Why isn't the error scaled down during Mul's backprop ?

[singam-sanjay]

nn/Mul.lua

Lines 29 to 33 in 8726825

	function Mul:updateGradInput(input, gradOutput)
	self.gradInput:resizeAs(input):zero()
	self.gradInput:add(self.weight[1], gradOutput)
	return self.gradInput
	end

Why isn't the error caused by the input to the Mul layer not divided by the scaling factor, but multiplied by the same ?

If the input to the layer with the scaling factor of 2 is [1, 2] and the expected output is [4,4], the error would be [-2, 0]. Subtracting the scaled down error ([-1, 0]) from the input would correct the input.

Please clarify.