Skip to main content
. 2013 Apr 29;8(4):e61892. doi: 10.1371/journal.pone.0061892

Figure 3. Distribution of resources for the CUDA kernel that performs the Levenberg-Marquardt algorithm.

Figure 3

Voxels are assigned to threads of CUDA blocks. Each CUDA block is comprised of Inline graphic threads and processes Inline graphic voxels (Inline graphic was used in this study).