Cube-4 Implementations on the Teramac Custom Computing Machine

We present two implementations of the Cube-4 volume rendering architecture on the Teramac cus­ tom computing machine. Cube-4 uses a slice­ parallel ray-casting alg01'ithm that allows for a paral­ lel and pipelined implementation of ray-casting with tri-linear interpolation and su'rface normal estima­ tion from interpolated samples. Shading, classifica­ tion and compositing are part of rendering pipeline. Wzth the partitioning schemes introduced in this pa­ per, Cube-4 is capable of 1'endering lmye datasets with a limited number of pipelines. The Teramac hardwm'e simulat01' at the Hewlett-Packard research laboratories, Palo Alto, CA, on which Cube-4 was implemented, belongs to the new class of custom computing machines. Teramac combines the speed of special-purpose hardware with the flexibility of general-purpose computel's. With Teramac as a de­ velopment tool we were able to implement in just five weeks working Cube-4 prototypes, capable of rendering for example datasets of 1283 voxels in 0.65 seconds at 0,96 MHz processing frequency. The performance results from these implementations indicate real-time performance for high-resolution data-sets.