2013
DOI: 10.1109/tcad.2012.2217964
|View full text |Cite
|
Sign up to set email alerts
|

NICSLU: An Adaptive Sparse Matrix Solver for Parallel Circuit Simulation

Abstract: The sparse matrix solver has become a bottleneck in simulation program with integrated circuit emphasis (SPICE)-like circuit simulators. It is difficult to parallelize the solver because of the high data dependency during the numeric LU factorization and the irregular structure of circuit matrices. This paper proposes an adaptive sparse matrix solver called NICSLU, which uses a multithreaded parallel LU factorization algorithm on shared-memory computers with multicore/multisocket central processing units to ac… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
33
0

Year Published

2013
2013
2024
2024

Publication Types

Select...
4
4
2

Relationship

2
8

Authors

Journals

citations
Cited by 69 publications
(33 citation statements)
references
References 47 publications
0
33
0
Order By: Relevance
“…Therefore for large circuits the solver step (1.5) is the most dominant part of the Newton loop and was the subject of several research work. In several publications [20][21][22][23] the authors present various methods to speed up and to parallelize the linear solver step in the inner loop. These approaches are limited not just by Amdahl's law for parallelization, but they also have limited speedup capability due to their pure linear algebra view on the problem [10].…”
Section: Q(x(t K )) -Q(x(t K-1 ))mentioning
confidence: 99%
“…Therefore for large circuits the solver step (1.5) is the most dominant part of the Newton loop and was the subject of several research work. In several publications [20][21][22][23] the authors present various methods to speed up and to parallelize the linear solver step in the inner loop. These approaches are limited not just by Amdahl's law for parallelization, but they also have limited speedup capability due to their pure linear algebra view on the problem [10].…”
Section: Q(x(t K )) -Q(x(t K-1 ))mentioning
confidence: 99%
“…LU factorizations are performed using NICSLU [9], Eigen package is employed for matrix multiplications [10], and LP problems are solved by Mosek optimization software [11]. To evaluate the performance of our approach, four IBM PG benchmarks for transient analysis [12] are utilized.…”
Section: A Experimental Setupmentioning
confidence: 99%
“…To solve an equation Ax = b, the CHOLMOD solver first decomposes the coefficient matrix A into L L T and then executes back substitutions to obtain the solution. In the global network simulation, a recently released NICS-LU [24] simulator is adopted.…”
Section: A Overall Flow Of Hierarchical Simulationmentioning
confidence: 99%