Nowadays, NVIDIA’s CUDA is a general purpose scalable parallel programming model for writing highly parallel applications. It provides several key abstractions – a hierarchy of thread blocks, shared memory, and barrier synchronization. This model has proven quite successful at programming multithreaded many core GPUs and scales transparently to hundreds of cores: scientists throughout industry and academia are already using CUDA to achieve dramatic speedups on production and research codes. GPU-base clusters are likely to play an important role in future cloud data centers, because some compute-intensive applications may require both CPUs and GPUs. The goal of this paper is to develop a VM execution mechanism that could run these applications inside VMs and allow them to effectively leverage GPUs in such a way that different VMs can share GPUs without interfering with one another.