Heat Diffusion Simulation on GPU

This thesis deals with the simulation of heat diffusion in human tissues. The proposed algorithm uses a finite-difference time-domain method, which is applied on the governing equation describing the system. A modern graphics card is used to accelerate the simulation. The performance achieved on the GPU card is compared with the implementation exploiting a modern multicore CPU. The output of this thesis is a set of differently optimized algorithms targeted on NVIDIA graphics cards. The experimental results reveal that the use of shared memory is contraproductive and the best performance is achieved by a register based implementation. The overall speedup of 18.5 was reached when comparing a NVIDIA GeForce GTX 580 with a quad-core Intel Core i7 920 CPU. This nicely corresponds with the theoretical capabilities of both architectures