2D and 3D Computer Graphics Algorithms under MorphoSys

TL;DR

This paper introduces new mappings of 2D and 3D geometric transformations on the MorphoSys reconfigurable computing system, enhancing graphics processing performance through optimized algorithms and validated by simulations and comparisons.

Contribution

It presents novel mappings of geometric transformations on MorphoSys, demonstrating improved performance and efficiency over existing systems.

Findings

Achieved significant speedup in transformation computations

Validated results through numerical simulations with MorphoSys mULATE

Compared performance favorably against Intel and FPGA systems

Abstract

This paper presents new mappings of 2D and 3D geometrical transformation on the MorphoSys (M1) reconfigurable computing (RC) prototype [2]. This improves the system performance as a graphics accelerator [1-5]. Three algorithms are mapped including two for calculating 2D transformations, and one for 3D transformations. The results presented indicate an improved performance. The speedup achieved is explained as well as the advantages in the mapping of the application. The transformations on an 8x8 RC array were run, and numerical examples were simulated to validate our results, using the MorphoSys mULATE program, which simulates MorphoSys operations. Comparisons with other systems are presented, namely, with Intel processing systems and Celoxica RC-1000 FPGA.