Github user vrilleup commented on a diff in the pull request: https://github.com/apache/spark/pull/964#discussion_r13896271 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala --- @@ -201,6 +202,31 @@ class RowMatrix( } /** + * Multiply the Gramian matrix `A^T A` by a DenseVector on the right. + * + * @param v a local DenseVector whose length must match the number of columns of this matrix. + * @return a local DenseVector representing the product. + */ + private[mllib] def multiplyGramianMatrix(v: DenseVector): DenseVector = { + val n = numCols().toInt + + val bv = rows.aggregate(BDV.zeros[Double](n))( + seqOp = (U, r) => { + val rBrz = r.toBreeze + val a = rBrz.dot(v.toBreeze) --- End diff -- nice optimization! moved outside the closure with broadcast
--- 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. ---