ScaLAPACK user's guide
LAPACK Users' guide (third ed.)
LAPACK Users' guide (third ed.)
SuperLU_DIST: A scalable distributed-memory sparse direct solver for unsymmetric linear systems
ACM Transactions on Mathematical Software (TOMS)
A column pre-ordering strategy for the unsymmetric-pattern multifrontal method
ACM Transactions on Mathematical Software (TOMS)
Solving unsymmetric sparse systems of linear equations with PARDISO
Future Generation Computer Systems - Special issue: Selected numerical algorithms
A parallel hybrid banded system solver: the SPIKE algorithm
Parallel Computing - Parallel matrix algorithms and applications (PMAA'04)
A Parallel Implementation of Electron-Phonon Scattering in Nanoelectronic Devices up to 95k Cores
Proceedings of the 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis
Atomistic nanoelectronic device engineering with sustained performances up to 1.44 PFlop/s
Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis
Hi-index | 0.00 |
Physics-based simulation of electron transport in nanoelectronic devices requires the solution of thousands of highly complex equations to obtain the output characteristics of one single input voltage. The only way to obtain a complete set of bias points within a reasonable amount of time is the recourse to supercomputers offering several hundreds to thousands of cores. To profit from the rapidly increasing availability of such machines we have developed a state-of-the-art quantum mechanical transport simulator dedicated to nanodevices and working with four levels of parallelism. Using these four levels we demonstrate that an almost ideal scaling of the walltime up to 32768 processors with a parallel efficiency of 86% is reached in the simulation of realistically extended and gated field-effect transistors. Obtaining the current characteristics of these devices is reduced to some hundreds of seconds instead of days on a small cluster or months on a single CPU.