Ever looked up in the sky and wondered where it all came from? Cosmologists are in the same boat, trying to understand how the Universe arrived at the structure we observe today. They use supercomputers to follow the fate of very small initial fluctuations in an otherwise uniform density. As time passes, gravity causes the small fluctuations to grow, eventually forming the complex structures that characterize the current Universe. The numerical simulations use tracer particles representing lumps of matter to carry out the calculations. The distribution of matter at early times is known only in a statistical sense so we can’t predict exactly where galaxies will show up in the sky. But quite accurate predictions can be made for how the galaxies are distributed in space, even with relatively simplified simulations.
As observations become increasingly detailed, the simulations need to become more detailed as well, requiring huge amounts of simulation particles. Today, top-notch simulation codes like the Hardware/Hybrid Accelerated Cosmology Code (HACC )  can follow more than half a trillion particles in a volume of more than 1 Gpc3 (1 cubic Gigaparsec. That’s a cube with sides 3.26 billion light years long) on the largest scale GPU-accelerated supercomputers like Titan at the Oak Ridge National Laboratory. The “Q Continuum” simulation  that Figure 1 shows is an example.
While simulating the Universe at this resolution is by itself a challenge, it is only half the job. The analysis of the simulation results is equally challenging. It turns out that GPUs can help with accelerating both the simulation and the analysis. In this post we’ll demonstrate how we use Thrust and CUDA to accelerate cosmological simulation and analysis and visualization tasks, and how we’re generalizing this work into libraries and toolkits for scientific visualization.
An object of great interest to cosmologists is the so-called “halo”. A halo is a high-density region hosting galaxies and clusters of galaxies, depending on the halo mass. The task of finding billions of halos and determining their centers is computationally demanding. Continue reading