A Picture Is Worth a Thousand Numbers—Enhancing Cube’s Analysis Capabilities with Plugins

Knobloch, Michael; Saviankou, Pavel; Schlütter, Marc; Visser, A.C.; Mohr, Bernd

doi:10.1007/978-3-030-66057-4_13

Cited by 2 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is worth digging deeper with the tools at hand. Profiling showed that the algorithm outlined in A high-level overview of the parallel performance can be gained with the Advisor mode of Cube [20]. This prints the efficiency metrics developed in the POP project 4 for the entire execution or an arbitrary phase of the application.…”

Section: First Measurement Attemptsmentioning

confidence: 95%

See 1 more Smart Citation

Using performance analysis tools for parallel-in-time integrators -- Does my time-parallel code do what I think it does?

Speck,

Knobloch,

Lührs

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

While many ideas and proofs of concept for parallel-in-time integration methods exists, the number of large-scale, accessible time-parallel codes is rather small. This is often due to the apparent or subtle complexity of the algorithms and the many pitfalls awaiting developers of parallel numerical software. One example of such a time-parallel code is pySDC, which implements, among others, the parallel full approximation scheme in space and time (PFASST). Inspired by nonlinear multigrid ideas, PFASST allows to integrate multiple time-steps simultaneously using a space-time hierarchy of spectral deferred corrections. In this paper we demonstrate the application of performance analysis tools to the PFASST implementation pySDC. We aim to answer whether the code works as intended and whether the time-parallelization is as efficient as expected. Tracing the path we took for this work, we highlight the obstacles encountered, describe remedies and explain the sometimes surprising findings made possible by the tools. Although focusing only on a single implementation of a particular parallel-in-time integrator, we hope that our results and in particular the way we obtained them are a blueprint for other time-parallel codes.

show abstract

Section: First Measurement Attemptsmentioning

confidence: 95%

“…The CubeGUI is highly customizable and extendable. It provides a plugin interface to add new analysis capabilities [20] and an integrated domain-specific language called CubePL to manipulate CUBE metrics [31]. Fig.…”

Section: Cubementioning

confidence: 99%

Using performance analysis tools for parallel-in-time integrators -- Does my time-parallel code do what I think it does?

Speck,

Knobloch,

Lührs

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In general, efficiencies 0.8 are considered acceptable, while lower values signal performance concerns that warrant further investigation. We use the following open-source tools: Score-P [32] for profiling and tracing, Scalasca [26] for extended analyses, and CUBE [31] for presentation. 4 0.92 0.96 0.42 ++ Transfer Efficiency (TE) 5 0.99 1.00 0.97 1 Parallel efficiency is the ratio of mean computation time to total runtime of all processes 2 Load balance is the mean/maximum ratio of computation time outside of MPI 3 Communication efficiency is the ratio of maximum computation time to total runtime.…”

mentioning

confidence: 99%

A matrix-free parallel solution method for the three-dimensional heterogeneous Helmholtz equation

Chen,

Dwarka,

Vuik

2024

etna

View full text Add to dashboard Cite

The Helmholtz equation is related to seismic exploration, sonar, antennas, and medical imaging applications. It is one of the most challenging problems to solve in terms of accuracy and convergence due to the scalability issues of the numerical solvers. For 3D large-scale applications, high-performance parallel solvers are also needed. In this paper, a matrix-free parallel iterative solver is presented for the three-dimensional (3D) heterogeneous Helmholtz equation. We consider the preconditioned Krylov subspace methods for solving the linear system obtained from finite-difference discretization. The Complex Shifted Laplace Preconditioner (CSLP) is employed since it results in a linear increase in the number of iterations as a function of the wavenumber. The preconditioner is approximately inverted using one parallel 3D multigrid cycle. For parallel computing, the global domain is partitioned blockwise. The matrix-vector multiplication and preconditioning operator are implemented in a matrix-free way instead of constructing large, memory-consuming coefficient matrices. Numerical experiments of 3D model problems demonstrate the robustness and outstanding strong scaling of our matrix-free parallel solution method. Moreover, the weak parallel scalability indicates our approach is suitable for realistic 3D heterogeneous Helmholtz problems with minimized pollution error.

show abstract

A Picture Is Worth a Thousand Numbers—Enhancing Cube’s Analysis Capabilities with Plugins

Cited by 2 publications

References 12 publications

Using performance analysis tools for parallel-in-time integrators -- Does my time-parallel code do what I think it does?

Using performance analysis tools for parallel-in-time integrators -- Does my time-parallel code do what I think it does?

A matrix-free parallel solution method for the three-dimensional heterogeneous Helmholtz equation

Contact Info

Product

Resources

About