Publication | Closed Access
VASP hits the memory wall: Processors efficiency comparison
29
Citations
21
References
2019
Year
EngineeringGpu BenchmarkingComputer ArchitectureProcessor ArchitectureElectronic StructureMolecular DynamicsGpu ComputingMulti-channel Memory ArchitectureMemory WallEfficient Vasp CalculationsParallel ComputingPhysicsComputer EngineeringComputer ScienceNvidia Tesla P100Virtual MemoryComputational PhysicsGpu ArchitectureHardware AccelerationParallel Programming
Summary First‐principles calculations of electronic structure have been one of the most important classes of supercomputer applications for a long time. In this paper, we consider VASP as a de facto standard tool for density functional theory calculations widely used in materials science, condensed matter research, and other related fields. The choice of hardware for the efficient VASP calculations is not easy because of the large number of processor types available. We use the benchmark metric that is based on the balance of the peak floating point performance and the memory bandwidth. This metric gives us the possibility to compare different types of processors. We consider time‐to‐solution and energy‐to‐solution criteria and compare different Intel, AMD, and ARM 64‐bit CPUs and hybrid CPU‐GPU systems based on Nvidia Tesla P100.
| Year | Citations | |
|---|---|---|
Page 1
Page 1