harperjiang

2017-03-06 13:53:13,431 INFO [main] o.n.l.f.Nd4jBackend [Nd4jBackend.java:194] Loaded [CpuBackend] backend
2017-03-06 13:53:13,547 INFO [main] o.n.n.NativeOpsHolder [NativeOpsHolder.java:38] Number of threads used for NativeOps: 4
2017-03-06 13:53:13,802 INFO [main] o.r.Reflections [Reflections.java:229] Reflections took 202 ms to scan 11 urls, producing 29 keys and 176 values 
2017-03-06 13:53:14,055 INFO [main] o.n.n.Nd4jBlas [Nd4jBlas.java:38] Number of threads used for BLAS: 4
2017-03-06 13:53:14,520 INFO [main] e.u.c.e.n.Slow [Slow.java:117] GEMM tests:
2017-03-06 13:53:14,534 INFO [main] e.u.c.e.n.Slow [Slow.java:125] Concat time: 7586 us
2017-03-06 13:53:14,556 INFO [main] e.u.c.e.n.Slow [Slow.java:125] Concat time: 138 us
2017-03-06 13:53:14,571 INFO [main] e.u.c.e.n.Slow [Slow.java:125] Concat time: 88 us
2017-03-06 13:53:14,602 INFO [main] e.u.c.e.n.Slow [Slow.java:125] Concat time: 65 us
2017-03-06 13:53:14,637 INFO [main] e.u.c.e.n.Slow [Slow.java:125] Concat time: 101 us

harperjiang

public static void main(String[] args) {
		fast();
		slow();
	}

	static void fast() {
		int hiddenDim = 200;
		int numChar = 100;
		int length = 500;
		int batchSize = 50;

harperjiang

Concat time: 24630 us
Concat time: 147 us
Concat time: 208 us
Concat time: 136 us
Concat time: 125 us
Concat time: 130 us
Concat time: 123 us
Concat time: 118 us
Concat time: 119 us
Concat time: 115 us

harperjiang

public class Slow {
    public static void main(String[] args) {

        int hiddenDim = 200;
        int numChar = 100;
        int length = 500;
        int batchSize = 50;
        int[] pshape = new int[]{numChar, hiddenDim};
        INDArray c2v = xavier(pshape);

harperjiang

import org.nd4j.linalg.api.ndarray.INDArray
import org.nd4j.linalg.api.ops.impl.broadcast.BroadcastAddOp
import org.nd4j.linalg.api.rng.distribution.impl.UniformDistribution
import org.nd4j.linalg.factory.Nd4j

import scala.util.Random

object Xavier {
  def init(shape: Array[Int]): INDArray = {
    var n = shape.dropRight(1).product