Implementation and performance evaluation of a communication-avoiding GMRES method for stencil-based code on GPU cluster

Matsumoto, Kazuya; Idomura, Yasuhiro; Ina, Takuya; Mayumi, Akie; Yamada, S.

doi:10.1007/s11227-019-02983-7

Cited by 4 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, CFD solvers that are efficient on CPUs have been coupled with accelerator-enhanced DEM solvers [15,16]. Linear solvers that use scalable multi-grid [17] and Krylov Subspace methods [18] have now been demonstrated to show superior performance on GPU accelerators. MFiX-Exa, the software employed in this work, is an emerging CFD-DEM solver that utilizes GPU acceleration for both continuum and particle solves within a hybrid MPI+GPU parallelism framework.…”

Section: Introductionmentioning

confidence: 99%

Performance comparison of CFD-DEM solver MFiX-Exa, on GPUs and CPUs

Lao¹,

Holt²,

Vaidhynathan³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present computational performance comparisons of gas-solid simulations performed on current CPU and GPU architectures using MFiX Exa, a CFD-DEM solver that leverages hybrid CPU+GPU parallelism. A representative fluidized bed simulation with varying particle numbers from 2 to 67 million is used to compare serial and parallel performance. A single GPU was observed to be about 10 times faster compared to a single CPU core. The use of 3 GPUs on a single compute node was observed to be 4x faster than using all 64 CPU cores. We also observed that using an error controlled adaptive time stepping scheme for particle advance provided a consistent 4x speedup on both CPUs and GPUs. Weak scaling results indicate superior parallel efficiencies when using GPUs compared to CPUs for the problem sizes studied in this work.

show abstract