Fixed-Point Designer

Model and optimize fixed-point and floating-point algorithms

Fixed-Point Designer provides data types and tools for optimizing and implementing fixed-point and floating-point algorithms on embedded hardware. It includes fixed-point and floating-point data types and target-specific numeric settings.  With Fixed-Point Designer you can perform target-aware simulation that is bit-true for fixed point. You can then test and debug quantization effects such as overflows and precision loss before implementing the design on hardware.

Fixed-Point Designer provides apps and tools for analyzing double-precision algorithms and converting them to reduced-precision floating point or fixed point. Optimization tools enable you to select data types that meet your numerical accuracy requirements and target hardware constraints. For efficient implementation you can replace computationally expensive design constructs with hardware-optimal patterns such as compressed lookup tables.

Production C and HDL code can be generated directly from your fixed- and floating-point optimized models.

What Is Fixed-Point Designer?

Screenshot of the MATLAB Command Window after executing the command “fi(pi)”.

Fixed-Point Modeling

Evaluate performance tradeoffs on numerical precision by simulating fixed-point algorithms with application-specific word lengths, binary-point, or arbitrary slope and bias scaling. Control details such as rounding and overflow modes.

Specify Fixed-Point Objects in MATLAB and Simulink

Documentation | Examples

Transition from a Simulink block diagram to a picture of a processor, symbolizing the concept of “bit-true simulation and code generation.”

Bit-True Code Generation

Maintain bit-true agreement between simulation results and generated code for reduced-precision designs, ensuring high-fidelity algorithm deployment.

Fixed-Point Code Generation

Documentation | Examples

Deep Network Quantizer app icon as seen in the MATLAB Apps menu.

Fixed-Point AI Models

Quantize learnable parameters of machine learning models and deep neural networks to fixed-point datatypes in preparation for deployment to resource-constrained devices.

INT8 Quantization for Neural Networks

Documentation | Examples

Histogram range of signal values during model simulation.

Catch Errors Early

Quickly identify and debug sources of overflow, precision loss, and wasted range or precision. Resolve issues with numerical behavior earlier in the Model-Based Design workflow, lowering development costs.

Use the Fixed-Point Tool to Explore Numerical Behavior

Documentation | Examples

Drop-down menu containing list of available options for new workflows in the Fixed-Point Tool.

Automated Data Typing

Improve the numerical efficiency of your designs with automated fixed-point and floating-point data typing. Explore quantization effects on numerical behavior with guided conversion workflows.

Convert Floating-Point Model to Fixed Point

Documentation | Examples

Single Precision Converter displaying a Simulink model was successfully converted to use single-precision datatypes.

Embedded Floating-Point

Automatically convert designs from double to single and half-precision for enhanced efficiency in embedded environments. Emulate flush-to-zero behavior for denormal numbers.

Specify Single-Precision Data Type for Embedded Application

Documentation | Examples

Fixed-Point icon overlaying blue-V diagram, a common symbol for describing the Model-Based Design flow.

Cross-Product Support

Integrate fixed-point numbers across your designs, from modeling to final deployment. Leverage built-in fixed-point support for signal, audio processing, and communications workflows.

Documentation | Examples

Simulink model of system containing Complex Burst QR Decomposition block.

HDL-Optimized Matrix Blocks

Access a Fixed-Point HDL Library of Simulink blocks that model design patterns for systems of linear equations and core matrix operations, such as QR decomposition, for hardware-efficient implementation on FPGAs. Generate HDL code with HDL Coder.

Documentation | Examples

Simulink model of a fuel rate control system containing compressed lookup tables for pumping constant and pump rate.

Lookup Table Compression

Approximate mathematically complex functions or complex subsystems with an optimal lookup table. Compress existing lookup tables to reduce memory usage by optimizing data points and data types.

Lookup Table Optimization (2:21)

Documentation | Examples

Product Resources:

Documentation Examples Videos Requirements Release notes

VivaQuant Accelerates Development and Validation of Embedded Device for Ambulatory ECG Sensing

“MATLAB, MATLAB Coder, and Fixed-Point Designer enabled our small team to develop a complex real-time signal processing algorithm, optimize it to reduce power and memory requirements, accelerate embedded code implementation, and perform the rigorous testing required for medical device validation.”
Marina Brockway, VivaQuant

View more customer stories