Solution of many Biological 2 and 3 dimensional systems in Biology can require the solution of billions of differential equations describing the complex dynamics of each element that form a multiscale problem. Therefore, large-scale models of complex systems have been limited to groups with access to supercomputers and clusters. Here, we introduce a new approach that makes high-performance simulation of biological systems accessible to virtually anyone with a modest computer via parallelization using their graphic cards GPU. We present examples of cardiac arrhythmia simulations in anatomically accurate heart structures, with quantitative comparisons to experiments on mammalian hearts. We also show the versatility of this approach with other examples of large scale dynamics such as fluid flow and crystal growth. We finish by describing how this methodology is independent of operating system or device. Therefore, the programs developed under this approach to solve biological problems described by partial differential equations can be ran on windows. mac and Unix/Linux machines including cellphones which can solve up to 7 billion differential equations per second.