public static void SingleOutputBackward(NdArray <Real> y, NdArray <Real> x, NdArray <Real> weight, NdArray <Real> bias, ComputeKernel backwardgWKernel, ComputeKernel backwardgXKernel, ICompressibleActivation <Real> activation)
{
int outputCount = weight.Shape[0];
int inputCount = weight.Shape[1];
Real[] gx = new Real[x.Data.Length];
Real[] activatedgy = activation != null?activation.GetActivatedgy(y, x) : y.Grad;
if (bias != null)
{
LinearFunc.CalcBiasGrad(activatedgy, y.BatchCount, outputCount, bias.Grad);
}
using (ComputeBuffer <Real> gpugY = new ComputeBuffer <Real>(OpenCL.Context, ComputeMemoryFlags.ReadOnly | ComputeMemoryFlags.UseHostPointer, activatedgy))
{
using (ComputeBuffer <Real> gpugW = new ComputeBuffer <Real>(OpenCL.Context, ComputeMemoryFlags.ReadWrite | ComputeMemoryFlags.UseHostPointer, weight.Grad))
using (ComputeBuffer <Real> gpuX = new ComputeBuffer <Real>(OpenCL.Context, ComputeMemoryFlags.ReadOnly | ComputeMemoryFlags.UseHostPointer, x.Data))
{
backwardgWKernel.SetMemoryArgument(0, gpugY);
backwardgWKernel.SetMemoryArgument(1, gpuX);
backwardgWKernel.SetMemoryArgument(2, gpugW);
backwardgWKernel.SetValueArgument(3, y.BatchCount);
backwardgWKernel.SetValueArgument(4, outputCount);
backwardgWKernel.SetValueArgument(5, inputCount);
OpenCL.CommandQueue.Execute
(
backwardgWKernel,
null,
new long[] { inputCount, outputCount },
null,
null
);
OpenCL.CommandQueue.Finish();
OpenCL.CommandQueue.ReadFromBuffer(gpugW, ref weight.Grad, true, null);
}
using (ComputeBuffer <Real> gpugX = new ComputeBuffer <Real>(OpenCL.Context, ComputeMemoryFlags.WriteOnly | ComputeMemoryFlags.AllocateHostPointer, gx.Length))
using (ComputeBuffer <Real> gpuW = new ComputeBuffer <Real>(OpenCL.Context, ComputeMemoryFlags.ReadOnly | ComputeMemoryFlags.UseHostPointer, weight.Data))
{
backwardgXKernel.SetMemoryArgument(0, gpugY);
backwardgXKernel.SetMemoryArgument(1, gpuW);
backwardgXKernel.SetMemoryArgument(2, gpugX);
backwardgXKernel.SetValueArgument(3, y.BatchCount);
backwardgXKernel.SetValueArgument(4, outputCount);
backwardgXKernel.SetValueArgument(5, inputCount);
OpenCL.CommandQueue.Execute
(
backwardgXKernel,
null,
new long[] { inputCount, y.BatchCount },
null,
null
);
OpenCL.CommandQueue.Finish();
OpenCL.CommandQueue.ReadFromBuffer(gpugX, ref gx, true, null);
}
}
for (int i = 0; i < x.Grad.Length; i++)
{
x.Grad[i] += gx[i];
}
}
