This paper describes the implementation of a large bandwidth multi-GPU signal processing system for radio astronomy observation. This system performs computationally intensive FFT (Fast Fourier Transform) and spectrum analysis to achieve real-time analysis of a large bandwidth spectrum. This is accomplished by implementing a four-step FFT algorithm in CUDA. The key feature of this implementation is that the data size transferred between CPU and GPU is reduced using redundant calculation. We

more »

... apply pipeline execution to our system to minimize idle processor time, even with multiple GPUs on a shared bus. Using a single GPU, this system can analyze 1GB of signal data (128MHz bandwidth at 1Hz resolution in single precision floating-point complex format) in 0.44 seconds. With the multi-GPU setup, using four GPUs enables 4GB of signal data to be processed in 0.82 seconds. This is equivalent to a processing speed of around 60 GFLOPS. In particular, we focus on using this system in the SERENDIP (Search for Extraterrestrial Radio Emissions from Nearby Developed Intelligent Populations) project. By using multiple GPUs we can get enough practical performance for high bandwidth radio astronomy projects such as SERENDIP.