{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:53:42Z","timestamp":1767678822348,"version":"3.48.0"},"reference-count":10,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/lca.2025.3624158","type":"journal-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:23:47Z","timestamp":1761153827000},"page":"393-396","source":"Crossref","is-referenced-by-count":0,"title":["Reimagining RDMA Through the Lens of ML"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6670-5076","authenticated-orcid":false,"given":"Ertza","family":"Warraich","sequence":"first","affiliation":[{"name":"Department of Computer Science, Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7194-2357","authenticated-orcid":false,"given":"Ali","family":"Imran","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA"}]},{"given":"Annus","family":"Zulfiqar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA"}]},{"given":"Shay","family":"Vargaftik","sequence":"additional","affiliation":[{"name":"Broadcom, Palo Alto, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2870-7166","authenticated-orcid":false,"given":"Sonia","family":"Fahmy","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5168-9045","authenticated-orcid":false,"given":"Muhammad","family":"Shahbaz","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Michigan, Ann Arbor, MI, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"685","article-title":"OptiReduce: Resilient and tail-optimal AllReduce for distributed deep learning in the cloud","volume-title":"Proc. 22nd USENIX Symp. Netw. Syst. Des. Implementation","author":"Warraich"},{"key":"ref2","first-page":"1421","article-title":"Towards domain-specific network transport for distributed DNN training","volume-title":"Proc. 21st USENIX Symp. Netw. Syst. Des. Implementation","author":"Wang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"ref4","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Alistarh"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"ref6","first-page":"44","article-title":"SRNIC: A scalable architecture for RDMA NICs","volume-title":"Proc. 9th Asia-Pacific Workshop Netw.","author":"Wang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230557"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"ref9","first-page":"18332","article-title":"DeepSpeed-MoE: Advancing MoE inference and training to power next-generation AI scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rajbhandari"},{"year":"2025","key":"ref10","article-title":"AMD\u2019s soft error mitigation"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/11062520\/11214426.pdf?arnumber=11214426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:51:12Z","timestamp":1767678672000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11214426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":10,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lca.2025.3624158","relation":{},"ISSN":["1556-6056","1556-6064","2473-2575"],"issn-type":[{"type":"print","value":"1556-6056"},{"type":"electronic","value":"1556-6064"},{"type":"electronic","value":"2473-2575"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}