Cataloging the Visible Universe through Bayesian Inference at Petascale

TL;DR

This paper presents Celeste, a Bayesian inference tool in Julia, capable of processing 55 TB of astronomical imaging data at petascale speed to generate detailed celestial catalogs.

Contribution

It introduces a high-performance, scalable Bayesian inference framework in Julia that efficiently processes massive astronomical datasets at petascale.

Findings

Achieved 1.54 DP PFLOP/s peak performance on supercomputing hardware.

Processed 178 TB of data in 14.6 minutes across 8192 nodes.

Successfully optimized parameters for 188 million celestial objects.

Abstract

Astronomical catalogs derived from wide-field imaging surveys are an important tool for understanding the Universe. We construct an astronomical catalog from 55 TB of imaging data using Celeste, a Bayesian variational inference code written entirely in the high-productivity programming language Julia. Using over 1.3 million threads on 650,000 Intel Xeon Phi cores of the Cori Phase II supercomputer, Celeste achieves a peak rate of 1.54 DP PFLOP/s. Celeste is able to jointly optimize parameters for 188M stars and galaxies, loading and processing 178 TB across 8192 nodes in 14.6 minutes. To achieve this, Celeste exploits parallelism at multiple levels (cluster, node, and thread) and accelerates I/O through Cori's Burst Buffer. Julia's native performance enables Celeste to employ high-level constructs without resorting to hand-written or generated low-level code (C/C++/Fortran), and yet achieve petascale performance.