Modern GPUs are able to perform significantly more arithmetic operations than transfers of a single word to or from global memory. Hence, many GPU kernels are limited by memory bandwidth and cannot exploit the arithmetic power of GPUs. However, the memory locality can be often improved by kernel fusion when a sequence of kernels is executed and some kernels in this sequence share data.In this paper, we show how kernels performing map, reduce or their nested combinations can be fused automatically by our source-to-source compiler. To demonstrate the usability of the compiler, we have implemented several BLAS-1 and BLAS-2 routines and show how the performance of their sequences can be improved by fusions. Compared to similar sequences using CUBLAS, our compiler is able to generate code that is up to 2.61× faster for the examples tested.

Simulation of real-time interactions with soft tissue models is necessary for the development of computer-based medical training systems. To provide realistic visual and haptic feedback to a user by integrating measured material properties into the models, finite element (FE) modeling techniques are typically preferred. However, running a static nonlinear FE model in real-time is a highly challenging task since the resulting stiffness matrix (K) is not constant and varies with the depth of indentation into tissue. We propose a new approach allowing visio-haptic interaction with a FE model of a human liver having both non-linear geometric and material properties. The material properties used in the model are extracted from the experimental data of pig liver to make the simulations more realistic. Our computational approach consists of two main steps: a pre-computation of the configuration space of all possible deformation states of the model, followed by the interpolation of the precomputed data for the calculation of the reaction forces displayed to the user through a haptic device during the real-time interactions. No a priori assumptions or modeling simplifications about the mathematical complexity of the underlying soft tissue model, size and irregularity of the FE mesh are necessary. We show that deformation and force response of the liver in simulations are heavily influenced by the material model, boundary conditions, path of the loading and the type of function used for the interpolation of the pre-computed data.

No abstract