Fig. 4From: GPU accelerated voxel-driven forward projection for iterative reconstruction of cone-beam CTCalculation time curves of different methods: threads are allocated in axial planes and racing threads are solved with atomic operations (black); threads are allocated in vertical planes and racing threads are solved with atomic operations without thread-plane direction interchange (green); threads are allocated in vertical planes and racing threads are solved with atomic operations with thread-plane direction interchange at given angles (blue); threads are allocated in vertical planes and racing threads are solved with atomic operations with thread-plane direction interchange at critical angles (red)Back to article page