Hybrid MPI-thread parallelization of adaptive mesh operations
详细信息 查看全文
- 作者：Dan Ibanez ; dan.a.ibanez@gmail.com" class="auth_mail" title="E-mail the corresponding author ; ibaned@rpi.edu" class="auth_mail" title="E-mail the corresponding author ; ; Ian Dunn dunni@rpi.edu" class="auth_mail" title="E-mail the corresponding author ; Mark S. Shephard shephard@rpi.edu" class="auth_mail" title="E-mail the corresponding author
- 关键词：Hybrid system ; Shared memory ; Parallel programming models ; MPI ; Termination detection ; Non-blocking
- 刊名：Parallel Computing
- 出版年：2016
- 出版时间：February 2016
- 年：2016
- 卷：52
- 期：Complete
- 页码：133-143
- 全文大小：971 K
文摘
- •
Development of a hybrid MPI-thread programming system called PCU.
- •
Inter-thread message passing, including non-blocking collectives.
- •
A novel, scalable termination detection technique for communication rounds.
- •
Hybrid parallel scalability to 16K cores on an IBM Blue Gene/Q.