{"title":"Building a Full Scale VLSI-Based Volume Visualization System","authors":"R. Bakalash, A. Kaufman, Zhong Xu","doi":"10.2312/EGGH/EGGH90/109-115","DOIUrl":null,"url":null,"abstract":"The hardware realization of an advanced prototype of the Cube volume visualization system, Cube-3, is presented. The primary hardware component of Cube is a viewing and rendering multiprocessor with distributed 3D voxel memory. Cube-3 design is based on our experience with two earlier prototypes: Cube-1 realized in hardware using printed circuit board technology and Cube-2 our first custom-designed VLSI implementation. Both prototypes are of reduced-size resolution (163) and can generate only orthographic views. Cube-3 is the next generation prototype of a full-scale resolution of 2563 voxels. It has been functionally extended to generate non-orthographic projections, 3D real-time transformations, and shading. The ability to project and manipulate volumetric images in real-time is attributed to a unique skewed memory organization, a generalized skewed mapping, a special ray projection bus, a congradient shading technique, and a new barrel-shifting mechanism. This paper specifically describes the latter mechanism.","PeriodicalId":321323,"journal":{"name":"Advances in Computer Graphics Hardware V","volume":"4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Computer Graphics Hardware V","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2312/EGGH/EGGH90/109-115","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
The hardware realization of an advanced prototype of the Cube volume visualization system, Cube-3, is presented. The primary hardware component of Cube is a viewing and rendering multiprocessor with distributed 3D voxel memory. Cube-3 design is based on our experience with two earlier prototypes: Cube-1 realized in hardware using printed circuit board technology and Cube-2 our first custom-designed VLSI implementation. Both prototypes are of reduced-size resolution (163) and can generate only orthographic views. Cube-3 is the next generation prototype of a full-scale resolution of 2563 voxels. It has been functionally extended to generate non-orthographic projections, 3D real-time transformations, and shading. The ability to project and manipulate volumetric images in real-time is attributed to a unique skewed memory organization, a generalized skewed mapping, a special ray projection bus, a congradient shading technique, and a new barrel-shifting mechanism. This paper specifically describes the latter mechanism.