The use of accelerators such as GPUs has become mainstream to achieve high performance on modern computing systems. GPUs come with their own (limited) memory and are connected to the main memory of the machine through a bus (with limited bandwidth). When a computation is started on a GPU, the corresponding data needs to be transferred to the GPU before the computation starts. Such data movements may become a bottleneck for performance, especially when several GPUs have to share the communication bus. Task-based runtime schedulers have emerged as a convenient and efficient way to use such heterogeneous platforms. With such systems, the scheduler has the ability to choose which task to allocate to which GPU and to reorder tasks so as to minimize data movements. We focus on this problem of partitioning and ordering tasks that share some of their input data. We present a novel dynamic strategy based on data selection, to efficiently allocate tasks to GPUs, and a custom eviction policy. We compare them to existing strategies using standard scheduling techniques in runtime systems. All strategies have been implemented on top of the StarPU runtime, and we show that our dynamic strategy achieves better performance when scheduling tasks on multiple GPUs with limited memory.