The connection machine
ARTSccelerated ray-tracing system
IEEE Computer Graphics and Applications
SIGGRAPH '86 Proceedings of the 13th annual conference on Computer graphics and interactive techniques
Fast ray tracing by ray classification
SIGGRAPH '87 Proceedings of the 14th annual conference on Computer graphics and interactive techniques
An improved illumination model for shaded display
Communications of the ACM
New techniques for ray tracing procedurally defined objects
SIGGRAPH '83 Proceedings of the 10th annual conference on Computer graphics and interactive techniques
SIGGRAPH '84 Proceedings of the 11th annual conference on Computer graphics and interactive techniques
An adaptive subdivision algorithm and parallel architecture for realistic image synthesis
SIGGRAPH '84 Proceedings of the 11th annual conference on Computer graphics and interactive techniques
Ray tracing of Steiner patches
SIGGRAPH '84 Proceedings of the 11th annual conference on Computer graphics and interactive techniques
An updated cross-indexed guide to the ray-tracing literature
ACM SIGGRAPH Computer Graphics
A Competitive Analysis of Load Balancing Strategiesfor Parallel Ray Tracing
The Journal of Supercomputing
Parallel Computing on an Ethernet Cluster of Workstations: Opportunities and Constraints
The Journal of Supercomputing
Design for a real-time high-quality volume rendering workstation
VVS '89 Proceedings of the 1989 Chapel Hill workshop on Volume visualization
Ray tracing on programmable graphics hardware
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Fast rotation of volume data on data parallel architectures
VIS '91 Proceedings of the 2nd conference on Visualization '91
KD-tree acceleration structures for a GPU raytracer
Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware
Ray tracing on programmable graphics hardware
SIGGRAPH '05 ACM SIGGRAPH 2005 Courses
| Hi-index | 0.00 |
A new ray-tracing algorithm designed specifically for massively parallel hypercube connected processors is introduced. World space is subdivided according to a fixed size 3-D orthogonal grid. Rays are traced using ray-points which move along the rays, referencing the voxels intersected. One processor is assigned per ray, as well as one processor per object fragment.A pointerless data structure called an induced octree is used. This structure exists only as an ordering of the data in processor-address space, yet with it, all processors can determine the jump-distance to the nearest non-empty voxel in parallel to within a power of two. Ray-points move by large jumps whenever possible, and ray-object intersection proceeds in log time in the average ray length. Sorting via the network is the parallel analogue to octree-traversal.A code-scheduling mechanism is introduced which improves processor usage for SIMD architectures.Preliminary results are presented for an implementation using a CM-1 CPU equipped with 16k processors.