Sparse LU Factorizations on Multicore Platforms
Xiaoye Sherry Li (Lawrence Berkeley National Laboratory)
Abstract:
The Chip Multiprocessor (CMP) will be the basic building block for
computer systems ranging from laptops to supercomputers.
New software developments at all levels are needed to fully utilize
these systems. In this work, we evaluate performance of different
high-performance sparse LU factorization and triangular solution
algorithms on several representative multicore machines.
We include both pthreads and MPI implementations in this study,
and found that the pthreads implementation consistently delivers good
performance and a left-looking algorithm is usually superior.
Keywords:
Numerical Algorithms for CS&E, parallel architectures, sparse matrix computations,
