problematic.scala

import breeze.linalg._
import gust.linalg.cuda._
import jcuda.jcublas._

implicit val handle = new cublasHandle()
JCublas2.cublasCreate(handle)

// an extract from a REPL session
val A = CuMatrix.fromDense(DenseMatrix((1.0f, 1.0f, 2.0f, 1.0f), (1.0f, 2.0f, 1.0f, -2.0f), (3.0f, -1.0f, 3.0f, -2.0f), (-2.0f, 3.0f, -1.0f, 1.0f)))
val N = 4

val Aarray = jcuda.Pointer.to(A.offsetPointer)    // this is the one I'm most uncertain about
val P = CuMatrix.create[Int](N, 1)                // but I'm not sure about those 2 either
val info = CuMatrix.create[Int](N,1)

JCublas2.cublasSgetrfBatched(handle, N, Aarray, N, P.offsetPointer, info.offsetPointer, 1)  // this call returns success (0),
                                                                                            // but A is zeroed-out