{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T11:56:02Z","timestamp":1792756562823,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,10]],"date-time":"2022-07-10T00:00:00Z","timestamp":1657411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,10]]},"DOI":"10.1145\/3489517.3530506","type":"proceedings-article","created":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T23:19:29Z","timestamp":1661296769000},"page":"583-588","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Self adaptive reconfigurable arrays (SARA)"],"prefix":"10.1145","author":[{"given":"Ananda","family":"Samajdar","sequence":"first","affiliation":[{"name":"Georgia Tech"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Qin","sequence":"additional","affiliation":[{"name":"Georgia Tech"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Pellauer","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tushar","family":"Krishna","sequence":"additional","affiliation":[{"name":"Georgia Tech"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,8,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Manoj Alwani et al. 2016. Fused-layer CNN accelerators. In MICRO.","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"e_1_3_2_1_2_1","unstructured":"Tianqi Chen et al. 2018. Learning to optimize tensor programs. In NeurIPS."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Jeremy Fowers et al. 2018. A configurable cloud-scale DNN processor for real-time AI. In ISCA. IEEE 1--14.","DOI":"10.1109\/ISCA.2018.00012"},{"key":"e_1_3_2_1_5_1","volume-title":"Tetris: Scalable and efficient neural network acceleration with 3d memory. In ASPLOS.","author":"Mingyu Gao","year":"2017","unstructured":"Mingyu Gao et al. 2017. Tetris: Scalable and efficient neural network acceleration with 3d memory. In ASPLOS."},{"key":"e_1_3_2_1_6_1","volume-title":"Tangram: Optimized coarse-grained dataflow for scalable NN accelerators. In ASPLOS.","author":"Mingyu Gao","year":"2019","unstructured":"Mingyu Gao et al. 2019. Tangram: Optimized coarse-grained dataflow for scalable NN accelerators. In ASPLOS."},{"key":"e_1_3_2_1_7_1","volume-title":"Planaria: Dynamic Architecture Fission for Spatial Multi-Tenant Acceleration of Deep Neural Networks","author":"Soroush Ghodrati","year":"2020","unstructured":"Soroush Ghodrati et al. 2020. Planaria: Dynamic Architecture Fission for Spatial Multi-Tenant Acceleration of Deep Neural Networks. In MICRO. IEEE."},{"key":"e_1_3_2_1_8_1","unstructured":"Norman P Jouppi et al. 2017. In-datacenter performance analysis of a tensor processing unit. In ISCA. 1--12."},{"key":"e_1_3_2_1_9_1","volume-title":"Neurocube: A programmable digital neuromorphic architecture with high-density 3D memory. ISCA","author":"Duckhwan Kim","year":"2016","unstructured":"Duckhwan Kim et al. 2016. Neurocube: A programmable digital neuromorphic architecture with high-density 3D memory. ISCA (2016)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Tushar Krishna et al. 2014. SMART: single-cycle multihop traversals over a shared network on chip. IEEE micro (2014).","DOI":"10.1109\/MM.2014.48"},{"key":"e_1_3_2_1_11_1","volume-title":"Maeri: Enabling flexible dataflow mapping over dnn accelerators via reconfigurable interconnects. ASPLOS","author":"Hyoukjun Kwon","year":"2018","unstructured":"Hyoukjun Kwon et al. 2018. Maeri: Enabling flexible dataflow mapping over dnn accelerators via reconfigurable interconnects. ASPLOS (2018)."},{"key":"e_1_3_2_1_12_1","volume-title":"Flexflow: A flexible dataflow accelerator architecture for convolutional neural networks. In HPCA.","author":"Wenyan Lu","year":"2017","unstructured":"Wenyan Lu et al. 2017. Flexflow: A flexible dataflow accelerator architecture for convolutional neural networks. In HPCA."},{"key":"e_1_3_2_1_13_1","volume-title":"SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training. In HPCA.","author":"Eric Qin","year":"2020","unstructured":"Eric Qin et al. 2020. SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training. In HPCA."},{"key":"e_1_3_2_1_14_1","volume-title":"Cascades: Interconnect-aware FPGA implementation of Machine Learning problems. In FPL.","author":"Ananda Samajdar","year":"2019","unstructured":"Ananda Samajdar et al. 2019. Scaling the Cascades: Interconnect-aware FPGA implementation of Machine Learning problems. In FPL."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Ananda Samajdar et al. 2020. A Systematic Methodology for Characterizing Scalability of DNN Accelerators using SCALE-Sim. In ISPASS.","DOI":"10.1109\/ISPASS48437.2020.00016"},{"key":"e_1_3_2_1_16_1","volume-title":"Simba: Scaling deep-learning inference with multi-chip-module-based architecture. In MICRO.","author":"Shao Yakun Sophia","year":"2019","unstructured":"Yakun Sophia Shao et al. 2019. Simba: Scaling deep-learning inference with multi-chip-module-based architecture. In MICRO."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Chen Zhang et al. 2015. Optimizing fpga-based accelerator design for deep convolutional neural networks. In FPGA.","DOI":"10.1145\/2684746.2689060"}],"event":{"name":"DAC '22: 59th ACM\/IEEE Design Automation Conference","location":"San Francisco California","acronym":"DAC '22","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA"]},"container-title":["Proceedings of the 59th ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489517.3530506","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3489517.3530506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:17Z","timestamp":1750186937000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489517.3530506"}},"subtitle":["learning flexible GEMM accelerator configuration and mapping-space using ML"],"short-title":[],"issued":{"date-parts":[[2022,7,10]]},"references-count":17,"alternative-id":["10.1145\/3489517.3530506","10.1145\/3489517"],"URL":"https:\/\/doi.org\/10.1145\/3489517.3530506","relation":{},"subject":[],"published":{"date-parts":[[2022,7,10]]},"assertion":[{"value":"2022-08-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}