Floating-point maximum value (double precision) (Floating-point Maximum (Double))
This instruction extracts the maximum value from the double-precision floating-point format data in the register pair specified by general-purpose registers reg1 and reg2, and stores it in the register pair specified by general-purpose register reg3.
If one of the source operands is S-NaN, an IEEE754-defined invalid operation exception is detected.
If invalid operation exceptions are not enabled, Q-NaN is stored and no exception occurs.