Fast Correlation Function Calculator -- A high-performance pair counting toolkit

Abstract

Context. A novel high-performance exact pair counting toolkit called Fast Correlation Function Calculator (FCFC) is presented, which is publicly available at https://github.com/cheng-zhao/FCFC. Aims. As the rapid growth of modern cosmological datasets, the evaluation of correlation functions with observational and simulation catalogues has become a challenge. High-efficiency pair counting codes are thus in great demand. Methods. We introduce different data structures and algorithms that can be used for pair counting problems, and perform comprehensive benchmarks to identify the most efficient ones for real-world cosmological applications. We then describe the three levels of parallelisms used by FCFC -- including SIMD, OpenMP, and MPI -- and run extensive tests to investigate the scalabilities. Finally, we compare the efficiency of FCFC against alternative pair counting codes. Results. The data structures and histogram update algorithms implemented in FCFC are shown to outperform alternative methods. FCFC does not benefit much from SIMD as the bottleneck of our histogram update algorithm is mostly cache latency. Nevertheless, the efficiency of FCFC scales well with the numbers of OpenMP threads and MPI processes, albeit the speedups may be degraded with over a few thousand threads in total. FCFC is found to be faster than most (if not all) other public pair counting codes for modern cosmological pair counting applications.

arXiv comment18 pages, 18 figures. The FCFC package is publicly available at https://github.com/cheng-zhao/FCFC

References in corpus (11)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• The cosmological simulation code GADGET-2
• The Baryon Oscillation Spectroscopic Survey of SDSS-III
• Large-Scale Structure of the Universe and Cosmological Perturbation Theory
• The SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Overview and Early Data
• Corrfunc --- A Suite of Blazing Fast Correlation Functions on the CPU
• Forward Modeling of Large-Scale Structure: An open-source approach with Halotools
• Computing the Three-Point Correlation Function of Galaxies in $\mathcal{O}(N^2)$ Time
• Detection of dark matter Skewness in the VIRMOS-DESCART survey: Implications for Ω_0
• ENCORE: An $\mathcal{O}(N_{\mathrm{g}}^2)$ Estimator for Galaxy $N$-Point Correlation Functions
• Fast n-point correlation functions and three-point lensing application

Cited by in corpus (8)

• Consistency of effective field theory analyses of the BOSS power spectrum
• Cosmological Constraints with Void Lensing I: the Simulation-Based Inference Framework
• Euclid preparation. 3-dimensional galaxy clustering in configuration space. Part I. 2-point correlation function estimation
• ELG$\times$LRG distribution through dark matter halo dynamics
• Cosmological constraints with the linear point from the BOSS survey
• Pair Counting without Binning -- A New Approach to Correlation Functions in Clustering Statistics
• cosmokdtree: a flexible OpenMP-parallelized k-d tree for computational astrophysics applications
• Probing gravity with non-linear clustering in redshift space