{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:33:33Z","timestamp":1772724813697,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031320408","type":"print"},{"value":"9783031320415","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-32041-5_3","type":"book-chapter","created":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T21:56:29Z","timestamp":1683755789000},"page":"42-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Large Scale DLRM Implementation on\u00a0Heterogeneous Memory Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6105-1643","authenticated-orcid":false,"given":"Mark","family":"Hildebrand","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8880-8703","authenticated-orcid":false,"given":"Jason","family":"Lowe-Power","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3014-5326","authenticated-orcid":false,"given":"Venkatesh","family":"Akella","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,10]]},"reference":[{"issue":"1","key":"3_CR1","doi-asserted-by":"publisher","first-page":"127","DOI":"10.14778\/3485450.3485462","volume":"15","author":"M Adnan","year":"2021","unstructured":"Adnan, M., Maboud, Y.E., Mahajan, D., Nair, P.J.: Accelerating recommendation system training by leveraging popular choices. Proc. VLDB Endow. 15(1), 127\u2013140 (2021). https:\/\/doi.org\/10.14778\/3485450.3485462","journal-title":"Proc. VLDB Endow."},{"key":"3_CR2","unstructured":"Ardestani, E.K., et al.: Supporting massive DLRM inference through software defined memory. CoRR abs\/2110.11489 (2021). https:\/\/arxiv.org\/abs\/2110.11489"},{"issue":"9","key":"3_CR3","doi-asserted-by":"publisher","first-page":"1598","DOI":"10.14778\/3397230.3397251","volume":"13","author":"L Dhulipala","year":"2020","unstructured":"Dhulipala, L., et al.: Sage: parallel semi-asymmetric graph algorithms for NVRAMs. Proc. VLDB Endow. 13(9), 1598\u20131613 (2020). https:\/\/doi.org\/10.14778\/3397230.3397251","journal-title":"Proc. VLDB Endow."},{"key":"3_CR4","doi-asserted-by":"publisher","unstructured":"Eisenman, A., et al.: Reducing DRAM footprint with NVM in Facebook. In: Proceedings of the Thirteenth EuroSys Conference, EuroSys 2018, Porto, Portugal, 23\u201326 April 2018, pp. 42:1\u201342:13 (2018). https:\/\/doi.org\/10.1145\/3190508.3190524","DOI":"10.1145\/3190508.3190524"},{"key":"3_CR5","unstructured":"Eisenman, A., et al.: Bandana: using non-volatile memory for storing deep learning models. CoRR abs\/1811.05922 (2018). http:\/\/arxiv.org\/abs\/1811.05922"},{"key":"3_CR6","unstructured":"Fang, J., et al.: A frequency-aware software cache for large recommendation system embeddings (2022). https:\/\/arxiv.org\/abs\/2208.05321"},{"key":"3_CR7","unstructured":"Gupta, U., et al.: The architectural implications of Facebook\u2019s DNN-based personalized recommendation. CoRR abs\/1906.03109 (2019). https:\/\/arxiv.org\/abs\/1906.03109"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Gupta, U., et al.: 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), pp. 982\u2013995. IEEE (2020)","DOI":"10.1109\/ISCA45697.2020.00084"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Hildebrand, M., Angeles, J.T., Lowe-Power, J., Akella, V.: A case against hardware managed dram caches for NVRAM based systems. In: 2021 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 194\u2013204 (2021)","DOI":"10.1109\/ISPASS51385.2021.00036"},{"key":"3_CR10","first-page":"711","volume":"3","author":"A Ivanov","year":"2021","unstructured":"Ivanov, A., Dryden, N., Ben-Nun, T., Li, S., Hoefler, T.: Data movement is all you need: a case study on optimizing transformers. Proc. Mach. Learn. Syst. 3, 711\u2013732 (2021)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"3_CR11","unstructured":"Izraelevitz, J., et al.: Basic performance measurements of the Intel Optane DC persistent memory module. CoRR abs\/1903.05714 (2019). http:\/\/arxiv.org\/abs\/1903.05714"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Kalamkar, D., Georganas, E., Srinivasan, S., Chen, J., Shiryaev, M., Heinecke, A.: Optimizing deep learning recommender systems training on CPU cluster architectures. In: International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020, pp. 1\u201315. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00047"},{"key":"3_CR13","unstructured":"Kim, J., Choe, W., Ahn, J.: Exploring the design space of page management for multi-tiered memory systems. In: 2021 USENIX Annual Technical Conference (USENIX ATC 2021), pp. 715\u2013728 (2021)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: Building a performance model for deep learning recommendation model training on GPUs (2022). https:\/\/arxiv.org\/abs\/2201.07821","DOI":"10.1109\/ISPASS55109.2022.00030"},{"key":"3_CR15","unstructured":"Mattson, P., et al.: MLPerf training benchmark (2019)"},{"key":"3_CR16","doi-asserted-by":"publisher","unstructured":"Mudigere, D., et al.: Software-hardware co-design for fast and scalable training of deep learning recommendation models. In: Proceedings of the 49th Annual International Symposium on Computer Architecture, ISCA 2022, pp. 993\u20131011. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3470496.3533727","DOI":"10.1145\/3470496.3533727"},{"key":"3_CR17","unstructured":"Naumov, M., et al.: Deep learning recommendation model for personalization and recommendation systems. CoRR abs\/1906.00091 (2019). http:\/\/arxiv.org\/abs\/1906.00091"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Powers, D.M.W.: Applications and explanations of Zipf\u2019s law. In: New Methods in Language Processing and Computational Natural Language Learning (1998)","DOI":"10.3115\/1603899.1603924"},{"key":"3_CR19","doi-asserted-by":"publisher","unstructured":"Sethi, G., Acun, B., Agarwal, N., Kozyrakis, C., Trippel, C., Wu, C.J.: RecShard: statistical feature-based memory optimization for industry-scale neural recommendation. In: Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2022, pp. 344\u2013358. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3503222.3507777","DOI":"10.1145\/3503222.3507777"},{"key":"3_CR20","doi-asserted-by":"publisher","unstructured":"Shanbhag, A., Tatbul, N., Cohen, D., Madden, S.: Large-scale in-memory analytics on intel\u00ae optane\u2122 DC persistent memory. In: Proceedings of the 16th International Workshop on Data Management on New Hardware, DaMoN 2020. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3399666.3399933","DOI":"10.1145\/3399666.3399933"},{"key":"3_CR21","doi-asserted-by":"publisher","unstructured":"Xie, M., et al.: Fleche: an efficient GPU embedding cache for personalized recommendations. In: Proceedings of the Seventeenth European Conference on Computer Systems, EuroSys 2022, pp. 402\u2013416. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3492321.3519554","DOI":"10.1145\/3492321.3519554"},{"key":"3_CR22","doi-asserted-by":"publisher","unstructured":"Yan, Z., Lustig, D., Nellans, D., Bhattacharjee, A.: Nimble page management for tiered memory systems. In: Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2019, Providence, RI, USA, 13\u201317 April 2019, pp. 331\u2013345 (2019). https:\/\/doi.org\/10.1145\/3297858.3304024","DOI":"10.1145\/3297858.3304024"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-32041-5_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T22:00:43Z","timestamp":1683756043000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-32041-5_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031320408","9783031320415"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-32041-5_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"10 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"78","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"21","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.74","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.49","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}