AITurbo: Unified Compute Allocation for Partial Predictable Training in Commodity Clusters

Laiping Zhao, Fangshu Li, Wenyu Qu, Kunlin Zhan, Qingman Zhang. AITurbo: Unified Compute Allocation for Partial Predictable Training in Commodity Clusters. In Erwin Laure, Stefano Markidis, Ana Lucia Verbanescu, Jay F. Lofstead, editors, HPDC '21: The 30th International Symposium on High-Performance Parallel and Distributed Computing, Virtual Event, Sweden, June 21-25, 2021. pages 133-145, ACM, 2021. [doi]

Abstract

Abstract is missing.