Floating-Point Specification in MATLAB
Because single precision numbers use only 32 bits, they require
less memory than double-precision numbers while still offering many
of the benefits of floating point arithmetic. The half-precision
data type occupies only 16 bits of memory, but its floating-point
representation enables it to handle wider dynamic ranges than
integer or fixed-point data types of the same size. You can use a
CustomFloat object to define a floating-point numeric
data type with specified word length and mantissa length.
|Specify floating-point, integer, or fixed-point data type|
|Describe floating point data type implemented by compiler for target hardware|
|Construct half-precision numeric object|
|Base 10 power and scale half-precision numbers|
|Reciprocal square root|
|Multiply and add using fused multiply add approach|
|Add target object to internal database|
|Create target object|
|Retrieve target objects from internal database|
|Remove target object from internal database|
Custom Floating Point
|Manage target hardware and build tool information|
- Floating-Point Numbers
Representation and manipulation of floating-point numbers.
- What is Half Precision?
Introduction to the half-precision data type in MATLAB® and Simulink®.
- Half Precision Code Generation Support
C/C++ and GPU code generation support for functions that support half-precision inputs.
- Generate Native Half-Precision C Code Using MATLAB Coder
Generate C code for embedded hardware targets that natively supports half precision floating-point data types.