This paper presents a divide-and-conquer ray-traced volume rendering algorithm and a parallel image compositing method, along with their implementation and performance on the Connection Machine CM-5, and networked wor...
详细信息
This paper presents a divide-and-conquer ray-traced volume rendering algorithm and a parallel image compositing method, along with their implementation and performance on the Connection Machine CM-5, and networked workstations. This algorithm distributes both the data and the computations to individual processing units to achieve fast, high-quality rendering of high-resolution data. The volume data, once distributed, is left intact. The processing nodes perform local raytracing of their subvolume concurrently. No communication between processing units is needed during this locally ray-tracing process. A subimage is generated by each processing unit and the final image is obtained by compositing subimages in the proper order, which can be determined a priori. Test results on the CM-5 and a group of networked workstations demonstrate the practicality of our rendering algorithm and compositing method.
This paper presents a new multicomputer polygon rendering algorithm that is specialized for interactive applications. The algorithm differs from previous algorithms in two ways. First, it load balances the rasterizati...
详细信息
This paper presents a new multicomputer polygon rendering algorithm that is specialized for interactive applications. The algorithm differs from previous algorithms in two ways. First, it load balances the rasterization once per frame, instead of as the frame progresses, using the previous frame's distribution of polygons on the screen as input to the load-balancing algorithm. Second, it uses a new message sending scheme that reduces the number of messages required. These characteristics mean that the algorithm only requires global synchronization between frames, which allows for higher frame rates. The algorithm was selected using a simulator which confirmed that using the previous frame's polygon distribution on the screen is nearly as good as using the current frame's distribution. The algorithm is implemented on Caltech's Intel Touchstone Delta, a 512 processor multicomputer system, and preliminary performance figures are given. The highest performance achieved to date is 930,000 triangles per second using 256 processors and a 806,640 triangle data set.
Since a power network control system constitutes a large-scale computer network, intricate functions of software such as processing synchronization and data transmission among the constituent computers are required fo...
详细信息
Since a power network control system constitutes a large-scale computer network, intricate functions of software such as processing synchronization and data transmission among the constituent computers are required for improvement of system performance and efficiency. Methods for the support of overall large-scale system design are still scarce. Conventional text-oriented tools are insufficient to design, construct, and maintain large and complicated systems. As a means for solving this problem, an analytical method has been designed based on computer graphicsvisualization of static structural data and execution trace data of a software application's functional units. Prototyping tools for the development of software, enabling the direct manipulation of graphical elements through user-machine interfaces based on virtual reality technology, have been developed.< >
Volume rendering algorithms visualize sampled three dimensional data. A variety of applications create sampled data, including medical imaging, simulations, animation, and remote sensing. Researchers have sought to sp...
详细信息
Volume rendering algorithms visualize sampled three dimensional data. A variety of applications create sampled data, including medical imaging, simulations, animation, and remote sensing. Researchers have sought to speed up volume rendering because of the high run time and wide application. Our algorithm uses permutation warping to achieve linear speedup on dataparallel machines. This new algorithm calculates higher quality images than previous distributed approaches, and also provides more view angle freedom. We present permutation warping results on the SIMD MasPar MP-1. The efficiency results from nonconflicting communication. The communication remains efficient with arbitrary view directions, larger data sets, larger parallel machines, and high order filters. We show constant run time versus view angle, tunable filter quality, and efficient memory implementation.
The authors describe a dataparallel method for polygon rendering on a massively parallel machine. This method, based on a simple shading model, is targeted for applications which require very fast rendering for extre...
详细信息
The authors describe a dataparallel method for polygon rendering on a massively parallel machine. This method, based on a simple shading model, is targeted for applications which require very fast rendering for extremely large sets of polygons. Such sets are found in many scientific visualization applications. The renderer can handle arbitrarily complex polygons which need not be meshed. Issues involving load balancing are addressed and a dataparallel load balancing algorithm is presented. The rendering and load balancing algorithms are implemented on both the CM-200 and the CM-5. Experimental results are presented. This rendering toolkit enables a scientist to display 3D shaded polygons directly from a parallel machine avoiding the transmission of huge amounts of data to a post-processing rendering system.
Superscalar implementations of RISC architectures are emerging as the dominant high-performance microprocessor technology for the mid-1990's. For instruction-level parallelism to increase beyond present levels, mu...
详细信息
ISBN:
(纸本)9780818652806
Superscalar implementations of RISC architectures are emerging as the dominant high-performance microprocessor technology for the mid-1990's. For instruction-level parallelism to increase beyond present levels, multiple memory operations per cycle are required. The paper evaluates several alternatives for two-ported data cache memory systems. A new split data cache memory design is compared to a more conventional true dual-ported memory. Experimental simulations are used to determine the performance benefits of these cache models on superscalar processors. These experiments are reported for a contemporary processor with modest instruction-level parallelism and for a hypothetical very aggressive, highly parallel processor.< >
We describe experiences during the investigation of parallel methods for faster isosurface generation on SIMD machines. A sequential version of a well known isosurfacing algorithm is algorithmically enhanced for a par...
The proceedings contain 59 papers. The topics discussed include: parallel processing of form, color, motion, and depth: anatomy, physiology, art, and illusion;the interaction between visualization and science;a 3-D st...
ISBN:
(纸本)0818628960
The proceedings contain 59 papers. The topics discussed include: parallel processing of form, color, motion, and depth: anatomy, physiology, art, and illusion;the interaction between visualization and science;a 3-D streamline tracking algorithm using dual stream functions;approximation and rendering of volume data using wavelet transforms;Virtual Smoke: an interactive 3D flow visualization technique;interactive splatting of nonrectilinear volumes;interactive visualization of large scalar voxel fields;towards a comprehensive volume visualization system;rendering surface-particles;generalized focal surfaces: a new method for surface interrogation;an architecture for a scientific visualization system;direct volumetric visualization;improving visualization of hierarchies with Treemaps: design issues and experimentation;four-dimensional views of 3D scalar fields;volume rendering on a distributed memory parallel computer;and anatomical atlases based on volume visualization.
A prototype implementation of a splatting volume renderer (SVR) on a commercially available distributed memory MIMD (multiple instruction stream, multiple data stream) parallel processor, the nCUBE2, is described. Som...
详细信息
ISBN:
(纸本)9780818628962
A prototype implementation of a splatting volume renderer (SVR) on a commercially available distributed memory MIMD (multiple instruction stream, multiple data stream) parallel processor, the nCUBE2, is described. Some relatively good rendering times can be achieved with the nCUBE SVR. Message-passing bottlenecks occur when large numbers of floating-point values have to be collected from every processor for every picture. For large images this is a severe limitation. An initial implementation of a SVR on a distributed memory parallel computer demonstrates the need for parallel computers with high-bandwidth connections between processors, and also for new parallelizable volume rendering algorithms.< >
Automatic graphic object layout methods have long been studied in many application areas in which graphic objects should be laid out to satisfy the constraints specific to each application. In those areas, carefully d...
详细信息
Automatic graphic object layout methods have long been studied in many application areas in which graphic objects should be laid out to satisfy the constraints specific to each application. In those areas, carefully designed layout algorithms should be used to satisfy each application's constraints. However, those algorithms tend to be complicated and not reusable for other applications. Moreover, it is difficult to add each user's preferences to the layout scheme of the algorithm. To overcome these difficulties, the author developed a general-purpose interactive graphic layout system GALAPAGOS based on genetic algorithms. GALAPAGOS is general-purpose because graphic objects are laid out not by specifying how to lay them out, but just by specifying the preferences for the layout. GALAPAGOS can not only lay out complicated graphs automatically, but also allow users to modify the constraints at run time so that users can tell the system their own preferences.< >
暂无评论