high performance computing on graphics processing units: hgpu.org

The development of increasingly powerful and low cost massively parallel processors, known as GPUs, has created new opportunities for high speed and high precision computational work in physics. GPUs are extremely well suited to solving computationally intense problems at speeds much greater than traditional processors. They are now found in most personal computers, with research grade models available at reasonable prices. This makes a wide variety of previously intractably computationally intense problems solvable at a personal workstation. In this thesis I explore how these massively parallel processors work on both the hardware and software level, and the types of problems they are capable of solving better than traditional processors. Then, I move on to develop parallel programming solutions to computing the logistic map and solving ordinary differential equations. I evaluate how much of a speed advantage the GPU gives over the CPU and the limiting factors on the speed of the GPU implementations.