GPU optimizations for a production molecular docking code

Modeling molecular docking is critical to both understanding life processes and designing new drugs. In previous work we created the first published GPU-accelerated docking code (PIPER) which achieved a roughly 5x speed-up over a contemporaneous 4 core CPU. Advances in GPU architecture and in the CPU code, however, have since reduced this relative performance by a factor of 10. In this paper we describe the upgrade of GPU PIPER. This required an entire rewrite, including algorithm changes and moving most remaining non-accelerated CPU code onto the GPU. The result is a 7x improvement in GPU performance and a 3.3x speedup over the CPU-only code. We find that this difference in time is almost entirely due to the difference in run times of the 3D FFT library functions on CPU (MKL) and GPU (cuFFT), respectively. The GPU code has been integrated into the ClusPro docking server which has over 4000 active users.