{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T03:20:01Z","timestamp":1794021601038,"version":"4.8.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T00:00:00Z","timestamp":1593388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,29]]},"DOI":"10.1145\/3392717.3392751","type":"proceedings-article","created":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T14:49:02Z","timestamp":1593442142000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":96,"title":["Sparse-TPU"],"prefix":"10.1145","author":[{"given":"Xin","family":"He","sequence":"first","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhankar","family":"Pal","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aporva","family":"Amarnath","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siying","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong-Hyeon","family":"Park","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Austin","family":"Rovinski","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haojie","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhan","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronald","family":"Dreslinski","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Mudge","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,6,29]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872887.2750386"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2593069.2596667"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2513591.2527071"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049670"},{"key":"e_1_3_2_1_5_1","unstructured":"Jeff Dean. 2017. Machine learning for systems and systems for machine learning. In Presentation at 2017 Conference on Neural Information Processing Systems.  Jeff Dean. 2017. Machine learning for systems and systems for machine learning. In Presentation at 2017 Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_6_1","volume-title":"Predicting Parameters in Deep Learning. CoRR abs\/1306.0543","author":"Denil Misha","year":"2013","unstructured":"Misha Denil , Babak Shakibi , Laurent Dinh , Marc'Aurelio Ranzato , and Nando de Freitas . 2013. Predicting Parameters in Deep Learning. CoRR abs\/1306.0543 ( 2013 ). arXiv:1306.0543 http:\/\/arxiv.org\/abs\/1306.0543 Misha Denil, Babak Shakibi, Laurent Dinh, Marc'Aurelio Ranzato, and Nando de Freitas. 2013. Predicting Parameters in Deep Learning. CoRR abs\/1306.0543 (2013). arXiv:1306.0543 http:\/\/arxiv.org\/abs\/1306.0543"},{"key":"e_1_3_2_1_7_1","volume-title":"Albert Maurice Erisman, and John Ker Reid","author":"Duff Iain S","year":"2017","unstructured":"Iain S Duff , Albert Maurice Erisman, and John Ker Reid . 2017 . Direct methods for sparse matrices. Oxford University Press . Iain S Duff, Albert Maurice Erisman, and John Ker Reid. 2017. Direct methods for sparse matrices. Oxford University Press."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/567806.567810"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00023"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.68"},{"key":"e_1_3_2_1_12_1","volume-title":"Dynamic Network Surgery for Efficient DNNs. CoRR abs\/1608.04493","author":"Guo Yiwen","year":"2016","unstructured":"Yiwen Guo , Anbang Yao , and Yurong Chen .2016. Dynamic Network Surgery for Efficient DNNs. CoRR abs\/1608.04493 ( 2016 ). arXiv:1608.04493 http:\/\/arxiv.org\/abs\/1608.04493 Yiwen Guo, Anbang Yao, and Yurong Chen.2016. Dynamic Network Surgery for Efficient DNNs. CoRR abs\/1608.04493 (2016). arXiv:1608.04493 http:\/\/arxiv.org\/abs\/1608.04493"},{"key":"e_1_3_2_1_13_1","volume-title":"Dally","author":"Han Song","year":"2016","unstructured":"Song Han , Xingyu Liu , Huizi Mao , Jing Pu , Ardavan Pedram , Mark A. Horowitz , and William J . Dally . 2016 . EIE : Efficient Inference Engine on Compressed Deep Neural Network. CoRR abs\/1602.01528 (2016). arXiv:1602.01528 http:\/\/arxiv.org\/abs\/1602.01528 Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark A. Horowitz, and William J. Dally. 2016. EIE: Efficient Inference Engine on Compressed Deep Neural Network. CoRR abs\/1602.01528 (2016). arXiv:1602.01528 http:\/\/arxiv.org\/abs\/1602.01528"},{"key":"e_1_3_2_1_14_1","volume-title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.","author":"Han Song","year":"2016","unstructured":"Song Han , Huizi Mao , and William Dally . 2016 . Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. Song Han, Huizi Mao, and William Dally. 2016. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding."},{"key":"e_1_3_2_1_15_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han , Huizi Mao , and William J Dally . 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 ( 2015 ). Song Han, Huizi Mao, and William J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2019.2943575"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/292395.292412"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304028"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304626"},{"key":"e_1_3_2_1_22_1","unstructured":"Nallatech. 2018. OpenCAPI enabled FPGAs---the perfect bridge to a data centricworld. https:\/\/openpowerfoundation.org\/wp-content\/uploads\/2018\/10\/Allan-Cantle.Nallatech-Presentation-2018-OPF-Summit_Amsterdam-presentation.pdf. [Online].  Nallatech. 2018. OpenCAPI enabled FPGAs---the perfect bridge to a data centricworld. https:\/\/openpowerfoundation.org\/wp-content\/uploads\/2018\/10\/Allan-Cantle.Nallatech-Presentation-2018-OPF-Summit_Amsterdam-presentation.pdf. [Online]."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"e_1_3_2_1_24_1","volume-title":"2019 Symposium on VLSI Technology. IEEE, C150--C151","author":"Pal Subhankar","year":"2019","unstructured":"Subhankar Pal , Dong-hyeon Park, Siying Feng , Paul Gao , Jielun Tan , Austin Rovinski , Shaolin Xie , Chun Zhao , Aporva Amarnath , Timothy Wesley , 2019 . A 7.3 M Output Non-Zeros\/J Sparse Matrix-Matrix Multiplication Accelerator using Memory Reconfiguration in 40 nm . In 2019 Symposium on VLSI Technology. IEEE, C150--C151 . Subhankar Pal, Dong-hyeon Park, Siying Feng, Paul Gao, Jielun Tan, Austin Rovinski, Shaolin Xie, Chun Zhao, Aporva Amarnath, Timothy Wesley, et al. 2019. A 7.3 M Output Non-Zeros\/J Sparse Matrix-Matrix Multiplication Accelerator using Memory Reconfiguration in 40 nm. In 2019 Symposium on VLSI Technology. IEEE, C150--C151."},{"key":"e_1_3_2_1_25_1","volume-title":"Dally","author":"Parashar Angshuman","year":"2017","unstructured":"Angshuman Parashar , Minsoo Rhu , Anurag Mukkara , Antonio Puglielli , Rangharajan Venkatesan , Brucek Khailany , Joel S. Emer , Stephen W. Keckler , and William J . Dally . 2017 . SCNN : An Accelerator for Compressed-sparse Convolutional Neural Networks. CoRR abs\/1708.04485 (2017). arXiv:1708.04485 http:\/\/arxiv.org\/abs\/1708.04485 Angshuman Parashar, Minsoo Rhu, Anurag Mukkara, Antonio Puglielli, Rangharajan Venkatesan, Brucek Khailany, Joel S. Emer, Stephen W. Keckler, and William J. Dally. 2017. SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks. CoRR abs\/1708.04485 (2017). arXiv:1708.04485 http:\/\/arxiv.org\/abs\/1708.04485"},{"key":"e_1_3_2_1_26_1","volume-title":"Shaolin Xie, Chun Zhao, Aporva Amarnath, Timothy Wesley, et al.","author":"Park Dong-Hyeon","year":"2020","unstructured":"Dong-Hyeon Park , Subhankar Pal , Siying Feng , Paul Gao , Jielun Tan , Austin Rovinski , Shaolin Xie, Chun Zhao, Aporva Amarnath, Timothy Wesley, et al. 2020 . A 7.3 M Output Non-Zeros\/J, 11.7 M Output Non-Zeros\/GB Reconfigurable Sparse Matrix-Matrix Multiplication Accelerator. IEEE Journal of Solid-State Circuits ( 2020). Dong-Hyeon Park, Subhankar Pal, Siying Feng, Paul Gao, Jielun Tan, Austin Rovinski, Shaolin Xie, Chun Zhao, Aporva Amarnath, Timothy Wesley, et al. 2020. A 7.3 M Output Non-Zeros\/J, 11.7 M Output Non-Zeros\/GB Reconfigurable Sparse Matrix-Matrix Multiplication Accelerator. IEEE Journal of Solid-State Circuits (2020)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/800123.803971"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093315.3037746"},{"key":"e_1_3_2_1_29_1","volume-title":"SCALE-Sim: Systolic CNN Accelerator. CoRR abs\/1811.02883","author":"Samajdar Ananda","year":"2018","unstructured":"Ananda Samajdar , Yuhao Zhu , Paul N. Whatmough , Matthew Mattina , and Tushar Krishna . 2018. SCALE-Sim: Systolic CNN Accelerator. CoRR abs\/1811.02883 ( 2018 ). arXiv:1811.02883 http:\/\/arxiv.org\/abs\/1811.02883 Ananda Samajdar, Yuhao Zhu, Paul N. Whatmough, Matthew Mattina, and Tushar Krishna. 2018. SCALE-Sim: Systolic CNN Accelerator. CoRR abs\/1811.02883 (2018). arXiv:1811.02883 http:\/\/arxiv.org\/abs\/1811.02883"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2012.2193936"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809983"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/359168.359175"},{"key":"e_1_3_2_1_33_1","unstructured":"Paul Teich. 2018. Tear Apart Google's TPU 3.0 AI Coprocessor. https:\/\/www.nextplatform.com\/2018\/05\/10\/tearing-apart-googles-tpu-3-0-ai-coprocessor\/  Paul Teich. 2018. Tear Apart Google's TPU 3.0 AI Coprocessor. https:\/\/www.nextplatform.com\/2018\/05\/10\/tearing-apart-googles-tpu-3-0-ai-coprocessor\/"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358256"}],"event":{"name":"ICS '20: 2020 International Conference on Supercomputing","location":"Barcelona Spain","acronym":"ICS '20","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 34th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3392717.3392751","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3392717.3392751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:41:15Z","timestamp":1750185675000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3392717.3392751"}},"subtitle":["adapting systolic arrays for sparse matrices"],"short-title":[],"issued":{"date-parts":[[2020,6,29]]},"references-count":35,"alternative-id":["10.1145\/3392717.3392751","10.1145\/3392717"],"URL":"https:\/\/doi.org\/10.1145\/3392717.3392751","relation":{},"subject":[],"published":{"date-parts":[[2020,6,29]]},"assertion":[{"value":"2020-06-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}