ARM Compute Library architecture
R2026b(To be removed) ARM architecture supported by target hardware
Model Configuration Pane: Code Generation / Interface
Support for the ARM® Compute Library as a target for deep learning code generation will be removed in
a future release. Instead, set Target Library to
none to generate generic C/C++ code that does not depend on any
third-party library. If you need to deploy to an ARM device that supports Neon instructions, set the
InstructionSetExtensions parameter to "Neon
v7". To set these parameters programmatically, use this code in the command
window:
set_param(mdl, "DLTargetLibrary", "none"); set_param(mdl, "InstructionSetExtensions", "Neon v7");
Setting InstructionSetExtensions to "Neon
v7" requires Embedded Coder®. The "none" target library workflow with instruction set
extensions is more capable in MATLAB® and Simulink®, and supports a larger set of layers.
Description
The ARM Compute Library architecture parameter specifies the ARM architecture that is supported by your target hardware.
Dependency
To enable this parameter, set the
Target Library parameter to ARM
Compute.
Settings
Unspecified (default) | character vectorSpecifies the ARM architecture supported in the target hardware, specified as a character vector. The specified architecture must be the same as the architecture for the ARM Compute Library on the target hardware.
Recommended Settings
| Application | Setting |
|---|---|
| Debugging | |
| Traceability | |
| Efficiency | |
| Safety precaution |
Programmatic Use
Parameter:
DLArmComputeArch |
| Type: character vector |
Value:
'Unspecified' | 'armv8' |
'armv7' |
Default:
'Unspecified' |
