Efficient floating point overflow and underflow detection system

摘要

A processing system that determines whether an underflow or overflow condition has occurred concurrently with the determination of the floating point exponent result uses a group of latched constants which can be added to the intermediate exponent and the exponent adjust to determine out of range conditions for all cases. The appropriate one of these latched constants (exponent range check values; exp-range-chk) are added to the exp-int and exp-adjust to give a value that will vary based on whether the exp-result is out of range, or not. Different exp-range-chk values are used for underflow single precision, underflow double precision, overflow single precision and overflow double precision. The sum of these three values (exp-int, exp-adj, exp-range-chk) will yield a binary number having a most significant bit (MSB) that is dependent upon the exp-result value. More particularly, the MSB will be a logical 1 when an out of range condition has occurred and a logical 0 for normal in range exponent results.