COMPUTER NUMERICAL STORAGE FORMAT WITH PRECISION TYPE INDICATOR

Various techniques for storing computer numbers such as floating-point numbers. In one embodiment, a data processing unit is configured to represent floating-point numbers using a first precision with a first number of bits and a second precision with a second number of bits, where the second number of bits is greater than the first number of bits. A floating-point type value may be set upon a memory store to indicate whether a first representation of a floating-point number uses the first or the second number of bits. A second representation of the floating-point number and the floating-point type value may be stored accordingly. In some embodiments, the second representation may correspond to the first representation with one or more bits shifted. This format may lead to memory power savings when reading from a memory location of the second precision when the result is indicated as the first precision.