Accelerating Recommender Systems using GPUs
LIAAD – INESC TEC, DCC – University of Porto
arXiv:1511.02433 [cs.IR], (8 Nov 2015)
We describe GPU implementations of the matrix recommender algorithms CCD++ and ALS. We compare the processing time and predictive ability of the GPU implementations with existing multi-core versions of the same algorithms. Results on the GPU are better than the results of the multi-core versions (maximum speedup of 14.8).
November 13, 2015 by hgpu
