{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:15:34Z","timestamp":1784211334097,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,14]],"date-time":"2017-10-14T00:00:00Z","timestamp":1507939200000},"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":[[2017,10,14]]},"DOI":"10.1145\/3132747.3132756","type":"proceedings-article","created":{"date-parts":[[2017,10,12]],"date-time":"2017-10-12T12:51:09Z","timestamp":1507812669000},"page":"137-152","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":167,"title":["KV-Direct"],"prefix":"10.1145","author":[{"given":"Bojie","family":"Li","sequence":"first","affiliation":[{"name":"USTC and Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyuan","family":"Ruan","sequence":"additional","affiliation":[{"name":"Microsoft Research and UCLA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wencong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Beihang University and Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanwei","family":"Lu","sequence":"additional","affiliation":[{"name":"USTC and Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqiang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Putnam","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"USTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lintao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,10,14]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"InfiniBand Architecture Specification: Release 1.0","unstructured":"2000. InfiniBand Architecture Specification: Release 1.0 . InfiniBand Trade Association . 2000. InfiniBand Architecture Specification: Release 1.0. InfiniBand Trade Association."},{"key":"e_1_3_2_2_2_1","unstructured":"2017. Altera SDK for OpenCL. (2017). http\/\/:www.altera.com\/.  2017. Altera SDK for OpenCL. (2017). http\/\/:www.altera.com\/."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2318857.2254766"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2436256.2436271"},{"key":"e_1_3_2_2_5_1","volume-title":"The 5th USENIX Workshop on Hot Topics in Cloud Computing. USENIX","author":"Blott Michaela","year":"2013","unstructured":"Michaela Blott , Kimon Karras , Ling Liu , Kees Vissers , Jeremia B\u00e4r , and Zsolt Istv\u00e1n . 2013 . Achieving 10Gbps Line-rate Key-value Stores with FPGAs . In The 5th USENIX Workshop on Hot Topics in Cloud Computing. USENIX , San Jose, CA. Michaela Blott, Kimon Karras, Ling Liu, Kees Vissers, Jeremia B\u00e4r, and Zsolt Istv\u00e1n. 2013. Achieving 10Gbps Line-rate Key-value Stores with FPGAs. In The 5th USENIX Workshop on Hot Topics in Cloud Computing. USENIX, San Jose, CA."},{"key":"e_1_3_2_2_6_1","volume-title":"HotStorage '15","author":"Blott Michaela","year":"2015","unstructured":"Michaela Blott , Ling Liu , Kimon Karras , and Kees A Vissers . 2015 . Scaling Out to a Single-Node 80Gbps Memcached Server with 40Terabytes of Memory .. In HotStorage '15 . Michaela Blott, Ling Liu, Kimon Karras, and Kees A Vissers. 2015. Scaling Out to a Single-Node 80Gbps Memcached Server with 40Terabytes of Memory.. In HotStorage '15."},{"key":"e_1_3_2_2_7_1","volume-title":"USENIX summer","author":"Bonwick Jeff","unstructured":"Jeff Bonwick and others. 1994. The Slab Allocator: An Object-Caching Kernel Memory Allocator .. In USENIX summer , Vol. 16 . Boston, MA , USA. Jeff Bonwick and others. 1994. The Slab Allocator: An Object-Caching Kernel Memory Allocator.. In USENIX summer, Vol. 16. Boston, MA, USA."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486011"},{"key":"e_1_3_2_2_9_1","volume-title":"Dong Ping Zhang","author":"Breslow Alex D","year":"2016","unstructured":"Alex D Breslow , Dong Ping Zhang , Joseph L Greathouse , Nuwan Jayasena , and Dean M Tullsen. 2016 . Horton tables: fast hash tables for in-memory data-intensive computing. In USENIX ATC '16. Alex D Breslow, Dong Ping Zhang, Joseph L Greathouse, Nuwan Jayasena, and Dean M Tullsen. 2016. Horton tables: fast hash tables for in-memory data-intensive computing. In USENIX ATC '16."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195647"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2435264.2435306"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1365815.1365816"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901349"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2905012"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807152"},{"key":"e_1_3_2_2_16_1","unstructured":"TPC Council. 2010. tpc-c benchmark revision 5.11. (2010).  TPC Council. 2010. tpc-c benchmark revision 5.11. (2010)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1323293.1294281"},{"key":"e_1_3_2_2_18_1","volume-title":"NSDI '14","author":"Dragojevi\u0107 Aleksandar","year":"2014","unstructured":"Aleksandar Dragojevi\u0107 , Dushyanth Narayanan , Miguel Castro , and Orion Hodson . 2014 . FaRM: fast remote memory . In NSDI '14 . Aleksandar Dragojevi\u0107, Dushyanth Narayanan, Miguel Castro, and Orion Hodson. 2014. FaRM: fast remote memory. In NSDI '14."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/139669.140382"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2377677.2377681"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000108"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408797"},{"key":"e_1_3_2_2_23_1","volume-title":"NSDI '13","author":"Fan Bin","year":"2013","unstructured":"Bin Fan , David G Andersen , and Michael Kaminsky . 2013 . MemC3: Compact and concurrent memcache with dumber caching and smarter hashing . In NSDI '13 . 371--384. Bin Fan, David G Andersen, and Michael Kaminsky. 2013. MemC3: Compact and concurrent memcache with dumber caching and smarter hashing. In NSDI '13. 371--384."},{"key":"e_1_3_2_2_24_1","volume-title":"VFP: A Virtual Switch Platform for Host SDN in the Public Cloud. In NSDI '17","author":"Firestone Daniel","year":"2017","unstructured":"Daniel Firestone . 2017 . VFP: A Virtual Switch Platform for Host SDN in the Public Cloud. In NSDI '17 . Boston, MA, 315--328. Daniel Firestone. 2017. VFP: A Virtual Switch Platform for Host SDN in the Public Cloud. In NSDI '17. Boston, MA, 315--328."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/1012889.1012894"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/146628.139678"},{"key":"e_1_3_2_2_27_1","volume-title":"SDN for the Cloud. In Keynote in the 2015 ACM Conference on Special Interest Group on Data Communication.","author":"Greenberg Albert","year":"2015","unstructured":"Albert Greenberg . 2015 . SDN for the Cloud. In Keynote in the 2015 ACM Conference on Special Interest Group on Data Communication. Albert Greenberg. 2015. SDN for the Cloud. In Keynote in the 2015 ACM Conference on Special Interest Group on Data Communication."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851275.1851207"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87779-0_24"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987569"},{"key":"e_1_3_2_2_31_1","unstructured":"DPDK Intel. 2014. Data plane development kit. (2014).  DPDK Intel. 2014. Data plane development kit. (2014)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2013.6645520"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2629582"},{"key":"e_1_3_2_2_34_1","volume-title":"NSDI '14","author":"Jeong EunYoung","year":"2014","unstructured":"EunYoung Jeong , Shinae Woo , Muhammad Asim Jamshed , Haewon Jeong , Sunghwan Ihm , Dongsu Han , and KyoungSoo Park . 2014 . mTCP: a Highly Scalable User-level TCP Stack for Multicore Systems .. In NSDI '14 . 489--502. EunYoung Jeong, Shinae Woo, Muhammad Asim Jamshed, Haewon Jeong, Sunghwan Ihm, Dongsu Han, and KyoungSoo Park. 2014. mTCP: a Highly Scalable User-level TCP Stack for Multicore Systems.. In NSDI '14. 489--502."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132764"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626299"},{"key":"e_1_3_2_2_37_1","volume-title":"Design Guidelines for High Performance RDMA Systems. In USENIX ATC '16","author":"Kalia Anuj","year":"2016","unstructured":"Anuj Kalia , Michael Kaminsky , and David G Andersen . 2016 . Design Guidelines for High Performance RDMA Systems. In USENIX ATC '16 . Anuj Kalia, Michael Kaminsky, and David G Andersen. 2016. Design Guidelines for High Performance RDMA Systems. In USENIX ATC '16."},{"key":"e_1_3_2_2_38_1","volume-title":"OSDI '16","author":"Kalia Anuj","year":"2016","unstructured":"Anuj Kalia , Michael Kaminsky , and David G Andersen . 2016 . FaSST: fast, scalable and simple distributed transactions with two-sided RDMA datagram RPCs . In OSDI '16 . 185--201. Anuj Kalia, Michael Kaminsky, and David G Andersen. 2016. FaSST: fast, scalable and simple distributed transactions with two-sided RDMA datagram RPCs. In OSDI '16. 185--201."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391238"},{"key":"e_1_3_2_2_40_1","volume-title":"HotOS '15","author":"Kaufmann Antoine","year":"2015","unstructured":"Antoine Kaufmann , Simon Peter , Thomas E Anderson , and Arvind Krishnamurthy . 2015 . FlexNIC: Rethinking Network DMA .. In HotOS '15 . Antoine Kaufmann, Simon Peter, Thomas E Anderson, and Arvind Krishnamurthy. 2015. FlexNIC: Rethinking Network DMA.. In HotOS '15."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872362.2872367"},{"key":"e_1_3_2_2_42_1","volume-title":"USENIX ATC '16","author":"Kejriwal Ankita","year":"2016","unstructured":"Ankita Kejriwal , Arjun Gopalan , Ashish Gupta , Zhihao Jia , Stephen Yang , and John Ousterhout . 2016 . SLIK: Scalable low-latency indexes for a key-value store . In USENIX ATC '16 . Ankita Kejriwal, Arjun Gopalan, Ashish Gupta, Zhihao Jia, Stephen Yang, and John Ousterhout. 2016. SLIK: Scalable low-latency indexes for a key-value store. In USENIX ATC '16."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2013.17"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934897"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132751"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"crossref","unstructured":"Mu Li David G Andersen and Jun Woo Park. 2014. Scaling Distributed Machine Learning with the Parameter Server.  Mu Li David G Andersen and Jun Woo Park. 2014. Scaling Distributed Machine Learning with the Parameter Server.","DOI":"10.1145\/2640087.2644155"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897393"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2592798.2592820"},{"key":"e_1_3_2_2_49_1","volume-title":"NSDI '16","author":"Li Xiaozhou","year":"2016","unstructured":"Xiaozhou Li , Raghav Sethi , Michael Kaminsky , David G Andersen , and Michael J Freedman . 2016 . Be fast, cheap and in control with SwitchKV . In NSDI '16 . Xiaozhou Li, Raghav Sethi, Michael Kaminsky, David G Andersen, and Michael J Freedman. 2016. Be fast, cheap and in control with SwitchKV. In NSDI '16."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2016.7577355"},{"key":"e_1_3_2_2_51_1","volume-title":"NSDI '14","author":"Lim Hyeontaek","year":"2014","unstructured":"Hyeontaek Lim , Dongsu Han , David G Andersen , and Michael Kaminsky . 2014 . MICA: a holistic approach to fast in-memory key-value storage . In NSDI '14 . 429--444. Hyeontaek Lim, Dongsu Han, David G Andersen, and Michael Kaminsky. 2014. MICA: a holistic approach to fast in-memory key-value storage. In NSDI '14. 429--444."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021743"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2168836.2168855"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626311"},{"key":"e_1_3_2_2_55_1","volume-title":"CPU-Efficient Key-Value Store. In USENIX ATC '13","author":"Mitchell Christopher","year":"2013","unstructured":"Christopher Mitchell , Yifeng Geng , and Jinyang Li . 2013 . Using OneSided RDMA Reads to Build a Fast , CPU-Efficient Key-Value Store. In USENIX ATC '13 . 103--114. Christopher Mitchell, Yifeng Geng, and Jinyang Li. 2013. Using OneSided RDMA Reads to Build a Fast, CPU-Efficient Key-Value Store. In USENIX ATC '13. 103--114."},{"key":"e_1_3_2_2_56_1","volume-title":"OSDI '14","volume":"14","author":"Narula Neha","year":"2014","unstructured":"Neha Narula , Cody Cutler , Eddie Kohler , and Robert Morris . 2014 . Phase Reconciliation for Contended In-Memory Transactions .. In OSDI '14 , Vol. 14 . 511--524. Neha Narula, Cody Cutler, Eddie Kohler, and Robert Morris. 2014. Phase Reconciliation for Contended In-Memory Transactions.. In OSDI '14, Vol. 14. 511--524."},{"key":"e_1_3_2_2_57_1","volume-title":"NSDI '13","author":"Nishtala Rajesh","year":"2013","unstructured":"Rajesh Nishtala , Hans Fugal , Steven Grimm , Marc Kwiatkowski , Herman Lee , Harry C Li , Ryan McElroy , Mike Paleczny , Daniel Peek , Paul Saab , and others. 2013 . Scaling memcache at facebook . In NSDI '13 . Rajesh Nishtala, Hans Fugal, Steven Grimm, Marc Kwiatkowski, Herman Lee, Harry C Li, Ryan McElroy, Mike Paleczny, Daniel Peek, Paul Saab, and others. 2013. Scaling memcache at facebook. In NSDI '13."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/1713254.1713276"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806887"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2014.7478821"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalgor.2003.12.002"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626309"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.5555\/2665671.2665678"},{"key":"e_1_3_2_2_65_1","volume-title":"21st USENIX Security Symposium (USENIX Security 12)","author":"Rizzo Luigi","year":"2012","unstructured":"Luigi Rizzo . 2012 . Netmap: a novel framework for fast packet I\/O . In 21st USENIX Security Symposium (USENIX Security 12) . 101--112. Luigi Rizzo. 2012. Netmap: a novel framework for fast packet I\/O. In 21st USENIX Security Symposium (USENIX Security 12). 101--112."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807207"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2467799"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934900"},{"key":"e_1_3_2_2_69_1","first-page":"202","article-title":"The free lunch is over: A fundamental turn toward concurrency in software","volume":"30","author":"Sutter Herb","year":"2005","unstructured":"Herb Sutter . 2005 . The free lunch is over: A fundamental turn toward concurrency in software . Dr. Dobbs journal 30 , 3 (2005), 202 -- 210 . Herb Sutter. 2005. The free lunch is over: A fundamental turn toward concurrency in software. Dr. Dobbs journal 30, 3 (2005), 202--210.","journal-title":"Dr. Dobbs journal"},{"key":"e_1_3_2_2_70_1","volume-title":"First International Workshop on Rack-scale Computing.","author":"Szepesi Tyler","year":"2014","unstructured":"Tyler Szepesi , Bernard Wong , Ben Cassell , and Tim Brecht . 2014 . Designing a low-latency cuckoo hash table for write-intensive workloads using RDMA . In First International Workshop on Rack-scale Computing. Tyler Szepesi, Bernard Wong, Ben Cassell, and Tim Brecht. 2014. Designing a low-latency cuckoo hash table for write-intensive workloads using RDMA. In First International Workshop on Rack-scale Computing."},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2016.022"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/2815400.2815419"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806777.2806849"},{"key":"e_1_3_2_2_74_1","volume-title":"NSDI '17","author":"Xiao Wencong","year":"2017","unstructured":"Wencong Xiao , Jilong Xue , Youshan Miao , Zhen Li , Cheng Chen , Ming Wu , Wei Li , and Lidong Zhou . 2017 . TuX2: Distributed Graph Computation for Machine Learning . In NSDI '17 . Wencong Xiao, Jilong Xue, Youshan Miao, Zhen Li, Cheng Chen, Ming Wu, Wei Li, and Lidong Zhou. 2017. TuX2: Distributed Graph Computation for Machine Learning. In NSDI '17."},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809984"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787483"}],"event":{"name":"SOSP '17: ACM SIGOPS 26th Symposium on Operating Systems Principles","location":"Shanghai China","acronym":"SOSP '17","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","USENIX Assoc USENIX Assoc"]},"container-title":["Proceedings of the 26th Symposium on Operating Systems Principles"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3132747.3132756","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3132747.3132756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:10:57Z","timestamp":1750212657000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3132747.3132756"}},"subtitle":["High-Performance In-Memory Key-Value Store with Programmable NIC"],"short-title":[],"issued":{"date-parts":[[2017,10,14]]},"references-count":75,"alternative-id":["10.1145\/3132747.3132756","10.1145\/3132747"],"URL":"https:\/\/doi.org\/10.1145\/3132747.3132756","relation":{},"subject":[],"published":{"date-parts":[[2017,10,14]]},"assertion":[{"value":"2017-10-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}