Fixed-Point Designer

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.

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 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.

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.

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.

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.

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.

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.

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.

“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