high performance computing on graphics processing units: hgpu.org

In this paper, we propose an efficient implementation of the branch and bound method for knapsack problems on a CPU-GPU system via CUDA. Branch and bound computations can be carried out either on the CPU or on a GPU according to the size of the branch and bound list. A better management of GPUs memories, less GPUCPU communications and better synchronization between GPU threads are proposed in this new implementation in order to increase efficiency. Indeed, a series of computational results is displayed and analyzed showing a substantial speedup on a Tesla C2050 GPU.