Learning Reduced Order Dynamics via Geometric Representations
Imran Nasim, Melanie Weber
SCML 2024
The Malleable Parallel Task Scheduling problem (MPTS) is an extension of one of the most classic scheduling problems (P∥C max). The only difference is that for MPTS, each task can be processed simultaneously by more than one processor. Such flexibility could dramatically reduce the makespan, but greatly increase the difficulty for solving the problem. By carefully analyzing some existing algorithms for MPTS, we find each of them suitable for some specific cases, but none is effective enough for all cases. Based on such observations, we introduce some optimization algorithms and improving techniques for MPTS, with their performance analyzed in theory. Combining these optimization algorithms and improving techniques gives rise to our novel scheduling algorithm OCM (Optimizations Combined for MPTS), a 2-approximation algorithm for MPTS. Extensive simulations on random datasets and SPLASH-2 benchmark reveal that for all cases, schedules produced by OCM have smaller makespans, compared with other existing algorithms. © 2012 Elsevier Inc. All rights reserved.
Imran Nasim, Melanie Weber
SCML 2024
Guo-Jun Qi, Charu Aggarwal, et al.
IEEE TPAMI
Seung Gu Kang, Jeff Weber, et al.
ACS Fall 2023
Ella Barkan, Ibrahim Siddiqui, et al.
Computational And Structural Biotechnology Journal