C. M. Wittenbrink and A. K. Somani. Permutation Warping for Data Parallel Volume Rendering. In Parallel Rendering Symposium, pages 57--60, Oct. 1993.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....projection [30] Fourier volume rendering [15] use of 3D textures [28] dedicated volume hardware [3, 21] taking advantage of spatial coherency with octree, binary space partitioning etc. 11, 4, 31] wavelets [19] shearing [23] parallelization with shear warp [9] and permutation warp [33], extensions to curvilinear and unstructured grids [5, 6] to name a few. Unfortunately, this plethora of DVR methods produce images that are different from each other. In critical applications such as clinical medical imaging where DVR is the method of choice, this can be very disconcerting. ....

Craig M. Wittenbrink and Arun K. Somani. Permutation warping for data parallel volume rendering. In Proceedings of the Parallel Rendering Symposium, pages 57--60, color plate p. 110, San Jose, CA, October 1993. D E A B C

....nine shear decomposition sequence, they managed to merge two neighboring shears into a single shear, resulting in an eight shear decomposition. The first attempt of directly performing decomposition on 3D rotation was recently taken by Toffoli and Quick [14] and also mentioned by Wittenbrink [17]: R = R x (OE)R y ( R z (ff) 2 4 1 a 12 a 13 0 1 a 23 0 0 1 3 5 2 4 1 0 0 b 21 1 0 b 31 b 32 1 3 5 2 4 1 c 12 c 13 0 1 c 23 0 0 1 3 5 (2) Each matrix in Eq. 2 is an upper lower triangular matrix, which can be interpreted as a general shear operation first sliding ....

....sample the volume only once. Here we propose such a method. The idea is to precompute a sampled volume and then use only zero order (nearest neighbor) interpolation in each shear pass to shuffle sampled voxels to their destinations. This is similar to Wittenbrink and Somani s permutation warping [16, 17]. However, there the sampled voxels are sent to their destinations using a global communication. Given an original volume (source volume) and the desired rotated volume (target volume) we first set up one to one correspondence between a source voxel and a target voxel. This one to one mapping is ....

[Article contains additional citation context not shown here]

C. M. Wittenbrink and A. K. Somani. Permutation warping for data parallel volume rendering. In ACM SIGGRAPH Symposium on Parallel Rendering, pages 57--60, Nov. 1993. 15

....a very important research area. Recent work in parallel rendering can be divided broadly into two main categories: algorithms and systems. Algorithm researchers have concentrated on the design of highly efficient parallel volume rendering algorithms [SS91, MPS92, MPHK94, Hsu93, CC93, Neu93, NL92, WS93] Their work has been concerned primarily with optimizing performance with respect to constant problem size (CPS) scaling [SHG93] and has largely ignored systems issues. Lately, some work has been done in developing distributed rendering systems that can make use of available parallel resources ....

C. Wittenbrink and A. Somani. Permutation warping for data parallel volume rendering. In 1993 Parallel Rendering Symposium Proceedings, pages 57--60. ACM Press, October 1993.

.... example 3D texture hardware as described in (Cabral, Cam, and Foran 1994) A different approach is to implement specialized algorithms for massively parallel computers (Challinger 1993; Hsu 1993; Ma, Painter, Hansen, and Krogh 1994; Corrie and Mackerras 1993; Vezina, Fletcher, and Robertson 1992; Wittenbrink and Somani 1993). Another very interesting approach is based on data and image coherence (Lacroute 1995; Lacroute and Levoy 1994) achieving nearly interactive rates even on standard workstations. In this work we are concerned with volume rendering algorithms which are suitable for massively parallel SIMD ....

Wittenbrink, C. M. and Somani, A. K. 1993. Permutation warping for data parallel volume rendering. In T. Crockett, C. Hansen, and S. Whitman, editors, Proceedings of the 1993 Symposium on Parallel Rendering , pages 57--60.

.... A few of them exist on experimental parallel processors, such as the Princeton Engine [15] or the DASH parallel system [13] Other implementations have been conducted on commercially available parallel machines such as the AMT DAP [1] Connection Machine CM 2 ( 14] 15] MasPar MP 1 ([18], 20] Intel iPSC 2 [12] nCube [5] Cray Y MP [16] IBM PVS [11] Silicon Graphics multiprocessor workstation [6] and network of Suns [17] The viewing algorithms adopted in these implementations are many and varied. Several are based on backward feed methods. In [12] and [13] ray casting is ....

Wittenbrink, C., Somani, A., "Permutation Warping for Data Parallel Volume Rendering", 1993 Parallel Rendering Symposium, San Jose, CA, October, 1993, pp. 57-60.

....volume hardware, taking advantage of spatial coherency with octree, binary space partitioning, etc. parallelization with shear warp, permutation warp, multi pass forwards, forwards wavefront, forwards splatting, backwards, etc. extensions to curvilinear grids, and combinations of the above [3, 13, 16, 8, 18, 6, 19, 21, 10, 5, 2, 11, 17]. Unfortunately, this plethora of DVR methods produce images that are different from each other. In critical applications such as clinical medical imaging where DVR is the method of choice, this can be very disconcerting. Fortunately, more and more DVR papers address the issue of image quality. ....

Craig M. Wittenbrink and Arun K. Somani. Permutation warping for data parallel volume rendering. In Proceedings of the Parallel Rendering Symposium, pages 57--60, color plate p. 110, San Jose, CA, October 1993.

....projection [30] Fourier volume rendering [15] use of 3D textures [28] dedicated volume hardware [3, 21] taking advantage of spatial coherency with octree, binary space partitioning etc. 11, 4, 31] wavelets [19] shearing [23] parallelization with shear warp [9] and permutation warp [33], extensions to curvilinear and unstructured grids [5, 6] to name a few. Unfortunately, this plethora of DVR methods produce images that are different from each other. In critical applications such as clinical medical imaging where DVR is the method of choice, this can be very disconcerting. ....

Craig M. Wittenbrink and Arun K. Somani. Permutation warping for data parallel volume rendering. In Proceedings of the Parallel Rendering Symposium, pages 57--60, color plate p. 110, San Jose, CA, October 1993.

.... 113] 44] 52] 107] 111, 81] 94] 16, 15] 34] 101] 40] 66] 73] 90] 116] 26] 20] 68] 6] 54, 52, 63, 28, 67] 7, 1, 42, 4, 62] 31, 75, 30, 38, 86] 41, 21, 119, 112, 118, 45, 58] 55, 65, 14, 29, 79] 115, 53, 70, 74, 87, 19, 117, 32] 72, 57, 92, 36, 7] 111, 12, 90, 97, 78, 5] [15, 27, 35, 43, 87, 28, 51, 22, 23, 59, 60, 64, 63, 66, 68, 71, 80, 81, 91, 93, 99, 47, 108] [103, 116, 83, 106, 107, 105, 2, 76, 110, 77] 11, 104, 101, 96, 89, 26, 73, 6, 17, 52, 54, 85, 114, 9, 82, 37, 24] 8, 61, 3, 56, 67, 88, 44, 10, 69, 48, 16, 84, 113, 95, 13, 50, 94, 40, 46] 100, 109, 102] 25, 18, 33, 39] ....

Craig M. Wittenbrink and Arun K. Somani. Permutation warping for data parallel volume rendering. In Proceedings of the Parallel Rendering Symposium, pages 57--60, color plate p. 110, San Jose, CA, October 1993.

....uses multiple passes of hypercube communication, and also idles processors as compositing occurs. Hsu s algorithm fully distributes the volume, but bottlenecks result when going from the three dimensional frames to the two dimensional screen, preventing linear speedup. Our permutation warping [37] approach computes a backwards mapping algorithm with optimal storage and deterministic communication on shared or distributed memory machines. O S ( S n 3 = O S P ( P P O S S log ( O W log ( W S S log P S 8 A network efficient parallel algorithm is the multipass forwards ....

....7 8 I E1. 8 t 1. 8 , I S1 a 1 I S2 a 2 I S3 a 3 I S8 a 8 t 1 1 a 1 ( t 2 1 a 2 ( t 3 1 a 3 ( t 1 1 a 1 ( I E12 t 12 , I E34 t 34 , I E56 t 56 , I E78 t 78 , I E1234 t 1234 , I E5678 t 5678 , 3W 2 W log 2W 2 a i I Si I ray W 2W 1 2W 2 28 proach [36][37][38] A fully parallel compositing approach was developed in parallel by Ma et al. 20] FIGURE 12 Halving of Frames During Parallel Product for Compositing Theorem 3: Parallel Volume Rendering is an optimal parallel algorithm by definition 1, 2, 3, 4, and 5 for processors on CREW and EREW PRAMs. ....

[Article contains additional citation context not shown here]

Wittenbrink, C. M., and Somani, A. K. Permutation Warping for Data Parallel Volume Rendering. Proc. Parallel Rendering Symposium `93. IEEE Computer Society and ACM, San Jose, CA, 1993, pp. 57-60, color plate pp. 110.

No context found.

C. M. Wittenbrink and A. K. Somani. Permutation Warping for Data Parallel Volume Rendering. In Parallel Rendering Symposium, pages 57--60, Oct. 1993.

No context found.

C.M. Wittenbrink, and A.K. Somani, "Permutation warping for data parallel volume rendering," ACM SIGGRAPH Symposium on Parallel Rendering, pp. 57-60, 1993.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC