Interferometric radio telescopes often rely on computationally expensive O(N^2) correlation calculations; fortunately these computations map well to massively parallel accelerators such as low-cost GPUs. This paper describes the OpenCL kernels develo
ped for the GPU based X-engine of a new hybrid FX correlator. Channelized data from the F-engine is supplied to the GPUs as 4-bit, offset-encoded real and imaginary integers. Because of the low bit width of the data, two values may be packed into a 32-bit register, allowing multiplication and addition of more than one value with a single fused multiply-add instruction. With this data and calculation packing scheme, as many as 5.6 effective tera-operations per second (TOPS) can be executed on a 4.3 TOPS GPU. The kernel design allows correlations to scale to large numbers of input elements, limited only by maximum buffer sizes on the GPU. This code is currently working on-sky with the CHIME Pathfinder Correlator in BC, Canada.
A pathfinder version of CHIME (the Canadian Hydrogen Intensity Mapping Experiment) is currently being commissioned at the Dominion Radio Astrophysical Observatory (DRAO) in Penticton, BC. The instrument is a hybrid cylindrical interferometer designed
to measure the large scale neutral hydrogen power spectrum across the redshift range 0.8 to 2.5. The power spectrum will be used to measure the baryon acoustic oscillation (BAO) scale across this poorly probed redshift range where dark energy becomes a significant contributor to the evolution of the Universe. The instrument revives the cylinder design in radio astronomy with a wide field survey as a primary goal. Modern low-noise amplifiers and digital processing remove the necessity for the analog beamforming that characterized previous designs. The Pathfinder consists of two cylinders 37,m long by 20,m wide oriented north-south for a total collecting area of 1,500 square meters. The cylinders are stationary with no moving parts, and form a transit instrument with an instantaneous field of view of $sim$100,degrees by 1-2,degrees. Each CHIME Pathfinder cylinder has a feedline with 64 dual polarization feeds placed every $sim$30,cm which Nyquist sample the north-south sky over much of the frequency band. The signals from each dual-polarization feed are independently amplified, filtered to 400-800,MHz, and directly sampled at 800,MSps using 8 bits. The correlator is an FX design, where the Fourier transform channelization is performed in FPGAs, which are interfaced to a set of GPUs that compute the correlation matrix. The CHIME Pathfinder is a 1/10th scale prototype version of CHIME and is designed to detect the BAO feature and constrain the distance-redshift relation.
