Abstract: We propose the idea of using variable-precision geometry transformations and lighting to accelerate 3D graphics rendering. Multiresolution approaches reduce the number of primitives to be rendered; our approach complements the multiresolution techniques as it reduces the precision of each graphics primitive. Our method relates the minimum number of bits of accuracy required in the input data to achieve a desired accuracy in the display output. We achieve speedup by taking advantage of (a) SIMD parallelism for arithmetic operations, now increasingly common on modern processors, and (b) spatial-temporal coherence in frame-to-frame transformations and lighting. We show the results of our method on datasets from several application domains including laser-scanned, procedural, and mechanical CAD datasets.