High-Performance Computing Applications for Visualization of Large Microscopy Images - High-Throughput Image Reconstruction and Analysis - page 315

The network-centric architecture of SAGE allows users to simultaneously run
various compute intensive applications, such as 3D volume rendering, 2D montage
viewers, and video streaming on local or remote computers. The environment also
supports collaboration where the pixels from applications can be displayed at mul-
tiple sites simultaneously using network multicast or broadcast. Since the resolution
of most graphical applications that run on these displays is very high, streaming
requires a lot of bandwidth. For example, an uncompressed 30-fps HDTV stream
with a resolution of 1,920 1.5 Gbps. The OptIPuter infras-

tructure plays a crucial role in enabling this distributed computing architecture.
Rendering and compute clusters can access the high-resolution displays over fast
optical networks and stream their pixel frame buffers.
SAGE's streaming architecture is designed so that the output of arbitrary

× 1,080 requires ∼

M R pixel display

screens [10], allowing user-definable layouts on the display. The dynamic pixel
routing capability lets users freely move and resize each application's imagery over
tiled displays in run-time, tightly synchronizing multiple component streams to
form a single virtual stream.

N pixel rendering cluster nodes can be streamed to Q

× ×

14.5.2 COVISE (Collaborative Visualization and Simulation Environment)
COVISE [28] was originally been developed at the High Performance Computing
Center Stuttgart (HLRS), and has been commercialized by the Stuttgart based
VISENSO GmbH. It is a toolkit to integrate several stages of a scientific or technical
application such as grid-generation, simulation, data import, post-processing, and
visualization. Each step is implemented as a module. Using a visual user interface,
these modules can be connected to a data flow network.
Each of the computational and I/O modules in this workflow can reside on
a different computer. This allows distributing the work load among different ma-
chines. For instance, the pre- and post-processing modules can run on a visual-
ization server, while the simulation runs on a remote supercomputer. The display
modules can run on the workstation of a user, or on a visualization cluster driving
a multiscreen visualization environment.
COVISE's virtual reality rendering module OpenCOVER can run on a variety
of interactive displays and environments. Figure 14.10 shows COVISE managing
the 15-tile rear-projected StarCAVE VR environment. It can even be used on a
single computer with a mouse, but then the user cannot take advantage of its im-
mersive capabilities. OpenCOVER is ideally run on tracked stereo environment,
using 3D pointing devices. OpenCOVER uses the OpenSceneGraph API for its
3D rendering, which is an object-oriented framework on top of OpenGL. Open-
COVER has the ability to link multiple virtual environments together over the
Internet, allowing for collaborative work between users in different buildings of
a campus, or even on different continents. OpenCOVER is an open interface, in
that the application programmer can write plug-in modules in C++ to create cus-
tomized virtual reality applications, using COVISE's support of a large variety
of virtual reality input and output devices, as well as interaction handling and
network communication algorithms.