Ray casting is a widely recognized method for high quality volume rendering. It traverses and samples the volume data ray by ray in image space. Traditionally, the algorithm is implemented in CPU on PC platform,resulting in slow speed and poor interacfivity. This paper introduces a new technique named View Dependent Layer Sampling (VDLS), which supports a hardware implementation of ray casting by Graphics Processing Unit (GPU).VDLS organizes the ray sampling points into a set of layers which can be efficiently represented by two view dependent geometric buffers as two dynamic textures. Based on the structure of VDLS, the six steps involved in the ray casting algorithm including ray generation, ray traversal, interpolation, classification, shading and composition can be fully accomplished in GPU, taking advantage of its programmability and flexibility. In addition, two speedup techniques exploiting object space and image space coherence are proposed for fast culling of the lapsed rays.Several advanced features regarding illumination and composition are further discussed, with which VDLS is capable of reconfiguring the well-known geometric hardware engine for volume ray casting. The novel approach of GPU supported ray casting can render up to 150 million interpolated, post shaded and composed ray samples per second for perspective view. Experimental results suggest that the proposed framework can be regarded as an alternative for on-the-fly visualization and exploitation of discrete scalar data in medical visualization, physical phenomena simulation and material testing applications.