addBiasToMatMulOutGPU function

GPUTensor<Matrix> addBiasToMatMulOutGPU(GPUTensor<Matrix> m, GPUTensor<Vector> b, CommandBuffer tape)

Implementation

GPUTensor<Matrix> addBiasToMatMulOutGPU(GPUTensor<Matrix> m, GPUTensor<Vector> b, CommandBuffer tape) {
  int rows = m.shape[0];
  int cols = m.shape[1];

  GPUTensor<Matrix> out = GPUTensor<Matrix>.empty(<int>[rows, cols]);

  tape.putInt(OP_BROADCAST_ADD);
  tape.putString(m.id);
  tape.putString(b.id);
  tape.putString(out.id);

  out.creator = GPUNode(
    <GPUTensor>[m, b],
        (CommandBuffer bTape) {
      bTape.putInt(OP_ADD_INTO);
      bTape.putString('${out.id}_grad');
      bTape.putString('${m.id}_grad');

      // FIXED: Sum across columns to isolate the row biases!
      bTape.putInt(OP_SUM_REDUCE_ROWS);
      bTape.putString('${out.id}_grad');
      bTape.putString('${b.id}_grad');
    },
    opName: 'addBiasToMatMulOutGPU',
    cost: rows * cols,
  );

  return out;
}