FLOATING-POINT NUMBER SQUARE ROOT CALCULATION METHOD AND FLOATING-POINT NUMBER CALCULATION MODULE

Embodiments of the present application provide a floating-point number square root calculation method and a floating-point number calculation module, having a shorter calculation latency and high throughput rate, and correspondingly provide an optimized rounding method, which can output an accurate result that satisfies rounding modes of the IEEE754 standard. In the floating-point number square root calculation method, the mantissa of the square root of a first floating-point number is determined by determining the square root of a target mantissa, wherein the target mantissa comprises the mantissa of the first floating-point number, and the first floating-point number is a normalized floating-point number. The high bit width part and the low bit width part of the square root of the target mantissa are calculated respectively, and the square root of the target mantissa is determined, wherein the fractional part of the square root of the target mantissa is the mantissa of the square root of the first floating-