search

nickgreenquist / cu2rec

CUDA Implementation of Parallel Matrix Factorization Algorithm for Recommender Systems
GNU Affero General Public License v3.0
13 stars 1 forks source link

Add Dot Product usable in Kernels #6

Closed nickgreenquist closed 5 years ago

dorukkilitcioglu commented 5 years ago

Would be inefficient with our current SGD, because we only do a single dot product per user/thread.