1.1k citations · 4.5k across the 114 of their papers we have counts for
8 papers · 1 filter
Performance engineering for the Lattice Boltzmann method on GPGPUs: Architectural requirements and performance results
Johannes Habich, Christian Feichtinger, Harald Köstler +2
GPUs offer several times the floating point performance and memory bandwidth of current standard two socket CPU servers, e.g. NVIDIA C2070 vs. Intel Xeon Westmere X5650. The lattic…
Sparse matrix-vector multiplication on GPGPU clusters: A new storage format and a scalable implementation
Moritz Kreutzer, Georg Hager, Gerhard Wellein +3
Sparse matrix-vector multiplication (spMVM) is the dominant operation in many sparse solvers. We investigate performance properties of spMVM with matrices of various sparsity patte…
Domain decomposition and locality optimization for large-scale lattice Boltzmann simulations
Markus Wittmann, Thomas Zeiser, Georg Hager +1
We present a simple, parallel and distributed algorithm for setting up and partitioning a sparse representation of a regular discretized simulation domain. This method is scalable…
Comparison of different Propagation Steps for the Lattice Boltzmann Method
Markus Wittmann, Thomas Zeiser, Georg Hager +1
Several possibilities exist to implement the propagation step of the lattice Boltzmann method. This paper describes common implementations which are compared according to the numbe…
Metal-insulator transition in the Edwards model
H. Fehske, S. Ejima, G. Wellein +1
To understand how charge transport is affected by a background medium and vice versa we study a two-channel transport model which captures this interplay via a novel, effective fer…
Hybrid-parallel sparse matrix-vector multiplication with explicit communication overlap on current multicore-based systems
Gerald Schubert, Holger Fehske, Georg Hager +1
We evaluate optimized parallel sparse matrix-vector operations for several representative application areas on widespread multicore-based cluster configurations. First the single-s…
Pushing the limits for medical image reconstruction on recent standard multicore processors
Jan Treibig, Georg Hager, Hannes G. Hofmann +2
Volume reconstruction by backprojection is the computational bottleneck in many interventional clinical computed tomography (CT) applications. Today vendors in this field replace s…
LIKWID: Lightweight Performance Tools
Jan Treibig, Georg Hager, Gerhard Wellein
Exploiting the performance of today's microprocessors requires intimate knowledge of the microarchitecture as well as an awareness of the ever-growing complexity in thread and cach…