X S Li 2008 J. Phys.: Conf. Ser. 125 012079 doi:10.1088/1742-6596/125/1/012079
X S Li
Show affiliationsThe 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 included both Pthreads and MPI implementations in this study and found that the Pthreads implementation consistently delivers good performance and that a left-looking algorithm is usually superior.
07.05.Bx Computer systems: hardware, operating systems, computer languages, and utilities
Issue 1 (2008)
X S Li 2008 J. Phys.: Conf. Ser. 125 012079
D V Vassilevich 2009 Class. Quantum Grav. 26 145010
Parthapratim Biswas et al 2007 J. Phys.: Condens. Matter 19 455202
M Krug et al 2009 New J. Phys. 11 105051
S Satake et al 2009 J. Phys.: Conf. Ser. 191 012012
Seung-Bok Choi et al 2009 Smart Mater. Struct. 18 125010
J D Alexander et al 2009 J. Phys. B: At. Mol. Opt. Phys. 42 141004
Songbai Chen and Jiliang Jing 2009 Class. Quantum Grav. 26 155006
S R Gocić et al 2009 J. Phys. D: Appl. Phys. 42 212001
Chris J Milne et al 2009 J. Phys.: Conf. Ser. 190 012052