high performance computing on graphics processing units: hgpu.org

Nowadays, dynamic solidification models of continuously cast steel are commonly used in steelworks over the world to control the casting process and to monitor the steel production. Moreover, these models of transient temperature field can also be utilized for optimization of continuous casting, its on-line regulation, or may help operators to solve non-standard or breakdown situations that can occur when casting. In order to solve these problems in real time, parallel computing of dynamic solidification models can favourably be utilized. One of possible approaches is to use parallel computing on graphics processing units (GPUs) that offer a great computing performance in comparison to ordinary computing on CPUs. The paper describes an implementation of the parallel dynamic solidification model with the use of the CUDA architecture and NVIDIA GPUs. A comparison between the use of parallel and non-parallel models is presented and analysed. Results show that parallel computing on GPUs can considerably enhance the computing performance of solidification models and their use and efficiency in other tasks.