Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/17742#discussion_r113428567 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala --- @@ -277,17 +278,39 @@ object MatrixFactorizationModel extends Loader[MatrixFactorizationModel] { val srcBlocks = blockify(rank, srcFeatures) val dstBlocks = blockify(rank, dstFeatures) val ratings = srcBlocks.cartesian(dstBlocks).flatMap { - case ((srcIds, srcFactors), (dstIds, dstFactors)) => - val m = srcIds.length - val n = dstIds.length - val ratings = srcFactors.transpose.multiply(dstFactors) - val output = new Array[(Int, (Int, Double))](m * n) - var k = 0 - ratings.foreachActive { (i, j, r) => - output(k) = (srcIds(i), (dstIds(j), r)) - k += 1 - } - output.toSeq + case (users, items) => + val m = users.size + val n = math.min(items.size, num) + val output = new Array[(Int, (Int, Double))](m * n) + var j = 0 + users.foreach (user => { + def order(a: (Int, Double)) = a._2 + val pq: BoundedPriorityQueue[(Int, Double)] = + new BoundedPriorityQueue[(Int, Double)](n)(Ordering.by(order)) + items.foreach (item => { + /** + * blas.ddot (F2jBLAS) is the same performance with the following code. + * the performace of blas.ddot with NativeBLAS is very bad. + * blas.ddot (F2jBLAS) is about 10% improvement comparing with linalg.dot. + * val rate = blas.ddot(rank, user._2, 1, item._2, 1) + */ + var rate: Double = 0 + var k = 0 + while(k < rank) { + rate += user._2(k) * item._2(k) + k += 1 + } + pq += ((item._1, rate)) --- End diff -- Here we can then use `dstFactor` instead
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org