{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:44:25Z","timestamp":1773193465672,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,9]],"date-time":"2022-04-09T00:00:00Z","timestamp":1649462400000},"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":[[2022,4,9]]},"DOI":"10.1145\/3489525.3511672","type":"proceedings-article","created":{"date-parts":[[2022,3,25]],"date-time":"2022-03-25T22:11:46Z","timestamp":1648246306000},"page":"177-186","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Near-Storage Processing for Solid State Drive Based Recommendation Inference with SmartSSDs\u00ae"],"prefix":"10.1145","author":[{"given":"Mohammadreza","family":"Soltaniyeh","sequence":"first","affiliation":[{"name":"Rutgers University, New Brunswick, NJ, USA"}]},{"given":"Veronica","family":"Lagrange Moutinho Dos Reis","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor, Inc., San Jose, CA, USA"}]},{"given":"Matt","family":"Bryson","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor, Inc., San Jose, CA, USA"}]},{"given":"Xuebin","family":"Yao","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor, Inc., San Jose, CA, USA"}]},{"given":"Richard P.","family":"Martin","sequence":"additional","affiliation":[{"name":"Rutgers University, New Brunswick, NJ, USA"}]},{"given":"Santosh","family":"Nagarakatte","sequence":"additional","affiliation":[{"name":"Rutgers University, New Brunswick, NJ, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Bandana: Using Non-volatile Memory for Storing Deep Learning Models. arxiv","author":"Eisenman Assaf","year":"2018","unstructured":"Assaf Eisenman , Maxim Naumov , Darryl Gardner , Misha Smelyanskiy , Sergey Pupyrev , Kim Hazelwood , Asaf Cidon , and Sachin Katti . 2018 . Bandana: Using Non-volatile Memory for Storing Deep Learning Models. arxiv : 1811.05922 [cs.LG] Assaf Eisenman, Maxim Naumov, Darryl Gardner, Misha Smelyanskiy, Sergey Pupyrev, Kim Hazelwood, Asaf Cidon, and Sachin Katti. 2018. Bandana: Using Non-volatile Memory for Storing Deep Learning Models. arxiv: 1811.05922 [cs.LG]"},{"key":"e_1_3_2_1_2_1","volume-title":"The Netezza Data Appliance Architecture: A Platform for High Performance Data Warehousing and Analytics. IBM Redbook","author":"Francisco Phil","year":"2011","unstructured":"Phil Francisco . 2011. The Netezza Data Appliance Architecture: A Platform for High Performance Data Warehousing and Analytics. IBM Redbook ( 2011 ). Phil Francisco. 2011. The Netezza Data Appliance Architecture: A Platform for High Performance Data Warehousing and Analytics. IBM Redbook (2011)."},{"key":"e_1_3_2_1_3_1","volume-title":"DeepRecSys: A System for Optimizing End-To-End At-Scale Neural Recommendation Inference. In 2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA). 982--995","author":"Gupta Udit","year":"2020","unstructured":"Udit Gupta , Samuel Hsia , Vikram Saraph , Xiaodong Wang , Brandon Reagen , Gu-Yeon Wei , Hsien-Hsin S. Lee , David Brooks , and Carole-Jean Wu . 2020 a . DeepRecSys: A System for Optimizing End-To-End At-Scale Neural Recommendation Inference. In 2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA). 982--995 . https:\/\/doi.org\/10.1109\/ISCA45697.2020.00084 10.1109\/ISCA45697.2020.00084 Udit Gupta, Samuel Hsia, Vikram Saraph, Xiaodong Wang, Brandon Reagen, Gu-Yeon Wei, Hsien-Hsin S. Lee, David Brooks, and Carole-Jean Wu. 2020 a. DeepRecSys: A System for Optimizing End-To-End At-Scale Neural Recommendation Inference. In 2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA). 982--995. https:\/\/doi.org\/10.1109\/ISCA45697.2020.00084"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00047"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Jul","author":"Haldar Malay","year":"2019","unstructured":"Malay Haldar , Mustafa Abdool , Prashant Ramanathan , Tao Xu , Shulin Yang , Huizhong Duan , Qing Zhang , Nick Barrow-Williams , Bradley C. Turnbull , Brendan M. Collins, and et al. 2019. Applying Deep Learning to Airbnb Search . Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Jul 2019 ). https:\/\/doi.org\/10.1145\/3292500.3330658 10.1145\/3292500.3330658 Malay Haldar, Mustafa Abdool, Prashant Ramanathan, Tao Xu, Shulin Yang, Huizhong Duan, Qing Zhang, Nick Barrow-Williams, Bradley C. Turnbull, Brendan M. Collins, and et al. 2019. Applying Deep Learning to Airbnb Search. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Jul 2019). https:\/\/doi.org\/10.1145\/3292500.3330658"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"e_1_3_2_1_7_1","volume-title":"Centaur: A Chiplet-Based, Hybrid Sparse-Dense Accelerator for Personalized Recommendations","author":"Hwang Ranggi","year":"2020","unstructured":"Ranggi Hwang , Taehun Kim , Youngeun Kwon , and Minsoo Rhu . 2020 . Centaur: A Chiplet-Based, Hybrid Sparse-Dense Accelerator for Personalized Recommendations . IEEE Press , 968--981. https:\/\/doi.org\/10.1109\/ISCA45697.2020.00083 10.1109\/ISCA45697.2020.00083 Ranggi Hwang, Taehun Kim, Youngeun Kwon, and Minsoo Rhu. 2020. Centaur: A Chiplet-Based, Hybrid Sparse-Dense Accelerator for Personalized Recommendations .IEEE Press, 968--981. https:\/\/doi.org\/10.1109\/ISCA45697.2020.00083"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of Machine Learning and Systems , , A. Smola, A. Dimakis, and I. Stoica (Eds.)","volume":"3","author":"Jiang Wenqi","year":"2021","unstructured":"Wenqi Jiang , Zhenhao He , Shuai Zhang , Thomas B. Preu\u00df er, Kai Zeng , Liang Feng , Jiansong Zhang , Tongxuan Liu , Yong Li , Jingren Zhou , Ce Zhang , and Gustavo Alonso . 2021 a. MicroRec: Efficient Recommendation Inference by Hardware and Data Structure Solutions . In Proceedings of Machine Learning and Systems , , A. Smola, A. Dimakis, and I. Stoica (Eds.) , Vol. 3 . 845--859. Wenqi Jiang, Zhenhao He, Shuai Zhang, Thomas B. Preu\u00df er, Kai Zeng, Liang Feng, Jiansong Zhang, Tongxuan Liu, Yong Li, Jingren Zhou, Ce Zhang, and Gustavo Alonso. 2021 a. MicroRec: Efficient Recommendation Inference by Hardware and Data Structure Solutions. In Proceedings of Machine Learning and Systems , , A. Smola, A. Dimakis, and I. Stoica (Eds.), Vol. 3. 845--859."},{"key":"e_1_3_2_1_9_1","volume-title":"2021 b. FleetRec: Large-Scale Recommendation Inference on Hybrid GPU-FPGA Clusters","author":"Jiang Wenqi","unstructured":"Wenqi Jiang , Zhenhao He , Shuai Zhang , Kai Zeng , Liang Feng , Jiansong Zhang , Tongxuan Liu , Yong Li , Jingren Zhou , Ce Zhang , and Gustavo Alonso . 2021 b. FleetRec: Large-Scale Recommendation Inference on Hybrid GPU-FPGA Clusters . Association for Computing Machinery , New York, NY, USA , 3097--3105. https:\/\/doi.org\/10.1145\/3447548.3467139 10.1145\/3447548.3467139 Wenqi Jiang, Zhenhao He, Shuai Zhang, Kai Zeng, Liang Feng, Jiansong Zhang, Tongxuan Liu, Yong Li, Jingren Zhou, Ce Zhang, and Gustavo Alonso. 2021 b. FleetRec: Large-Scale Recommendation Inference on Hybrid GPU-FPGA Clusters .Association for Computing Machinery, New York, NY, USA, 3097--3105. https:\/\/doi.org\/10.1145\/3447548.3467139"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Liu Ke Udit Gupta Carole-Jean Wu Benjamin Youngjae Cho Mark Hempstead Brandon Reagen Xuan Zhang David Brooks Vikas Chandra Utku Diril Amin Firoozshahian Kim Hazelwood Bill Jia Hsien-Hsin S. Lee Meng Li Bert Maher Dheevatsa Mudigere Maxim Naumov Martin Schatz Mikhail Smelyanskiy and Xiaodong Wang. 2019. RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing. arxiv: 1912.12953 [cs.DC]  Liu Ke Udit Gupta Carole-Jean Wu Benjamin Youngjae Cho Mark Hempstead Brandon Reagen Xuan Zhang David Brooks Vikas Chandra Utku Diril Amin Firoozshahian Kim Hazelwood Bill Jia Hsien-Hsin S. Lee Meng Li Bert Maher Dheevatsa Mudigere Maxim Naumov Martin Schatz Mikhail Smelyanskiy and Xiaodong Wang. 2019. RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing. arxiv: 1912.12953 [cs.DC]","DOI":"10.1109\/ISCA45697.2020.00070"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304028"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358284"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3358960.3375794"},{"key":"#cr-split#-e_1_3_2_1_14_1.1","doi-asserted-by":"crossref","unstructured":"Yang Li and Zhitao Dai. 2019. Design and Implementation of Hardware Accelerator for Recommendation System based on Heterogeneous Computing Platform. https:\/\/doi.org\/10.2991\/icmeit-19.2019.150 10.2991\/icmeit-19.2019.150","DOI":"10.2991\/icmeit-19.2019.150"},{"key":"#cr-split#-e_1_3_2_1_14_1.2","doi-asserted-by":"crossref","unstructured":"Yang Li and Zhitao Dai. 2019. Design and Implementation of Hardware Accelerator for Recommendation System based on Heterogeneous Computing Platform. https:\/\/doi.org\/10.2991\/icmeit-19.2019.150","DOI":"10.2991\/icmeit-19.2019.150"},{"key":"e_1_3_2_1_15_1","unstructured":"Maxim Naumov Dheevatsa Mudigere Hao-Jun Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole-Jean Wu Alisson 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 Vol. abs\/1906.00091 (2019). https:\/\/arxiv.org\/abs\/1906.00091  Maxim Naumov Dheevatsa Mudigere Hao-Jun Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole-Jean Wu Alisson 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 Vol. abs\/1906.00091 (2019). https:\/\/arxiv.org\/abs\/1906.00091"},{"key":"e_1_3_2_1_16_1","volume-title":"Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications. arxiv","author":"Park Jongsoo","year":"1811","unstructured":"Jongsoo Park , Maxim Naumov , Protonu Basu , Summer Deng , Aravind Kalaiah , Daya Khudia , James Law , Parth Malani , Andrey Malevich , Satish Nadathur , Juan Pino , Martin Schatz , Alexander Sidorov , Viswanath Sivakumar , Andrew Tulloch , Xiaodong Wang , Yiming Wu , Hector Yuen , Utku Diril , Dmytro Dzhulgakov , Kim Hazelwood , Bill Jia , Yangqing Jia , Lin Qiao , Vijay Rao , Nadav Rotem , Sungjoo Yoo , and Mikhail Smelyanskiy . 2018. Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications. arxiv : 1811 .09886 [cs.LG] Jongsoo Park, Maxim Naumov, Protonu Basu, Summer Deng, Aravind Kalaiah, Daya Khudia, James Law, Parth Malani, Andrey Malevich, Satish Nadathur, Juan Pino, Martin Schatz, Alexander Sidorov, Viswanath Sivakumar, Andrew Tulloch, Xiaodong Wang, Yiming Wu, Hector Yuen, Utku Diril, Dmytro Dzhulgakov, Kim Hazelwood, Bill Jia, Yangqing Jia, Lin Qiao, Vijay Rao, Nadav Rotem, Sungjoo Yoo, and Mikhail Smelyanskiy. 2018. Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications. arxiv: 1811.09886 [cs.LG]"},{"key":"e_1_3_2_1_17_1","volume-title":"NASCENT: Near-Storage Acceleration of Database Sort on SmartSSD. In The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays","author":"Salamat Sahand","year":"2021","unstructured":"Sahand Salamat , Armin Haj Aboutalebi , Behnam Khaleghi , Joo Hwan Lee , Yang Seok Ki , and Tajana Rosing . 2021 . NASCENT: Near-Storage Acceleration of Database Sort on SmartSSD. In The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays ( Virtual Event, USA) (FPGA '21). Association for Computing Machinery, New York, NY, USA, 262--272. https:\/\/doi.org\/10.1145\/343 1920.3439298 10.1145\/3431920.3439298 Sahand Salamat, Armin Haj Aboutalebi, Behnam Khaleghi, Joo Hwan Lee, Yang Seok Ki, and Tajana Rosing. 2021. NASCENT: Near-Storage Acceleration of Database Sort on SmartSSD. In The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (Virtual Event, USA) (FPGA '21). Association for Computing Machinery, New York, NY, USA, 262--272. https:\/\/doi.org\/10.1145\/3431920.3439298"},{"key":"e_1_3_2_1_18_1","unstructured":"Mohammadreza Soltaniyeh Richard P. Martin and Santosh Nagarakatte. 2021 a. SPOTS: An Accelerator for Sparse CNNs Leveraging General Matrix-Matrix Multiplication. arxiv: 2107.13386 [cs.AR]  Mohammadreza Soltaniyeh Richard P. Martin and Santosh Nagarakatte. 2021 a. SPOTS: An Accelerator for Sparse CNNs Leveraging General Matrix-Matrix Multiplication. arxiv: 2107.13386 [cs.AR]"},{"key":"e_1_3_2_1_19_1","volume-title":"Near-Storage Acceleration of Database Query Processing with SmartSSDs. In 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). 265--265","author":"Soltaniyeh Mohammadreza","year":"2021","unstructured":"Mohammadreza Soltaniyeh , Veronica Lagrange Moutinho Dos Reis , Matthew Bryson , Richard Martin , and Santosh Nagarakatte . 2021 b . Near-Storage Acceleration of Database Query Processing with SmartSSDs. In 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). 265--265 . https:\/\/doi.org\/10.1109\/FCCM51124.2021.00052 10.1109\/FCCM51124.2021.00052 Mohammadreza Soltaniyeh, Veronica Lagrange Moutinho Dos Reis, Matthew Bryson, Richard Martin, and Santosh Nagarakatte. 2021 b. Near-Storage Acceleration of Database Query Processing with SmartSSDs. In 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). 265--265. https:\/\/doi.org\/10.1109\/FCCM51124.2021.00052"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340922"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219869"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446763"},{"key":"e_1_3_2_1_23_1","unstructured":"Xilinx-Samsung. 2021. SmartSSD. https:\/\/www.xilinx.com\/applications\/data-center\/computational-storage\/smartssd.html  Xilinx-Samsung. 2021. SmartSSD. https:\/\/www.xilinx.com\/applications\/data-center\/computational-storage\/smartssd.html"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358045"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346997"},{"key":"e_1_3_2_1_26_1","volume-title":"Deep Interest Evolution Network for Click-Through Rate Prediction. arxiv","author":"Zhou Guorui","year":"1809","unstructured":"Guorui Zhou , Na Mou , Ying Fan , Qi Pi , Weijie Bian , Chang Zhou , Xiaoqiang Zhu , and Kun Gai . 2018a. Deep Interest Evolution Network for Click-Through Rate Prediction. arxiv : 1809 .03672 [stat.ML] Guorui Zhou, Na Mou, Ying Fan, Qi Pi, Weijie Bian, Chang Zhou, Xiaoqiang Zhu, and Kun Gai. 2018a. Deep Interest Evolution Network for Click-Through Rate Prediction. arxiv: 1809.03672 [stat.ML]"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"ICPE '22: ACM\/SPEC International Conference on Performance Engineering","location":"Beijing China","acronym":"ICPE '22","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2022 ACM\/SPEC on International Conference on Performance Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489525.3511672","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3489525.3511672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:23Z","timestamp":1750186943000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489525.3511672"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,9]]},"references-count":28,"alternative-id":["10.1145\/3489525.3511672","10.1145\/3489525"],"URL":"https:\/\/doi.org\/10.1145\/3489525.3511672","relation":{},"subject":[],"published":{"date-parts":[[2022,4,9]]},"assertion":[{"value":"2022-04-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}