Separable projection integrals for higher-order correlators of the cosmic microwave sky: acceleration by factors exceeding 100

DOI10.1016/J.JCP.2016.01.019zbMATH Open1349.85001arXiv1503.08809OpenAlexW1502604064MaRDI QIDQ2375009FDOQ2375009

Authors: J. P. Briggs, S. J. Pennycook, J. R. Fergusson, Juha Jäykkä, E. P. S. Shellard 

Publication date: 5 December 2016

Published in: Journal of Computational Physics (Search for Journal in Brave)

Abstract: We present a case study describing efforts to optimise and modernise "Modal", the simulation and analysis pipeline used by the Planck satellite experiment for constraining general non-Gaussian models of the early universe via the bispectrum (or three-point correlator) of the cosmic microwave background radiation. We focus on one particular element of the code: the projection of bispectra from the end of inflation to the spherical shell at decoupling, which defines the CMB we observe today. This code involves a three-dimensional inner product between two functions, one of which requires an integral, on a non-rectangular domain containing a sparse grid. We show that by employing separable methods this calculation can be reduced to a one-dimensional summation plus two integrations, reducing the overall dimensionality from four to three. The introduction of separable functions also solves the issue of the non-rectangular sparse grid. This separable method can become unstable in certain cases and so the slower non-separable integral must be calculated instead. We present a discussion of the optimisation of both approaches. We show significant speed-ups of ~100x, arising from a combination of algorithmic improvements and architecture-aware optimisations targeted at improving thread and vectorisation behaviour. The resulting MPI/OpenMP hybrid code is capable of executing on clusters containing processors and/or coprocessors, with strong-scaling efficiency of 98.6% on up to 16 nodes. We find that a single coprocessor outperforms two processor sockets by a factor of 1.3x and that running the same code across a combination of both microarchitectures improves performance-per-node by a factor of 3.38x. By making bispectrum calculations competitive with those for the power spectrum (or two-point correlator) we are now able to consider joint analysis for cosmological science exploitation of new data.

Full work available at URL: https://arxiv.org/abs/1503.08809

Recommendations

• The covariant perturbative approach to cosmic microwave background anisotropies
• Separating the kinetic Sunyaev-Zel'dovich effect from primary cosmic microwave background fluctuations
• A convolution integral representation of the thermal Sunyaev Zel dovich effect
• Diffuse source separation in CMB observations
• Towards a fast, model-independent cosmic microwave background bispectrum estimator
• CMB anisotropies at all orders: the non-linear Sachs-Wolfe formula

zbMATH Keywords

cosmologymany-corenested parallelismxeon phi

Mathematics Subject Classification ID

Packaged methods for numerical algorithms (65Y15) Software, source code, etc. for problems pertaining to astronomy and astrophysics (85-04)

Cites Work

• Wavelets on the n-sphere and related manifolds
• Fast and accurate computation of Gauss-Legendre and Gauss-Jacobi quadrature nodes and weights
• The needlets bispectrum

Uses Software

• MPI
• Intel TBB
• FastGaussQuadrature

This page was built for publication: Separable projection integrals for higher-order correlators of the cosmic microwave sky: acceleration by factors exceeding 100

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2375009)