This article consists of a collection of slides from the author's conference presentation on the special features, system design and architectures, mobile graphics and processing capabilities, and targeted markets for NVIDIA's Tegra K1 family of system-on-chip products.

Direct volume rendering (DVR) algorithms do not generate intermediate geometry to create a visualization, yet they produce countless variations in the resulting images. Therefore, comparative studies are essential for objective interpretation. Even though image and data level comparison metrics are available, it is still difficult to compare results because of the numerous rendering parameters and algorithm specifications involved. Most of the previous comparison methods use information from the final rendered images only. We overcome limitations of image level comparisons with our data level approach using intermediate rendering information. We provide a list of rendering parameters and algorithm specifications to guide comparison studies. We extend Williams and Uselton's rendering parameter list with algorithm specification items and provide guidance on how to compare algorithms. Real data are often too complex to study algorithm variations with confidence. Most of the analytic test data sets reported are often useful only for a limited feature of DVR algorithms. We provide simple and easily reproducible test data sets, a checkerboard and a ramp, that can make clear differences in a wide range of algorithm variations. With data level metrics, our test data sets make it possible to perform detailed comparison studies. A number of examples illustrate how to use these tools.

Managing scientific data is a challenging task, and many of the problems it presents have yet to be adequately solved. The Real-time Environmental Information Network and Analysis System (REINAS) is an operational solution to the problem of collecting and distributing environmental data in a real-time context, as well as supporting data acquisition, retrieval, visualization and long-term data maintenance. The system is built around one or more databases and has been developed to support both real-time and retrospective regional scale environmental science. Continuous real-time data is acquired from dispersed sensors and input to a logically integrated but physically distributed system. The database engine provides a powerful structure to handle data management, but current database technology can have difficulty meeting the performance requirements that a large real-time environmental system demands. The REINAS architecture and current status is described in detail, including the challenges that were addressed in the construction of an operational system which includes a regional wireless instrumentation network comprised of over 200 instrument platforms and 1500 sensor streams producing real-time data of interest to thousands of users.

In this paper we present a new approach in the compression of multispectral images. It is based on the merging of two processing tools, namely Karhunen-Loeve transform (KLT) as a spectral decorrelator, and object based image coding schemes. The potential use of the principal components analysis in multispectral imagery is described and it is used to perform a multispectral segmentation. This segmentation is taken as the basis for a specific spectral decorrelation for each segmented class. The resulting eigen images present lower variance than those obtained with classical KLT approaches. Each of the eigen regions is coded spatially using a shape adaptive DCT algorithm. The method outperforms non-region multispectral KLT+DCT schemes as well as JPEG, while adding region based functionalities.

Uncertainty or errors are introduced in fluid flow data as the data is acquired, transformed and rendered. Although researchers are aware of these uncertainties, little has been done to incorporate them in the existing visualization systems for fluid flow. In the absence of integrated presentation of data and its associated uncertainty, the analysis of the visualization is incomplete at best and may lead to inaccurate or incorrect conclusions. The article presents UFLOW-a system for visualizing uncertainty in fluid flow. Although there are several sources of uncertainties in fluid flow data, in this work, we focus on uncertainty arising from the use of different numerical algorithms for computing particle traces in a fluid flow. The techniques that we have employed to visualize uncertainty in fluid flow include uncertainty glyphs, flow envelopes, animations, priority sequences, twirling batons of trace viewpoints, and rakes. These techniques are effective in making the users aware of the effects of different integration methods and their sensitivity, especially near critical points in the flow field.

We investigate cache write generate, our cache mode invention. We demonstrate that for parallel image processing applications, the new mode improves main memory bandwidth, CPU efficiency, cache hits, and cache latency. We use register level simulations validated by the UW-Proteus system. Many memory, cache, and processor configurations are evaluated.

Environmental data have inherent uncertainty which is often ignored in visualization. Meteorological stations and doppler radars, including their time series averages, have a wealth of uncertainty information that traditional vector visualization methods such as meteorological wind barbs and arrow glyphs simply ignore. We have developed a new vector glyph to visualize uncertainty in winds and ocean currents. Our approach is to include uncertainty in direction and magnitude, as well as the mean direction and length, in vector glyph plots. Our glyph shows the variation in uncertainty, and provides fair comparisons of data from instruments, models, and time averages of varying certainty. We also define visualizations that incorporate uncertainty in an unambiguous manner as verity visualization. We use both quantitative and qualitative methods to compare our glyphs to traditional ones. Subjective comparison tests with experts are provided, as well as objective tests, where the information density of our new glyphs and traditional glyphs are compared. The design of the glyph and numerous examples using environmental data are given. We show enhanced visualizations, data together with their uncertainty information, that may improve understanding of environmental vector field data quality.

Reconstruction is used frequently in visualization of one, two, and three dimensional data. Data uncertainty is typically ignored, and a deficiency of many interpolation schemes is smoothing which may indicate features or characteristics of the data that are not there. The author investigates the use of iterated function systems (IFS's) for interpolation. He shows new derivations for fractal interpolation in two and three dimensional scalar data, and new point and polytope rendering algorithms with tremendous speed advantages over ray tracing. The interpolations may be used to give an indication of the uncertainty of the data, statistically represent the data at a variety of scales, allow tunability from the data, and may allow more accurate data analysis.

The Proteus architecture is a highly parallel MIMD, multiple instruction, multiple-data machine, optimized for large granularity tasks such as machine vision and image processing. The system can achieve 20 Giga-flops (80 Giga-flops peak). It accepts data via multiple serial links at a rate of up to 640 megabytes/second. The system employs a hierarchical reconfigurable interconnection network with the highest level being a circuit switched Enhanced Hypercube serial interconnection network for internal data transfers. The system is designed to use 256 to 1024 RISC processors. The processors use one megabyte external Read/Write Allocating Caches for reduced multiprocessor contention. The system detects, locates, and replaces faulty subsystems using redundant hardware to facilitate fault tolerance.>

We present, Generate, a new cache write handling scheme that avoids unnecessary reads from main memory, reduces bus contention, and increases the available bandwidth of the memory. Cache Write Generate increases the amount of CPU execution and memory load/store overlap, and decreases the memory cycle time. We compare the performance of cache write generate with write around and write allocate in single processor and shared bus multiprocessors and demonstrate a speedup of 1.2 to 1.5 over allocate and write around.