triton.language.xor_sum(input, axis=None, keep_dims=False)

Returns the xor sum of all elements in the input tensor along the provided axis

  • input – the input values

  • axis – the dimension along which the reduction should be done

  • keep_dims – if true, keep the reduced dimensions with length 1

This function can also be called as a member function on tensor, as x.xor_sum(...) instead of xor_sum(x, ...).