CADISHI: Fast parallel calculation of particle-pair distance histograms on CPUs and GPUs

TL;DR

CADISHI is a software package that enables fast, parallel calculation of particle-pair distance histograms on CPUs and GPUs, facilitating efficient analysis of spatial correlations in various scientific fields.

Contribution

It introduces optimized, parallel implementations of the histogram algorithm for CPUs and GPUs, supporting various boundary conditions and enabling high-throughput analysis of particle ensembles.

Findings

GPU implementations achieve up to 40 times faster histogramming rates than CPUs.

Supports orthorhombic and triclinic periodic boundary conditions.

Enables efficient processing of molecular dynamics trajectories with high resource utilization.

Abstract

We report on the design, implementation, optimization, and performance of the CADISHI software package, which calculates histograms of pair-distances of ensembles of particles on CPUs and GPUs. These histograms represent 2-point spatial correlation functions and are routinely calculated from simulations of soft and condensed matter, where they are referred to as radial distribution functions, and in the analysis of the spatial distributions of galaxies and galaxy clusters. Although conceptually simple, the calculation of radial distribution functions via distance binning requires the evaluation of $\mathcal{O}(N^2)$ particle-pair distances where $N$ is the number of particles under consideration. CADISHI provides fast parallel implementations of the distance histogram algorithm for the CPU and the GPU, written in templated C++ and CUDA. Orthorhombic and general triclinic periodic boxes are supported, in addition to the non-periodic case. The CPU kernels feature cache-blocking, vectorization and thread-parallelization to obtain high performance. The GPU kernels are tuned to exploit the memory and processor features of current GPUs, demonstrating histogramming rates of up to a factor 40 higher than on a high-end multi-core CPU. To enable high-throughput analyses of molecular dynamics trajectories, the compute kernels are driven by the Python-based CADISHI engine. It implements a producer-consumer data processing pattern and thereby enables the complete utilization of all the CPU and GPU resources available on a specific computer, independent of special libraries such as MPI, covering commodity systems up to high-end HPC nodes. Data input and output are performed efficiently via HDF5. (...) The CADISHI software is freely available under the MIT license.