Standalone floating-point conversion unit

Abstract

The invention relates to a standalone floating-point conversion unit. A data processing apparatus includes floating-point adder circuitry and floating-point conversion circuitry that generates a floating-point number as an output by performing a conversion on any input having a format from a list of formats including: an integer number, a fixed-point number, and a floating-point number having a format smaller than the output floating-point number. The floating-point conversion circuitry is physically distinct from the floating-point adder circuitry.

Description

technical field

[0001] The present disclosure relates to the field of data processing. Background technique

[0002] In a data processing arrangement, numbers may be represented in one of a number of different formats. For example, the 32-bit integer format uses 32 bits to represent the entire binary number. Another example is the 64-bit integer format, which uses 64 bits to represent an entire binary number. The increased number of bits used in the 64-bit format allows a wider range of values ​​to be represented than can be represented in the 32-bit integer format.

[0003] Another example format is floating point numbers. Floating point numbers can be used to represent any real number (not just any integer). As is the case with integer formats, increasing the number of bits used to represent floating-point numbers generally increases the range of values ​​that can be represented. In addition, increasing the number of bits used to represent a floating-point number incr...

Examples

Embodiment Construction

[0017] Floating point (FP) is a useful way to approximate real numbers using a small number of bits. The IEEE754-2008 floating-point standard proposes several different formats for floating-point numbers. Examples include binary 64 (also known as double precision or DP), binary 32 (also known as single precision or SP), and binary 16 (also known as half precision or HP). The numbers 64, 32, and 16 refer to the number of bits required for each format.

[0018] Floating point numbers are very similar to "scientific notation" taught in science class, where negative two million can be written instead as -2.0×10 6 . The parts of this number are the sign (negative in this example), the significand (2.0), the base of the exponent (10), and the exponent (6). All these parts have analogs in floating-point numbers, although there are differences, the most important of which are that the constituent parts are stored as binary numbers and that the base of exponent is always 2. Floatin...

technical field

[0001] The present disclosure relates to the field of data processing. Background technique

[0002] In a data processing arrangement, numbers may be represented in one of a number of different formats. For example, the 32-bit integer format uses 32 bits to represent the entire binary number. Another example is the 64-bit integer format, which uses 64 bits to represent an entire binary number. The increased number of bits used in the 64-bit format allows a wider range of values ​​to be represented than can be represented in the 32-bit integer format.

[0003] Another example format is floating point numbers. Floating point numbers can be used to represent any real number (not just any integer). As is the case with integer formats, increasing the number of bits used to represent floating-point numbers generally increases the range of values ​​that can be represented. In addition, increasing the number of bits used to represent a floating-point number incr...

Examples

Embodiment Construction

[0017] Floating point (FP) is a useful way to approximate real numbers using a small number of bits. The IEEE754-2008 floating-point standard proposes several different formats for floating-point numbers. Examples include binary 64 (also known as double precision or DP), binary 32 (also known as single precision or SP), and binary 16 (also known as half precision or HP). The numbers 64, 32, and 16 refer to the number of bits required for each format.

[0018] Floating point numbers are very similar to "scientific notation" taught in science class, where negative two million can be written instead as -2.0×10 6 . The parts of this number are the sign (negative in this example), the significand (2.0), the base of the exponent (10), and the exponent (6). All these parts have analogs in floating-point numbers, although there are differences, the most important of which are that the constituent parts are stored as binary numbers and that the base of exponent is always 2. Floatin...

Images