Hardware SIMD acceleration

Level of SIMD intrinsics

Since R2023a

Description

App Configuration Pane: Speed

Configuration Objects: coder.MexCodeConfig

Level of SIMD intrinsics to use to accelerate vector operations. MATLAB^® Coder™ checks your specified hardware and compiler and uses the compatible intrinsics up to the level that you specify.

You can generate SIMD code for Intel and AMD platforms. If you generate code for a different platform, the code does not contain SIMD intrinsics.

Settings

Portable (SSE2)

This setting is the default setting.

The generated SIMD code uses the SSE2 instruction set.

None

No instructions sets are used.

Full (AVX2)

The generated SIMD code uses the AVX2 instruction set.

Programmatic Use

Property: SIMDAcceleration

Values: 'Portable' | 'Full' | 'None'

Default: 'Portable'

Version History

Introduced in R2023a