Factors impacting performance of multithreaded sparse triangular solve.
Conference
·
OSTI ID:1012739
As computational science applications grow more parallel with multi-core supercomputers having hundreds of thousands of computational cores, it will become increasingly difficult for solvers to scale. Our approach is to use hybrid MPI/threaded numerical algorithms to solve these systems in order to reduce the number of MPI tasks and increase the parallel efficiency of the algorithm. However, we need efficient threaded numerical kernels to run on the multi-core nodes in order to achieve good parallel efficiency. In this paper, we focus on improving the performance of a multithreaded triangular solver, an important kernel for preconditioning. We analyze three factors that affect the parallel performance of this threaded kernel and obtain good scalability on the multi-core nodes for a range of matrix sizes.
- Research Organization:
- Sandia National Laboratories
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC04-94AL85000
- OSTI ID:
- 1012739
- Report Number(s):
- SAND2010-2936C
- Country of Publication:
- United States
- Language:
- English
Similar Records
Factors impacting performance of multithreaded triangular solve.
Highly scalable distributed-memory sparse triangular solution algorithms.
Test suite for evaluating performance of multithreaded MPI communication.
Conference
·
Tue Jun 01 00:00:00 EDT 2010
·
OSTI ID:1020371
Highly scalable distributed-memory sparse triangular solution algorithms.
Conference
·
Sun Dec 31 23:00:00 EST 2017
·
OSTI ID:1602817
Test suite for evaluating performance of multithreaded MPI communication.
Journal Article
·
Mon Nov 30 23:00:00 EST 2009
· Parallel Comput.
·
OSTI ID:977356