{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:03:26Z","timestamp":1764842606188,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":3,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,3]],"date-time":"2022-04-03T00:00:00Z","timestamp":1648944000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["2047521 and 1955650"],"award-info":[{"award-number":["2047521 and 1955650"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,3]]},"DOI":"10.1145\/3530390.3532735","type":"proceedings-article","created":{"date-parts":[[2022,5,18]],"date-time":"2022-05-18T22:15:49Z","timestamp":1652912149000},"page":"1-2","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["ScaleServe"],"prefix":"10.1145","author":[{"given":"Ali","family":"Jahanshahi","sequence":"first","affiliation":[{"name":"University of California, Riverside"}]},{"given":"Marcus","family":"Chow","sequence":"additional","affiliation":[{"name":"University of California, Riverside"}]},{"given":"Daniel","family":"Wong","sequence":"additional","affiliation":[{"name":"University of California, Riverside"}]}],"member":"320","published-online":{"date-parts":[[2022,5,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Clipper: A Low-Latency Online Prediction Serving System. In USENIX Symposium on Networked Systems Design and Implementation (NSDI).","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw , Xin Wang , Guilio Zhou , Michael J Franklin , Joseph E Gonzalez , and Ion Stoica . 2017 . Clipper: A Low-Latency Online Prediction Serving System. In USENIX Symposium on Networked Systems Design and Implementation (NSDI). Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael J Franklin, Joseph E Gonzalez, and Ion Stoica. 2017. Clipper: A Low-Latency Online Prediction Serving System. In USENIX Symposium on Networked Systems Design and Implementation (NSDI)."},{"volume-title":"ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA).","author":"Janapa Vijay","key":"e_1_3_2_1_2_1","unstructured":"Vijay Janapa Reddi and et al. 2020. Mlperf inference benchmark . In ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA). Vijay Janapa Reddi and et al. 2020. Mlperf inference benchmark. In ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA)."},{"key":"e_1_3_2_1_3_1","volume-title":"INFaaS: Automated Model-less Inference Serving. In 2021 USENIX Annual Technical Conference (USENIX ATC).","author":"Romero Francisco","year":"2021","unstructured":"Francisco Romero , Qian Li , Neeraja J Yadwadkar , and Christos Kozyrakis . 2021 . INFaaS: Automated Model-less Inference Serving. In 2021 USENIX Annual Technical Conference (USENIX ATC). Francisco Romero, Qian Li, Neeraja J Yadwadkar, and Christos Kozyrakis. 2021. INFaaS: Automated Model-less Inference Serving. In 2021 USENIX Annual Technical Conference (USENIX ATC)."}],"event":{"name":"PPoPP '22: 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"Seoul Republic of Korea","acronym":"PPoPP '22"},"container-title":["Proceedings of the 14th Workshop on General Purpose Processing Using GPU"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3530390.3532735","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3530390.3532735","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3530390.3532735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:24Z","timestamp":1750183764000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3530390.3532735"}},"subtitle":["a scalable multi-GPU machine learning inference system and benchmarking suite"],"short-title":[],"issued":{"date-parts":[[2022,4,3]]},"references-count":3,"alternative-id":["10.1145\/3530390.3532735","10.1145\/3530390"],"URL":"https:\/\/doi.org\/10.1145\/3530390.3532735","relation":{},"subject":[],"published":{"date-parts":[[2022,4,3]]},"assertion":[{"value":"2022-05-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}