image thumbnail

IEEE 754r Half Precision floating point converter

version 2.0 (33.2 KB) by James Tursa
Converts MATLAB or C variables to/from IEEE 754r Half Precision floating point bit pattern.

8.8K Downloads

Updated 18 May 2020

View License

halfprecision converts the input argument to/from a half precision floating point bit pattern corresponding to IEEE 754r. The bit pattern is stored in a uint16 class variable. Please note that halfprecision is *not* a class. That is, you cannot do any arithmetic with the half precision bit patterns. halfprecision is simply a function that converts the IEEE 754r half precision bit pattern to/from other numeric MATLAB variables, and performs various tests on the bit patterns (isinf, isnan, eps, etc.).

The half precision bit pattern is as follows:

1 bit sign bit
5 bits exponent, biased by 15
10 bits mantissa, hidden leading bit, normalized to 1.0

Special floating point bit patterns recognized and supported:

All exponent bits zero:
- If all mantissa bits are zero, then number is zero (possibly signed)
- Otherwise, number is a denormalized bit pattern (leading bit is present)

All exponent bits set to 1:
- If all mantissa bits are zero, then number is +Infinity or -Infinity
- Otherwise, number is NaN (Not a Number)

More details of this floating point format can be found here:

http://en.wikipedia.org/wiki/Half_precision

Building:

halfprecision requires that a mex routine be built (one time only). This process is typically self-building the first time you call the function as long as you have the files halfprecision.m and halfprecision.c in the same directory somewhere on the MATLAB path. If you need to manually build the mex function, see the documentation in halfprecision.m for instructions on building the mex routine.

Syntax

B = halfprecision(A)
C = halfprecision(B,classname or function)
L = halfprecision(directive)
halfprecision(B,'disp')

Description

A = a MATLAB numeric array, char array, or logical array.

B = the variable A converted into half precision floating point bit pattern.
The bit pattern will be returned as a uint16 class variable. The values
displayed are simply the bit pattern interpreted as if it were an unsigned
16-bit integer. To see the halfprecision values, use the 'disp' option, which
simply converts the bit patterns into a single class and then displays them.

C = the half precision floating point bit pattern in B converted into class S.
B must be a uint16 or int16 class variable.

classname = char string naming the desired class (e.g., 'single', 'int32', etc.)

function = char string giving one of the following functions:
'isinf' = returns a logical variable, true where B is inf
'isnan' = returns a logical variable, true where B is nan
'isnormal' = returns a logical variable, true where B is normalized
'isdenormal' = returns a logical variable, true where B is denormalized
'eps' = returns eps of the half precision values

directive = char string giving one of the following directives:
'openmp' = returns a logical variable, true when compiled with OpenMP
'realmax' = returns max half precision value
'realmin' = returns min half precision normalized value
'realmindenormal' = returns min half precision denormalized value
'version' = returns a string with compilation memory model

'disp' = The floating point bit values are simply displayed.

Examples

>> a = [-inf -1e30 -1.2 NaN 1.2 1e30 inf]
a =
1.0e+030 *
-Inf -1.0000 -0.0000 NaN 0.0000 1.0000 Inf

>> b = halfprecision(a)
b =
64512 64512 48333 65024 15565 31744 31744

>> halfprecision(b,'disp')
-Inf -Inf -1.2002 NaN 1.2002 Inf Inf

>> halfprecision(b,'double')
ans =
-Inf -Inf -1.2002 NaN 1.2002 Inf Inf

>> 2^(-24)
ans =
5.9605e-008

>> halfprecision(ans)
ans =
1

>> halfprecision(ans,'disp')
5.9605e-008

>> 2^(-25)
ans =
2.9802e-008

>> halfprecision(ans)
ans =
1

>> halfprecision(ans,'disp')
5.9605e-008

>> 2^(-26)
ans =
1.4901e-008

>> halfprecision(ans)
ans =
0

>> halfprecision(ans,'disp')
0

Note that the special cases of -Inf, +Inf, and NaN are handled correctly. Also, note that the -1e30 and 1e30 values overflow the half precision format and are converted into half precision -Inf and +Inf values, and stay that way when they are converted back into doubles.

Caveat: I have only tested this code on a PC, which is Little Endian. I put in code to handle Big Endian machines, but I do not have a way to test it, so I can't say for sure that it will work properly. Let me know if you have problems.

Cite As

James Tursa (2021). IEEE 754r Half Precision floating point converter (https://www.mathworks.com/matlabcentral/fileexchange/23173-ieee-754r-half-precision-floating-point-converter), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2007a
Compatible with any release
Platform Compatibility
Windows macOS Linux
Acknowledgements

Inspired: TerraSAR-X and TanDEM-X tools

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!