Abstract :
The ray tracing algorithm produces realistic high quality images, but it requires a long time for calculation on a single processor machine, which limits its practical use. With the development of distributed object architectures, such as CORBA (Common Object Request Broker), the most promising way to improve ray traced picture productions seems to be parallelisation, which offers both increased CPU power and memory facilities. A natural way for parallelisation is to distribute pixels over the CORBA object system. However, since we want to deal with large scenes and making our algorithm functional over any parallel architecture system, scene objects have also to be distributed among processors, so a modified parallel algorithm is necessary. We propose a new method, which distributes the scene objects among processors (CORBA objects) according to their speed frequencies, which uses the object coherency property. Our approach of exploiting the bus CORBA gives very encouraging results.
Keywords :
data flow computing; distributed object management; parallel algorithms; processor scheduling; ray tracing; realistic images; rendering (computer graphics); CORBA object system; CPU power; Common Object Request Broker; data distribution method; distributed object architecture; load balancing; memory facility; object coherency property; object data flow; parallel algorithm; parallel architecture system; parallel ray tracing algorithm; pixel distribution; realistic high quality image; rendering; scene object distribution; Central Processing Unit; Computer architecture; Computer graphics; Information systems; Layout; Network servers; Parallel algorithms; Parallel architectures; Production; Ray tracing;