Examples with MemoryType com.simiacryptus.mindseye.lang.cudnn.MemoryType used on opensource projects

Example 1 with MemoryType

use of com.simiacryptus.mindseye.lang.cudnn.MemoryType in project MindsEye by SimiaCryptus.

the class CudaLayerTester method buildIrregularCudaTensor.

/**
 * Build irregular cuda tensor cuda tensor list.
 *
 * @param gpu       the gpu
 * @param precision the precision
 * @param original  the original
 * @return the cuda tensor list
 */
public CudaTensorList buildIrregularCudaTensor(final CudnnHandle gpu, final Precision precision, final Tensor original) {
    TensorArray data = TensorArray.create(original);
    int[] inputSize = original.getDimensions();
    int channels = inputSize.length < 3 ? 1 : inputSize[2];
    int height = inputSize.length < 2 ? 1 : inputSize[1];
    int width = inputSize.length < 1 ? 1 : inputSize[0];
    final int listLength = 1;
    final int elementLength = data.getElements();
    MemoryType memoryType = MemoryType.Managed;
    @Nonnull final CudaMemory ptr0 = gpu.allocate((long) elementLength * listLength * precision.size, memoryType, false);
    @Nonnull final CudaDevice.CudaTensorDescriptor descriptor0 = gpu.newTensorDescriptor(precision, listLength, channels, height, width, channels * height * width, height * width, width, 1);
    for (int i = 0; i < listLength; i++) {
        Tensor tensor = data.get(i);
        assert null != data;
        assert null != tensor;
        assert Arrays.equals(tensor.getDimensions(), data.getDimensions()) : Arrays.toString(tensor.getDimensions()) + " != " + Arrays.toString(data.getDimensions());
        ptr0.write(precision, tensor.getData(), (long) i * elementLength);
        tensor.freeRef();
    }
    data.freeRef();
    Random r = new Random();
    int c = r.nextInt(5);
    int v = r.nextInt(5);
    int h = r.nextInt(5);
    @Nonnull final CudaMemory ptr1 = gpu.allocate((long) (channels + c) * (height + v) * (width + h) * listLength * precision.size, memoryType, false);
    @Nonnull final CudaDevice.CudaTensorDescriptor descriptor1 = gpu.newTensorDescriptor(precision, listLength, channels, height, width, (height + v) * (width + h) * (channels + c), (height + v) * (width + h), width + h, 1);
    gpu.cudnnTransformTensor(precision.getPointer(1.0), descriptor0.getPtr(), ptr0.getPtr(), precision.getPointer(0.0), descriptor1.getPtr(), ptr1.getPtr());
    assert CudaDevice.isThreadDeviceId(gpu.getDeviceId());
    ptr0.dirty();
    ptr1.dirty();
    descriptor0.freeRef();
    ptr0.freeRef();
    return CudaTensorList.wrap(CudaTensor.wrap(ptr1, descriptor1, precision), 1, original.getDimensions(), precision);
}