In this paper we present scaling results of a FFT library, FFTK, and a pseudospectral code, Tarang, on grid resolutions up to 819 2 3 grid using 65536 cores of Blue Gene/P and 196608 cores of Cray XC40 supercomputers . We observe that communication dominates computation, more so on the Cray XC40. The computation time scales as T comp ∼ p − 1 , and the communication time as T comm ∼ n − γ 2 with γ 2 ranging from 0.7 to 0.9 for Blue Gene/P, and from 0.43 to 0.73 for Cray XC40. FFTK, and the fluid and convection solvers of Tarang exhibit weak as well as strong scaling nearly up to 196608 cores of Cray XC40. We perform a comparative study of the performance on the Blue Gene/P and Cray XC40 clusters.

We present a technique for memory-efficient and time-efficient volume rendering of curvilinear adaptive mesh refinement data defined within extrudable computational spaces. One of the main challenges in the ray casting of curvilinear volumes is that a linear viewing ray in physical space will typically correspond to a curved ray in computational space. The proposed method utilizes a specialized representation of curvilinear space that provides for the compact representation of parameters for transformations between computational space and physical space, without requiring extensive preprocessing. By simplifying the representation of computational space positions using an extrusion of a profile surface, the requisite transformations can be greatly simplified. Our implementation achieves interactive rates with minimal load time and memory overhead using commodity graphics hardware with real-world data.

We have developed a threaded parallel data streaming approach using Globus to transfer multi-terabyte simulation data from a remote supercomputer to the scientistýs home analysis/visualization cluster, as the simulation executes, with negligible overhead. Data transfer experiments show that this concurrent data transfer approach is more favorable compared with writing to local disk and then transferring this data to be post-processed. The present approach is conducive to using the grid to pipeline the simulation with post-processing and visualization. We have applied this method to the Gyrokinetic Toroidal Code (GTC), a 3-dimensional particle-in-cell code used to study micro-turbulence in magnetic confinement fusion from first principles plasma theory.

One of the most fundamental issues in magnetic fusion research is the understanding of turbulent transport observed in present-day tokamak experiments. Plasma turbulence is very challenging from a theoretical point of view due to the nonlinearity and high dimensionality of the governing equations. Recent developments in algorithms along with the astounding advances in high performance computing now make first-principle particle simulations an important tool for improved understanding of such phenomena. Due to the five dimensional phase space (3 spatial, 2 velocity) and complex toroidal geometry, visualization is crucial for interpreting such simulation data. This paper discusses how visualization tools are currently used and what new physics has been elucidated, along with what can be learned about tokamak turbulence through the interplay between theory, simulation and visualization.>