Parallel computational steering for HPC applications using HDF5 files in distributed shared memory.

Interfacing a GUI driven visualization/analysis package to an HPC application enables a supercomputer to be used as an interactive instrument. We achieve this by replacing the IO layer in the HDF5 library with a custom driver which transfers data in parallel between simulation and analysis. Our implementation using ParaView as the interface, allows a flexible combination of parallel simulation, concurrent parallel analysis, and GUI client, either on the same or separate machines. Each MPI job may use different core counts or hardware configurations, allowing fine tuning of the amount of resources dedicated to each part of the workload. By making use of a distributed shared memory file, one may read data from the simulation, modify it using ParaView pipelines, write it back, to be reused by the simulation (or vice versa). This allows not only simple parameter changes, but complete remeshing of grids, or operations involving regeneration of field values over the entire domain. To avoid the problem of manually customizing the GUI for each application that is to be steered, we make use of XML templates that describe outputs from the simulation (and inputs back to it) to automatically generate GUI controls for manipulation of the simulation.

Cerebrospinal fluid dynamics in the human cranial subarachnoid space: an overlooked mediator of cerebral disease. I. Computational model.

Abnormal cerebrospinal fluid (CSF) flow is suspected to be a contributor to the pathogenesis of neurodegenerative diseases such as Alzheimer's through the accumulation of toxic metabolites, and to the malfunction of intracranial pressure regulation, possibly through disruption of neuroendocrine communication. For the understanding of transport processes involved in either, knowledge of in vivo CSF dynamics is important. We present a three-dimensional, transient, subject-specific computational analysis of CSF flow in the human cranial subarachnoid space (SAS) based on in vivo magnetic resonance imaging. We observed large variations in the spatial distribution of flow velocities with a temporal peak of 5 cm s(-1) in the anterior SAS and less than 4 mm s(-1) in the superior part. This could reflect dissimilar flushing requirements of brain areas that may show differences in susceptibility to pathological CSF flow. Our methods can be used to compare the transport of metabolites and neuroendocrine substances in healthy and diseased brains.

Predictor-corrector schemes for visualization of smoothed particle hydrodynamics data.

In this paper we present a method for vortex core line extraction which operates directly on the smoothed particle hydrodynamics (SPH) representation and, by this, generates smoother and more (spatially and temporally) coherent results in an efficient way. The underlying predictor-corrector scheme is general enough to be applied to other line-type features and it is extendable to the extraction of surfaces such as isosurfaces or Lagrangian coherent structures. The proposed method exploits temporal coherence to speed up computation for subsequent time steps. We show how the predictor-corrector formulation can be specialized for several variants of vortex core line definitions including two recent unsteady extensions, and we contribute a theoretical and practical comparison of these. In particular, we reveal a close relation between unsteady extensions of Fuchs et al. and Weinkauf et al. and we give a proof of the Galilean invariance of the latter. When visualizing SPH data, there is the possibility to use the same interpolation method for visualization as has been used for the simulation. This is different from the case of finite volume simulation results, where it is not possible to recover from the results the spatial interpolation that was used during the simulation. Such data are typically interpolated using the basic trilinear interpolant, and if smoothness is required, some artificial processing is added. In SPH data, however, the smoothing kernels are specified from the simulation, and they provide an exact and smooth interpolation of data or gradients at arbitrary points in the domain.

Time dependent processing in a parallel pipeline architecture.

Pipeline architectures provide a versatile and efficient mechanism for constructing visualizations, and they have been implemented in numerous libraries and applications over the past two decades. In addition to allowing developers and users to freely combine algorithms, visualization pipelines have proven to work well when streaming data and scale well on parallel distributed-memory computers. However, current pipeline visualization frameworks have a critical flaw: they are unable to manage time varying data. As data flows through the pipeline, each algorithm has access to only a single snapshot in time of the data. This prevents the implementation of algorithms that do any temporal processing such as particle tracing; plotting over time; or interpolation, fitting, or smoothing of time series data. As data acquisition technology improves, as simulation time-integration techniques become more complex, and as simulations save less frequently and regularly, the ability to analyze the time-behavior of data becomes more important. This paper describes a modification to the traditional pipeline architecture that allows it to accommodate temporal algorithms. Furthermore, the architecture allows temporal algorithms to be used in conjunction with algorithms expecting a single time snapshot, thus simplifying software design and allowing adoption into existing pipeline frameworks. Our architecture also continues to work well in parallel distributed-memory environments. We demonstrate our architecture by modifying the popular VTK framework and exposing the functionality to the ParaView application. We use this framework to apply time-dependent algorithms on large data with a parallel cluster computer and thereby exercise a functionality that previously did not exist.