Arbitor: A Numerically Accurate Hardware Emulation Tool for DNN Accelerators. In 2023 USENIX Annual Technical Conference, USENIX ATC 2023, Boston, MA, USA, July 10-12, 2023, Julia Lawall and Dan Williams (Eds.). USENIX Association, 519\u2013536. https:\/\/www.usenix.org\/conference\/atc23\/presentation\/jiang-chenhao"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.89"},{"key":"e_1_3_2_1_54_1","volume-title":"Dynamic Tensor Rematerialization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Vfs_2RnOD0H","author":"Kirisame Marisa","year":"2021","unstructured":"Marisa Kirisame , Steven Lyubomirsky , Altan Haan , Jennifer Brennan , Mike He , Jared Roesch , Tianqi Chen , and Zachary Tatlock . 2021 . Dynamic Tensor Rematerialization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Vfs_2RnOD0H Marisa Kirisame, Steven Lyubomirsky, Altan Haan, Jennifer Brennan, Mike He, Jared Roesch, Tianqi Chen, and Zachary Tatlock. 2021. Dynamic Tensor Rematerialization. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Vfs_2RnOD0H"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2004.1310763"},{"key":"e_1_3_2_1_56_1","unstructured":"Ronny\u00a0M. Krashinsky. 2011. Temporal SIMT execution optimization through elimination of redundant operations. https:\/\/patents.google.com\/patent\/US9830156B2  Ronny\u00a0M. Krashinsky. 2011. Temporal SIMT execution optimization through elimination of redundant operations. https:\/\/patents.google.com\/patent\/US9830156B2"},{"key":"e_1_3_2_1_57_1","unstructured":"Andrey Kuzmin Mart\u00a0Van Baalen Yuwei Ren Markus Nagel Jorn Peters and Tijmen Blankevoort. 2022. FP8 Quantization: The Power of the Exponent. In Advances in Neural Information Processing Systems Alice\u00a0H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=H3Gv7XEGzYV  Andrey Kuzmin Mart\u00a0Van Baalen Yuwei Ren Markus Nagel Jorn Peters and Tijmen Blankevoort. 2022. FP8 Quantization: The Power of the Exponent. In Advances in Neural Information Processing Systems Alice\u00a0H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=H3Gv7XEGzYV"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO53902.2022.9741270"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201383"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_62_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020","author":"Ma Lingxiao","year":"2020","unstructured":"Lingxiao Ma , Zhiqiang Xie , Zhi Yang , Jilong Xue , Youshan Miao , Wei Cui , Wenxiang Hu , Fan Yang , Lintao Zhang , and Lidong Zhou . 2020 . Rammer: Enabling Holistic Deep Learning Compiler Optimizations with rTasks . In 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020 , Virtual Event , November 4-6, 2020. USENIX Association, 881\u2013897. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/ma Lingxiao Ma, Zhiqiang Xie, Zhi Yang, Jilong Xue, Youshan Miao, Wei Cui, Wenxiang Hu, Fan Yang, Lintao Zhang, and Lidong Zhou. 2020. Rammer: Enabling Holistic Deep Learning Compiler Optimizations with rTasks. In 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020, Virtual Event, November 4-6, 2020. USENIX Association, 881\u2013897. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/ma"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/225830.225965"},{"key":"e_1_3_2_1_64_1","volume-title":"Proceedings of Machine Learning and Systems 2020","author":"Mattson Peter","year":"2020","unstructured":"Peter Mattson , Christine Cheng , Gregory\u00a0 F. Diamos , Cody Coleman , Paulius Micikevicius , David\u00a0 A. Patterson , Hanlin Tang , Gu-Yeon Wei , Peter Bailis , Victor Bittorf , David Brooks , Dehao Chen , Debo Dutta , Udit Gupta , Kim\u00a0 M. Hazelwood , Andy Hock , Xinyuan Huang , Daniel Kang , David Kanter , Naveen Kumar , Jeffery Liao , Deepak Narayanan , Tayo Oguntebi , Gennady Pekhimenko , Lillian Pentecost , Vijay\u00a0Janapa Reddi , Taylor Robie , Tom\u00a0 St. John , Carole-Jean Wu , Lingjie Xu , Cliff Young , and Matei Zaharia . 2020 . MLPerf Training Benchmark . In Proceedings of Machine Learning and Systems 2020 , MLSys 2020, Austin, TX, USA , March 2-4, 2020, Inderjit\u00a0S. Dhillon, Dimitris\u00a0S. Papailiopoulos, and Vivienne Sze (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2020\/hash\/411e39b117e885341f25efb8912945f7-Abstract.html Peter Mattson, Christine Cheng, Gregory\u00a0F. Diamos, Cody Coleman, Paulius Micikevicius, David\u00a0A. Patterson, Hanlin Tang, Gu-Yeon Wei, Peter Bailis, Victor Bittorf, David Brooks, Dehao Chen, Debo Dutta, Udit Gupta, Kim\u00a0M. Hazelwood, Andy Hock, Xinyuan Huang, Daniel Kang, David Kanter, Naveen Kumar, Jeffery Liao, Deepak Narayanan, Tayo Oguntebi, Gennady Pekhimenko, Lillian Pentecost, Vijay\u00a0Janapa Reddi, Taylor Robie, Tom\u00a0St. John, Carole-Jean Wu, Lingjie Xu, Cliff Young, and Matei Zaharia. 2020. MLPerf Training Benchmark. In Proceedings of Machine Learning and Systems 2020, MLSys 2020, Austin, TX, USA, March 2-4, 2020, Inderjit\u00a0S. Dhillon, Dimitris\u00a0S. Papailiopoulos, and Vivienne Sze (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2020\/hash\/411e39b117e885341f25efb8912945f7-Abstract.html"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815992"},{"key":"e_1_3_2_1_66_1","volume-title":"Mixed Precision Training. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=r1gs9JgRZ","author":"Micikevicius Paulius","year":"2018","unstructured":"Paulius Micikevicius , Sharan Narang , Jonah Alben , Gregory Diamos , Erich Elsen , David Garcia , Boris Ginsburg , Michael Houston , Oleksii Kuchaiev , Ganesh Venkatesh , and Hao Wu . 2018 . Mixed Precision Training. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=r1gs9JgRZ Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, and Hao Wu. 2018. Mixed Precision Training. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=r1gs9JgRZ"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.05433"},{"key":"e_1_3_2_1_68_1","volume-title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems. CoRR abs\/1906.00091","author":"Naumov Maxim","year":"2019","unstructured":"Maxim Naumov , Dheevatsa Mudigere , Hao- Jun\u00a0Michael Shi , Jianyu Huang , Narayanan Sundaraman , Jongsoo Park , Xiaodong Wang , Udit Gupta , Carole-Jean Wu , Alisson\u00a0 G. Azzolini , Dmytro Dzhulgakov , Andrey Mallevich , Ilia Cherniavskii , Yinghai Lu , Raghuraman Krishnamoorthi , Ansha Yu , Volodymyr Kondratenko , Stephanie Pereira , Xianjie Chen , Wenlin Chen , Vijay Rao , Bill Jia , Liang Xiong , and Misha Smelyanskiy . 2019. Deep Learning Recommendation Model for Personalization and Recommendation Systems. CoRR abs\/1906.00091 ( 2019 ). arXiv:1906.00091http:\/\/arxiv.org\/abs\/1906.00091 Maxim Naumov, Dheevatsa Mudigere, Hao-Jun\u00a0Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson\u00a0G. Azzolini, Dmytro Dzhulgakov, Andrey Mallevich, Ilia Cherniavskii, Yinghai Lu, Raghuraman Krishnamoorthi, Ansha Yu, Volodymyr Kondratenko, Stephanie Pereira, Xianjie Chen, Wenlin Chen, Vijay Rao, Bill Jia, Liang Xiong, and Misha Smelyanskiy. 2019. Deep Learning Recommendation Model for Personalization and Recommendation Systems. CoRR abs\/1906.00091 (2019). arXiv:1906.00091http:\/\/arxiv.org\/abs\/1906.00091"},{"key":"e_1_3_2_1_69_1","unstructured":"Vinh Nguyen Michael Carilli Sukru\u00a0Burc Eryilmaz Vartika Singh Michelle Lin Natalia Gimelshein Alban Desmaison and Edward Yang. 2021. Accelerating PyTorch with CUDA Graphs. https:\/\/pytorch.org\/blog\/accelerating-pytorch-with-cuda-graphs\/  Vinh Nguyen Michael Carilli Sukru\u00a0Burc Eryilmaz Vartika Singh Michelle Lin Natalia Gimelshein Alban Desmaison and Edward Yang. 2021. Accelerating PyTorch with CUDA Graphs. https:\/\/pytorch.org\/blog\/accelerating-pytorch-with-cuda-graphs\/"},{"key":"e_1_3_2_1_70_1","unstructured":"NVIDIA. 2020. NVIDIA A100 Tensor Core GPU Architecture. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf  NVIDIA. 2020. NVIDIA A100 Tensor Core GPU Architecture. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf"},{"key":"e_1_3_2_1_71_1","unstructured":"NVIDIA. 2021. NVIDIA Ampere GA102 GPU Architecture. https:\/\/www.nvidia.com\/content\/PDF\/nvidia-ampere-ga-102-gpu-architecture-whitepaper-v2.pdf  NVIDIA. 2021. NVIDIA Ampere GA102 GPU Architecture. https:\/\/www.nvidia.com\/content\/PDF\/nvidia-ampere-ga-102-gpu-architecture-whitepaper-v2.pdf"},{"key":"e_1_3_2_1_72_1","volume-title":"https:\/\/docs.nvidia.com\/cuda\/archive\/12.0.0\/cuda-c-programming-guide\/index.html Accessed on","author":"Programming Guide NVIDIA.","year":"2023","unstructured":"NVIDIA. 2023. CUDA C++ Programming Guide . https:\/\/docs.nvidia.com\/cuda\/archive\/12.0.0\/cuda-c-programming-guide\/index.html Accessed on April 28 2023 . NVIDIA. 2023. CUDA C++ Programming Guide. https:\/\/docs.nvidia.com\/cuda\/archive\/12.0.0\/cuda-c-programming-guide\/index.html Accessed on April 28 2023."},{"key":"e_1_3_2_1_73_1","unstructured":"NVIDIA. 2023. Linux X64 (AMD64\/EM64T) Display Driver. https:\/\/www.nvidia.com\/download\/driverResults.aspx\/199656\/en-us\/  NVIDIA. 2023. Linux X64 (AMD64\/EM64T) Display Driver. https:\/\/www.nvidia.com\/download\/driverResults.aspx\/199656\/en-us\/"},{"key":"e_1_3_2_1_74_1","volume-title":"NVIDIA H100 Tensor Core GPU Architecture. https:\/\/resources.nvidia.com\/en-us-tensor-core Accessed on","author":"NVIDIA.","year":"2023","unstructured":"NVIDIA. 2023. NVIDIA H100 Tensor Core GPU Architecture. https:\/\/resources.nvidia.com\/en-us-tensor-core Accessed on July 8 2023 . NVIDIA. 2023. NVIDIA H100 Tensor Core GPU Architecture. https:\/\/resources.nvidia.com\/en-us-tensor-core Accessed on July 8 2023."},{"key":"e_1_3_2_1_75_1","unstructured":"NVIDIA. 2023. NVIDIA Linux Open GPU Kernel Module Source. https:\/\/github.com\/NVIDIA\/open-gpu-kernel-modules\/tree\/525.89.02  NVIDIA. 2023. NVIDIA Linux Open GPU Kernel Module Source. https:\/\/github.com\/NVIDIA\/open-gpu-kernel-modules\/tree\/525.89.02"},{"key":"e_1_3_2_1_76_1","volume-title":"CUDA Templates for Linear Algebra Subroutines. https:\/\/github.com\/NVIDIA\/cutlass Accessed on","author":"NVIDIA.","year":"2023","unstructured":"NVIDIA. 2023. NVIDIA\/cutlass : CUDA Templates for Linear Algebra Subroutines. https:\/\/github.com\/NVIDIA\/cutlass Accessed on April 28 2023 . NVIDIA. 2023. NVIDIA\/cutlass: CUDA Templates for Linear Algebra Subroutines. https:\/\/github.com\/NVIDIA\/cutlass Accessed on April 28 2023."},{"key":"e_1_3_2_1_77_1","unstructured":"ONNX. 2022. Open Neural Network Exchange. https:\/\/github.com\/onnx\/onnx\/tree\/v1.12.0  ONNX. 2022. Open Neural Network Exchange. https:\/\/github.com\/onnx\/onnx\/tree\/v1.12.0"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/7902.7904"},{"key":"e_1_3_2_1_80_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke , Sam Gross , Francisco Massa , Adam Lerer , James Bradbury , Gregory Chanan , Trevor Killeen , Zeming Lin , Natalia Gimelshein , Luca Antiga , Alban Desmaison , Andreas Kopf , Edward Yang , Zachary DeVito , Martin Raison , Alykhan Tejani , Sasank Chilamkurthy , Benoit Steiner , Lu Fang , Junjie Bai , and Soumith Chintala . 2019. PyTorch: An Imperative Style , High-Performance Deep Learning Library . In Advances in Neural Information Processing Systems, H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d'Alch\u00e9-Buc, E.\u00a0Fox, and R.\u00a0Garnett (Eds.). Vol.\u00a032. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems, H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d'Alch\u00e9-Buc, E.\u00a0Fox, and R.\u00a0Garnett (Eds.). Vol.\u00a032. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf"},{"key":"e_1_3_2_1_81_1","unstructured":"David Patterson. 2022. A Decade of Machine Learning Accelerators: Lessons Learned and Carbon Footprint. https:\/\/chips-compilers-mlsys-22.github.io\/assets\/slides\/10%20Lessons%204%20TPU%20gens%20+%20CO2e%2045%20minutes.pdf  David Patterson. 2022. A Decade of Machine Learning Accelerators: Lessons Learned and Carbon Footprint. https:\/\/chips-compilers-mlsys-22.github.io\/assets\/slides\/10%20Lessons%204%20TPU%20gens%20+%20CO2e%2045%20minutes.pdf"},{"key":"e_1_3_2_1_82_1","unstructured":"PCI-SIG. 2010. PCI Express Base Specification Revision 3.0. https:\/\/pcisig.com\/specifications?field_technology_value%5B%5D=express&field_revision_value%5B%5D=3&field_document_type_value%5B%5D=specification&speclib=PCI+Express+Base+Specification+Revision+3.0  PCI-SIG. 2010. PCI Express Base Specification Revision 3.0. https:\/\/pcisig.com\/specifications?field_technology_value%5B%5D=express&field_revision_value%5B%5D=3&field_document_type_value%5B%5D=specification&speclib=PCI+Express+Base+Specification+Revision+3.0"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"key":"e_1_3_2_1_84_1","unstructured":"Reiner Pope Sholto Douglas Aakanksha Chowdhery Jacob Devlin James Bradbury Anselm Levskaya Jonathan Heek Kefan Xiao Shivani Agrawal and Jeff Dean. 2022. Efficiently Scaling Transformer Inference. arxiv:2211.05102\u00a0[cs.LG]  Reiner Pope Sholto Douglas Aakanksha Chowdhery Jacob Devlin James Bradbury Anselm Levskaya Jonathan Heek Kefan Xiao Shivani Agrawal and Jeff Dean. 2022. Efficiently Scaling Transformer Inference. arxiv:2211.05102\u00a0[cs.LG]"},{"key":"e_1_3_2_1_85_1","volume-title":"Thread State and the Global Interpreter Lock. https:\/\/docs.python.org\/3\/c-api\/init.html#thread-state-and-the-global-interpreter-lock Accessed on","year":"2023","unstructured":"Python. 2023. Thread State and the Global Interpreter Lock. https:\/\/docs.python.org\/3\/c-api\/init.html#thread-state-and-the-global-interpreter-lock Accessed on April 28 2023 . Python. 2023. Thread State and the Global Interpreter Lock. https:\/\/docs.python.org\/3\/c-api\/init.html#thread-state-and-the-global-interpreter-lock Accessed on April 28 2023."},{"key":"e_1_3_2_1_86_1","unstructured":"PyTorch. 2023. TorchDynamo Overview. https:\/\/pytorch.org\/docs\/stable\/dynamo\/index.html  PyTorch. 2023. TorchDynamo Overview. https:\/\/pytorch.org\/docs\/stable\/dynamo\/index.html"},{"key":"e_1_3_2_1_87_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019). https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf  Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019). https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"e_1_3_2_1_92_1","volume-title":"Proceedings of Machine Learning and Systems 2022","author":"Reed K.","year":"2022","unstructured":"James\u00a0 K. Reed , Zachary DeVito , Horace He , Ansley Ussery , and Jason Ansel . 2022 . torch.fx: Practical Program Capture and Transformation for Deep Learning in Python . In Proceedings of Machine Learning and Systems 2022 , MLSys 2022, Santa Clara, CA, USA, August 29 - September 1, 2022, Diana Marculescu, Yuejie Chi, and Carole-Jean Wu (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/2022\/hash\/ca46c1b9512a7a8315fa3c5a946e8265-Abstract.html James\u00a0K. Reed, Zachary DeVito, Horace He, Ansley Ussery, and Jason Ansel. 2022. torch.fx: Practical Program Capture and Transformation for Deep Learning in Python. In Proceedings of Machine Learning and Systems 2022, MLSys 2022, Santa Clara, CA, USA, August 29 - September 1, 2022, Diana Marculescu, Yuejie Chi, and Carole-Jean Wu (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/2022\/hash\/ca46c1b9512a7a8315fa3c5a946e8265-Abstract.html"},{"key":"e_1_3_2_1_93_1","volume-title":"ZeRO-Offload: Democratizing Billion-Scale Model Training. In 2021 USENIX Annual Technical Conference, USENIX ATC 2021","author":"Ren Jie","year":"2021","unstructured":"Jie Ren , Samyam Rajbhandari , Reza\u00a0Yazdani Aminabadi , Olatunji Ruwase , Shuangyan Yang , Minjia Zhang , Dong Li , and Yuxiong He . 2021 . ZeRO-Offload: Democratizing Billion-Scale Model Training. In 2021 USENIX Annual Technical Conference, USENIX ATC 2021 , July 14-16, 2021, Irina Calciu and Geoff Kuenning (Eds.). USENIX Association, 551\u2013564. https:\/\/www.usenix.org\/conference\/atc21\/presentation\/ren-jie Jie Ren, Samyam Rajbhandari, Reza\u00a0Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. ZeRO-Offload: Democratizing Billion-Scale Model Training. In 2021 USENIX Annual Technical Conference, USENIX ATC 2021, July 14-16, 2021, Irina Calciu and Geoff Kuenning (Eds.). USENIX Association, 551\u2013564. https:\/\/www.usenix.org\/conference\/atc21\/presentation\/ren-jie"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522352"},{"key":"e_1_3_2_1_95_1","volume-title":"Memory-efficient Neural Network Design. In The 49th Annual IEEE\/ACM International Symposium on Microarchitecture","author":"Rhu Minsoo","year":"2016","unstructured":"Minsoo Rhu , Natalia Gimelshein , Jason Clemons , Arslan Zulfiqar , and Stephen\u00a0 W. Keckler . 2016 . vDNN: Virtualized Deep Neural Networks for Scalable , Memory-efficient Neural Network Design. In The 49th Annual IEEE\/ACM International Symposium on Microarchitecture ( Taipei, Taiwan) (MICRO-49). IEEE Press, Article 18, 13\u00a0pages. http:\/\/dl.acm.org\/citation.cfm?id=3 195638.3195660 Minsoo Rhu, Natalia Gimelshein, Jason Clemons, Arslan Zulfiqar, and Stephen\u00a0W. Keckler. 2016. vDNN: Virtualized Deep Neural Networks for Scalable, Memory-efficient Neural Network Design. In The 49th Annual IEEE\/ACM International Symposium on Microarchitecture (Taipei, Taiwan) (MICRO-49). IEEE Press, Article 18, 13\u00a0pages. http:\/\/dl.acm.org\/citation.cfm?id=3195638.3195660"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00017"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_2_1_98_1","volume-title":"XLA: Compiling Machine Learning for Peak Performance.","author":"Sabne Amit","year":"2020","unstructured":"Amit Sabne . 2020 . XLA: Compiling Machine Learning for Peak Performance. Amit Sabne. 2020. XLA: Compiling Machine Learning for Peak Performance."},{"key":"e_1_3_2_1_99_1","unstructured":"Christian Sarofeen Piotr Bialecki Jie Jiang Kevin Stephano Masaki Kozuki Neal Vaidya and Stas Bekman. 2022. Introducing nvFuser a deep learning compiler for PyTorch. https:\/\/pytorch.org\/blog\/introducing-nvfuser-a-deep-learning-compiler-for-pytorch\/  Christian Sarofeen Piotr Bialecki Jie Jiang Kevin Stephano Masaki Kozuki Neal Vaidya and Stas Bekman. 2022. Introducing nvFuser a deep learning compiler for PyTorch. https:\/\/pytorch.org\/blog\/introducing-nvfuser-a-deep-learning-compiler-for-pytorch\/"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1145\/3381831"},{"key":"e_1_3_2_1_101_1","unstructured":"Junru Shao Xiyou Zhou Siyuan Feng Bohan Hou Ruihang Lai Hongyi Jin Wuwei Lin Masahiro Masuda Cody\u00a0Hao Yu and Tianqi Chen. 2022. Tensor Program Optimization with Probabilistic Programs. In Advances in Neural Information Processing Systems Alice\u00a0H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=nyCr6-0hinG  Junru Shao Xiyou Zhou Siyuan Feng Bohan Hou Ruihang Lai Hongyi Jin Wuwei Lin Masahiro Masuda Cody\u00a0Hao Yu and Tianqi Chen. 2022. Tensor Program Optimization with Probabilistic Programs. In Advances in Neural Information Processing Systems Alice\u00a0H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=nyCr6-0hinG"},{"key":"e_1_3_2_1_102_1","volume-title":"Proceedings of Machine Learning and Systems 2021","author":"Shen Haichen","year":"2021","unstructured":"Haichen Shen , Jared Roesch , Zhi Chen , Wei Chen , Yong Wu , Mu Li , Vin Sharma , Zachary Tatlock , and Yida Wang . 2021 . Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference . In Proceedings of Machine Learning and Systems 2021 , MLSys 2021, virtual, April 5-9, 2021, Alex Smola, Alex Dimakis, and Ion Stoica (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/ 2021\/hash\/4e732ced3463d06de0ca9a15b6153677-Abstract.html Haichen Shen, Jared Roesch, Zhi Chen, Wei Chen, Yong Wu, Mu Li, Vin Sharma, Zachary Tatlock, and Yida Wang. 2021. Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference. In Proceedings of Machine Learning and Systems 2021, MLSys 2021, virtual, April 5-9, 2021, Alex Smola, Alex Dimakis, and Ion Stoica (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/2021\/hash\/4e732ced3463d06de0ca9a15b6153677-Abstract.html"},{"key":"e_1_3_2_1_103_1","volume-title":"Neural Network Quantization with AI Model Efficiency Toolkit (AIMET). CoRR abs\/2201.08442","author":"Siddegowda Sangeetha","year":"2022","unstructured":"Sangeetha Siddegowda , Marios Fournarakis , Markus Nagel , Tijmen Blankevoort , Chirag Patel , and Abhijit Khobare . 2022. Neural Network Quantization with AI Model Efficiency Toolkit (AIMET). CoRR abs\/2201.08442 ( 2022 ). arXiv:2201.08442https:\/\/arxiv.org\/abs\/2201.08442 Sangeetha Siddegowda, Marios Fournarakis, Markus Nagel, Tijmen Blankevoort, Chirag Patel, and Abhijit Khobare. 2022. Neural Network Quantization with AI Model Efficiency Toolkit (AIMET). CoRR abs\/2201.08442 (2022). arXiv:2201.08442https:\/\/arxiv.org\/abs\/2201.08442"},{"key":"e_1_3_2_1_104_1","volume-title":"Hotline Profiler: Automatic Annotation and A Multi-Scale Timeline for Visualizing Time-Use in DNN Training.","author":"Snider Daniel","year":"2023","unstructured":"Daniel Snider , Fanny Chevalier , and Gennady Pekhimenko . 2023 . Hotline Profiler: Automatic Annotation and A Multi-Scale Timeline for Visualizing Time-Use in DNN Training. (2023). https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/hash\/763d339d9e1b0caa2ea9ae01d4b9e0d0-Abstract-mlsys2023.html Daniel Snider, Fanny Chevalier, and Gennady Pekhimenko. 2023. Hotline Profiler: Automatic Annotation and A Multi-Scale Timeline for Visualizing Time-Use in DNN Training. (2023). https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/hash\/763d339d9e1b0caa2ea9ae01d4b9e0d0-Abstract-mlsys2023.html"},{"key":"e_1_3_2_1_105_1","unstructured":"Sally Stevenson Stephen Jones and Fred Oh. 2022. Enabling Dynamic Control Flow in CUDA Graphs with Device Graph Launch. https:\/\/developer.nvidia.com\/blog\/enabling-dynamic-control-flow-in-cuda-graphs-with-device-graph-launch\/  Sally Stevenson Stephen Jones and Fred Oh. 2022. Enabling Dynamic Control Flow in CUDA Graphs with Device Graph Launch. https:\/\/developer.nvidia.com\/blog\/enabling-dynamic-control-flow-in-cuda-graphs-with-device-graph-launch\/"},{"key":"e_1_3_2_1_106_1","volume-title":"Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates","author":"Stiennon Nisan","year":"2020","unstructured":"Nisan Stiennon , Long Ouyang , Jeffrey Wu , Daniel Ziegler , Ryan Lowe , Chelsea Voss , Alec Radford , Dario Amodei , and Paul\u00a0 F Christiano . 2020. Learning to summarize with human feedback . In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates , Inc ., 3008\u20133021. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/ 2020 \/file\/1f89885d556929e98d3ef9b86448f951-Paper.pdf Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul\u00a0F Christiano. 2020. Learning to summarize with human feedback. In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates, Inc., 3008\u20133021. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1f89885d556929e98d3ef9b86448f951-Paper.pdf"},{"key":"e_1_3_2_1_107_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc\u00a0 V. Le . 2019 . EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks . In Proceedings of the 36th International Conference on Machine Learning, ICML 2019 , 9-15 June 2019, Long Beach, California, USA(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 6105\u20136114. http:\/\/proceedings.mlr.press\/v97\/tan19a.html Mingxing Tan and Quoc\u00a0V. Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 6105\u20136114. http:\/\/proceedings.mlr.press\/v97\/tan19a.html"},{"key":"e_1_3_2_1_108_1","unstructured":"Xiaodan Tan Paul\u00a0Gilbert Meyer Gennady Pekhimenko and Randy\u00a0Renfu Huang. 2023. Mixing sparsity compression. https:\/\/patents.google.com\/patent\/US20230100930A1  Xiaodan Tan Paul\u00a0Gilbert Meyer Gennady Pekhimenko and Randy\u00a0Renfu Huang. 2023. Mixing sparsity compression. https:\/\/patents.google.com\/patent\/US20230100930A1"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523448"},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_2_1_111_1","volume-title":"Efficient Inference with TensorRT. In GPU Technology Conference. https:\/\/on-demand.gputechconf.com\/gtc-eu\/2017\/presentation\/23425-han-vanholder-efficient-inference-with-tensorrt.pdf","author":"Vanholder Han","year":"2016","unstructured":"Han Vanholder . 2016 . Efficient Inference with TensorRT. In GPU Technology Conference. https:\/\/on-demand.gputechconf.com\/gtc-eu\/2017\/presentation\/23425-han-vanholder-efficient-inference-with-tensorrt.pdf Han Vanholder. 2016. Efficient Inference with TensorRT. In GPU Technology Conference. https:\/\/on-demand.gputechconf.com\/gtc-eu\/2017\/presentation\/23425-han-vanholder-efficient-inference-with-tensorrt.pdf"},{"key":"e_1_3_2_1_112_1","unstructured":"Patrick von Platen. 2020. How to generate text: using different decoding methods for language generation with Transformers. https:\/\/huggingface.co\/blog\/how-to-generate#beam-search  Patrick von Platen. 2020. How to generate text: using different decoding methods for language generation with Transformers. https:\/\/huggingface.co\/blog\/how-to-generate#beam-search"},{"key":"e_1_3_2_1_113_1","unstructured":"Patrick von Platen. 2021. Fine-Tune Wav2Vec2 for English ASR with Transformers. https:\/\/huggingface.co\/blog\/fine-tune-wav2vec2-english  Patrick von Platen. 2021. Fine-Tune Wav2Vec2 for English ASR with Transformers. https:\/\/huggingface.co\/blog\/fine-tune-wav2vec2-english"},{"key":"e_1_3_2_1_114_1","unstructured":"Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model. https:\/\/github.com\/kingoflolz\/mesh-transformer-jax  Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model. https:\/\/github.com\/kingoflolz\/mesh-transformer-jax"},{"key":"e_1_3_2_1_115_1","volume-title":"PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. In 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021","author":"Wang Haojie","year":"2021","unstructured":"Haojie Wang , Jidong Zhai , Mingyu Gao , Zixuan Ma , Shizhi Tang , Liyan Zheng , Yuanzhi Li , Kaiyuan Rong , Yuanyong Chen , and Zhihao Jia . 2021 . PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. In 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021 , July 14-16, 2021, Angela\u00a0Demke Brown and Jay\u00a0R. Lorch (Eds.). USENIX Association, 37\u201354. https:\/\/www.usenix.org\/conference\/osdi21\/presentation\/wang Haojie Wang, Jidong Zhai, Mingyu Gao, Zixuan Ma, Shizhi Tang, Liyan Zheng, Yuanzhi Li, Kaiyuan Rong, Yuanyong Chen, and Zhihao Jia. 2021. PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections. In 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021, July 14-16, 2021, Angela\u00a0Demke Brown and Jay\u00a0R. Lorch (Eds.). USENIX Association, 37\u201354. https:\/\/www.usenix.org\/conference\/osdi21\/presentation\/wang"},{"key":"e_1_3_2_1_116_1","unstructured":"Shibo Wang and Pankaj Kanwar. 2019. BFloat16: The secret to high performance on Cloud TPUs. https:\/\/cloud.google.com\/blog\/products\/ai-machine-learning\/bfloat16-the-secret-to-high-performance-on-cloud-tpus  Shibo Wang and Pankaj Kanwar. 2019. BFloat16: The secret to high performance on Cloud TPUs. https:\/\/cloud.google.com\/blog\/products\/ai-machine-learning\/bfloat16-the-secret-to-high-performance-on-cloud-tpus"},{"key":"e_1_3_2_1_117_1","volume-title":"Proceedings of Machine Learning and Systems, A.\u00a0Smola, A.\u00a0Dimakis, and I.\u00a0Stoica (Eds.). Vol.\u00a03. 599\u2013623","author":"Wang Shang","year":"2021","unstructured":"Shang Wang , Peiming Yang , Yuxuan Zheng , Xin Li , and Gennady Pekhimenko . 2021 . Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Models . In Proceedings of Machine Learning and Systems, A.\u00a0Smola, A.\u00a0Dimakis, and I.\u00a0Stoica (Eds.). Vol.\u00a03. 599\u2013623 . https:\/\/proceedings.mlsys.org\/paper\/2021\/file\/a97da629b098b75c294dffdc3e463904-Paper.pdf Shang Wang, Peiming Yang, Yuxuan Zheng, Xin Li, and Gennady Pekhimenko. 2021. Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Models. In Proceedings of Machine Learning and Systems, A.\u00a0Smola, A.\u00a0Dimakis, and I.\u00a0Stoica (Eds.). Vol.\u00a03. 599\u2013623. https:\/\/proceedings.mlsys.org\/paper\/2021\/file\/a97da629b098b75c294dffdc3e463904-Paper.pdf"},{"key":"e_1_3_2_1_118_1","unstructured":"Yao Wang. 2019. [RFC] Dynamic Shape Support - Graph Dispatching. https:\/\/github.com\/apache\/tvm\/issues\/4118  Yao Wang. 2019. [RFC] Dynamic Shape Support - Graph Dispatching. https:\/\/github.com\/apache\/tvm\/issues\/4118"},{"key":"e_1_3_2_1_119_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370330"},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_121_1","volume-title":"Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation. CoRR abs\/2004.09602","author":"Wu Hao","year":"2020","unstructured":"Hao Wu , Patrick Judd , Xiaojie Zhang , Mikhail Isaev , and Paulius Micikevicius . 2020. Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation. CoRR abs\/2004.09602 ( 2020 ). arXiv:2004.09602https:\/\/arxiv.org\/abs\/2004.09602 Hao Wu, Patrick Judd, Xiaojie Zhang, Mikhail Isaev, and Paulius Micikevicius. 2020. Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation. CoRR abs\/2004.09602 (2020). arXiv:2004.09602https:\/\/arxiv.org\/abs\/2004.09602"},{"key":"e_1_3_2_1_122_1","volume-title":"Proceedings of Machine Learning and Systems 2022","author":"Xing Jiarong","year":"2022","unstructured":"Jiarong Xing , Leyuan Wang , Shang Zhang , Jack Chen , Ang Chen , and Yibo Zhu . 2022 . Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance . In Proceedings of Machine Learning and Systems 2022 , MLSys 2022, Santa Clara, CA, USA, August 29 - September 1, 2022, Diana Marculescu, Yuejie Chi, and Carole-Jean Wu (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/2022\/hash\/38b3eff8baf56627478ec76a704e9b52-Abstract.html Jiarong Xing, Leyuan Wang, Shang Zhang, Jack Chen, Ang Chen, and Yibo Zhu. 2022. Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance. In Proceedings of Machine Learning and Systems 2022, MLSys 2022, Santa Clara, CA, USA, August 29 - September 1, 2022, Diana Marculescu, Yuejie Chi, and Carole-Jean Wu (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/2022\/hash\/38b3eff8baf56627478ec76a704e9b52-Abstract.html"},{"key":"e_1_3_2_1_123_1","volume-title":"Proceedings of Machine Learning and Systems 2021","author":"Yang Yichen","year":"2021","unstructured":"Yichen Yang , Phitchaya\u00a0Mangpo Phothilimthana , Yisu\u00a0Remy Wang , Max Willsey , Sudip Roy , and Jacques Pienaar . 2021 . Equality Saturation for Tensor Graph Superoptimization . In Proceedings of Machine Learning and Systems 2021 , MLSys 2021, virtual, April 5-9, 2021, Alex Smola, Alex Dimakis, and Ion Stoica (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/ 2021\/hash\/65ded5353c5ee48d0b7d48c591b8f430-Abstract.html Yichen Yang, Phitchaya\u00a0Mangpo Phothilimthana, Yisu\u00a0Remy Wang, Max Willsey, Sudip Roy, and Jacques Pienaar. 2021. Equality Saturation for Tensor Graph Superoptimization. In Proceedings of Machine Learning and Systems 2021, MLSys 2021, virtual, April 5-9, 2021, Alex Smola, Alex Dimakis, and Ion Stoica (Eds.). mlsys.org. https:\/\/proceedings.mlsys.org\/paper\/2021\/hash\/65ded5353c5ee48d0b7d48c591b8f430-Abstract.html"},{"key":"e_1_3_2_1_124_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582047"},{"key":"e_1_3_2_1_125_1","volume-title":"Orca: A Distributed Serving System for Transformer-Based Generative Models. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu , Joo\u00a0Seong Jeong , Geon-Woo Kim , Soojeong Kim , and Byung-Gon Chun . 2022 . Orca: A Distributed Serving System for Transformer-Based Generative Models. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022 , Carlsbad, CA, USA , July 11-13, 2022, Marcos\u00a0K. Aguilera and Hakim Weatherspoon (Eds.). USENIX Association, 521\u2013538. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu Gyeong-In Yu, Joo\u00a0Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A Distributed Serving System for Transformer-Based Generative Models. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022, Carlsbad, CA, USA, July 11-13, 2022, Marcos\u00a0K. Aguilera and Hakim Weatherspoon (Eds.). USENIX Association, 521\u2013538. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu"},{"key":"e_1_3_2_1_126_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415890"},{"key":"e_1_3_2_1_127_1","unstructured":"Jiecao Yu Andrew Lukefahr David Palframan Ganesh Dasika Reetuparnda Das and Scott Mahlke. 2017. Systems and devices for compressing neural network parameters. https:\/\/patents.google.com\/patent\/US11321604B2  Jiecao Yu Andrew Lukefahr David Palframan Ganesh Dasika Reetuparnda Das and Scott Mahlke. 2017. Systems and devices for compressing neural network parameters. https:\/\/patents.google.com\/patent\/US11321604B2"},{"key":"e_1_3_2_1_128_1","volume-title":"Proceedings of Machine Learning and Systems, D.\u00a0Marculescu, Y.\u00a0Chi, and C.\u00a0Wu (Eds.). Vol.\u00a04. 1\u201319","author":"Zhao Jie","year":"2022","unstructured":"Jie Zhao , Xiong Gao , Ruijie Xia , Zhaochuang Zhang , Deshi Chen , Lei Chen , Renwei Zhang , Zhen Geng , Bin Cheng , and Xuefeng Jin . 2022 . Apollo: Automatic Partition-based Operator Fusion through Layer by Layer Optimization . In Proceedings of Machine Learning and Systems, D.\u00a0Marculescu, Y.\u00a0Chi, and C.\u00a0Wu (Eds.). Vol.\u00a04. 1\u201319 . https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2022\/file\/069059b7ef840f0c74a814ec9237b6ec-Paper.pdf Jie Zhao, Xiong Gao, Ruijie Xia, Zhaochuang Zhang, Deshi Chen, Lei Chen, Renwei Zhang, Zhen Geng, Bin Cheng, and Xuefeng Jin. 2022. Apollo: Automatic Partition-based Operator Fusion through Layer by Layer Optimization. In Proceedings of Machine Learning and Systems, D.\u00a0Marculescu, Y.\u00a0Chi, and C.\u00a0Wu (Eds.). Vol.\u00a04. 1\u201319. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2022\/file\/069059b7ef840f0c74a814ec9237b6ec-Paper.pdf"},{"key":"e_1_3_2_1_129_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454106"},{"key":"e_1_3_2_1_130_1","volume-title":"Proceedings of Machine Learning and Systems, D.\u00a0Marculescu, Y.\u00a0Chi, and C.\u00a0Wu (Eds.). Vol.\u00a04. 848\u2013863","author":"Zheng Bojian","year":"2022","unstructured":"Bojian Zheng , Ziheng Jiang , Cody\u00a0Hao Yu , Haichen Shen , Joshua Fromm , Yizhi Liu , Yida Wang , Luis Ceze , Tianqi Chen , and Gennady Pekhimenko . 2022 . DietCode: Automatic Optimization for Dynamic Tensor Programs . In Proceedings of Machine Learning and Systems, D.\u00a0Marculescu, Y.\u00a0Chi, and C.\u00a0Wu (Eds.). Vol.\u00a04. 848\u2013863 . https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2022\/file\/fa7cdfad1a5aaf8370ebeda47a1ff1c3-Paper.pdf Bojian Zheng, Ziheng Jiang, Cody\u00a0Hao Yu, Haichen Shen, Joshua Fromm, Yizhi Liu, Yida Wang, Luis Ceze, Tianqi Chen, and Gennady Pekhimenko. 2022. DietCode: Automatic Optimization for Dynamic Tensor Programs. In Proceedings of Machine Learning and Systems, D.\u00a0Marculescu, Y.\u00a0Chi, and C.\u00a0Wu (Eds.). Vol.\u00a04. 848\u2013863. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2022\/file\/fa7cdfad1a5aaf8370ebeda47a1ff1c3-Paper.pdf"},{"key":"e_1_3_2_1_131_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00092"},{"key":"e_1_3_2_1_132_1","volume-title":"Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng , Chengfan Jia , Minmin Sun , Zhao Wu , Cody\u00a0Hao Yu , Ameer Haj-Ali , Yida Wang , Jun Yang , Danyang Zhuo , Koushik Sen , Joseph\u00a0 E. Gonzalez , and Ion Stoica . 2020 . Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020 , Virtual Event , November 4-6, 2020. USENIX Association, 863\u2013879. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/zheng Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody\u00a0Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2020. Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2020, Virtual Event, November 4-6, 2020. USENIX Association, 863\u2013879. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/zheng"},{"key":"e_1_3_2_1_133_1","volume-title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022","author":"Zheng Lianmin","year":"2022","unstructured":"Lianmin Zheng , Zhuohan Li , Hao Zhang , Yonghao Zhuang , Zhifeng Chen , Yanping Huang , Yida Wang , Yuanzhong Xu , Danyang Zhuo , Eric\u00a0 P. Xing , Joseph\u00a0 E. Gonzalez , and Ion Stoica . 2022 . Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022 , Carlsbad, CA, USA , July 11-13, 2022, Marcos\u00a0K. Aguilera and Hakim Weatherspoon (Eds.). USENIX Association, 559\u2013578. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/zheng-lianmin Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric\u00a0P. Xing, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2022. Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022, Carlsbad, CA, USA, July 11-13, 2022, Marcos\u00a0K. Aguilera and Hakim Weatherspoon (Eds.). USENIX Association, 559\u2013578. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/zheng-lianmin"},{"key":"e_1_3_2_1_134_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527440"},{"key":"e_1_3_2_1_135_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"e_1_3_2_1_136_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507723"},{"key":"e_1_3_2_1_137_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573476"},{"key":"e_1_3_2_1_138_1","volume-title":"ROLLER: Fast and Efficient Tensor Compilation for Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022","author":"Zhu Hongyu","year":"2022","unstructured":"Hongyu Zhu , Ruofan Wu , Yijia Diao , Shanbin Ke , Haoyu Li , Chen Zhang , Jilong Xue , Lingxiao Ma , Yuqing Xia , Wei Cui , Fan Yang , Mao Yang , Lidong Zhou , Asaf Cidon , and Gennady Pekhimenko . 2022 . ROLLER: Fast and Efficient Tensor Compilation for Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022 , Carlsbad, CA, USA , July 11-13, 2022, Marcos\u00a0K. Aguilera and Hakim Weatherspoon (Eds.). USENIX Association, 233\u2013248. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/zhu Hongyu Zhu, Ruofan Wu, Yijia Diao, Shanbin Ke, Haoyu Li, Chen Zhang, Jilong Xue, Lingxiao Ma, Yuqing Xia, Wei Cui, Fan Yang, Mao Yang, Lidong Zhou, Asaf Cidon, and Gennady Pekhimenko. 2022. ROLLER: Fast and Efficient Tensor Compilation for Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2022, Carlsbad, CA, USA, July 11-13, 2022, Marcos\u00a0K. Aguilera and Hakim Weatherspoon (Eds.). USENIX Association, 233\u2013248. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/zhu"},{"key":"e_1_3_2_1_139_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437984.3458838"}],"event":{"name":"MICRO '23: 56th Annual IEEE\/ACM International Symposium on Microarchitecture","location":"Toronto ON Canada","acronym":"MICRO '23","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["56th Annual IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613424.3614248","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613424.3614248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:46:21Z","timestamp":1750164381000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613424.3614248"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,28]]},"references-count":138,"alternative-id":["10.1145\/3613424.3614248","10.1145\/3613424"],"URL":"https:\/\/doi.org\/10.1145\/3613424.3614248","relation":{},"subject":[],"published":{"date-parts":[[2023,10,28]]},"assertion":[{"value":"2023-12-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}