[SPARK-1696][MLLIB] use alpha in dense dspr

It doesn't affect existing code because only `alpha = 1.0` is used in the code.

Author: Xiangrui Meng <meng@databricks.com>

Closes #778 from mengxr/mllib-dspr-fix and squashes the following commits:

a37402e [Xiangrui Meng] use alpha in dense dspr

mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala

@@ -440,7 +440,7 @@ object RowMatrix {
     val n = v.size
     v match {
       case dv: DenseVector =>
-        blas.dspr("U", n, 1.0, dv.values, 1, U)
+        blas.dspr("U", n, alpha, dv.values, 1, U)
       case sv: SparseVector =>
         val indices = sv.indices
         val values = sv.values