.png){kind=icon}
.png){kind=icon}
Return
A parallel algorithm for the time-domain boundary element method in elastodynamics with mCCSR sparse storage
.png){kind=icon}
PRE
AI
W
陈
DOI：10.1016/j.advengsoft.2026.104190.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A high-performance parallel framework for elastodynamic TDBEM is developed based on the mixed cell compressed sparse row (mCCSR) format, fully exploiting block sparsity and local symmetry. • A quantitative task-load model is proposed to characterize the integration cost of different element types, enabling a dynamic partitioning scheme for balanced matrix generation. • A hybrid dynamic/static parallel strategy is developed for matrix generation and solution stages, achieving robust scalability and high parallel efficiency for engineering-scale problems.
Keywords:
parallel computing
time-domain boundary element method
elastodynamics
sparse matrix storage
dynamic load balancing
Journal
IF:
5.7
Papers:
3.3K
Citations:
1.2W
Organization
Cited Papers