<!--
{
  "documentType" : "article",
  "framework" : "Accelerate",
  "identifier" : "/documentation/Accelerate/simd-library",
  "metadataVersion" : "0.1.0",
  "role" : "collectionGroup",
  "title" : "simd"
}
-->

# simd

Perform computations on small vectors and matrices.

## Discussion

simd provides types and functions for small vector and matrix computations. The types include integer and floating-point vectors and matrices, and the functions provide basic arithmetic operations, element-wise mathematical operations, and geometric and linear algebra operations.

simd supports vectors containing up to 16 elements (for single-precision values) or 8 elements (for double-precision values), and matrices up to 4 x 4 elements in size. Other frameworks, such as <doc://com.apple.documentation/documentation/Accelerate/vforce-library>, allow you to work with larger vectors.

## Topics

### Boolean Scalar Data Type

[`simd_bool`](/documentation/simd/simd_bool)

A Boolean scalar value.

### Signed Integer Vectors

  <doc://com.apple.accelerate/documentation/Accelerate/8-bit-signed-integer-vectors>

  <doc://com.apple.accelerate/documentation/Accelerate/16-bit-signed-integer-vectors>

  <doc://com.apple.accelerate/documentation/Accelerate/32-bit-signed-integer-vectors>

  <doc://com.apple.accelerate/documentation/Accelerate/64-bit-signed-integer-vectors>

### Unsigned Integer Vectors

  <doc://com.apple.accelerate/documentation/Accelerate/8-bit-unsigned-integer-vectors>

  <doc://com.apple.accelerate/documentation/Accelerate/16-bit-unsigned-integer-vectors>

  <doc://com.apple.accelerate/documentation/Accelerate/32-bit-unsigned-integer-vectors>

  <doc://com.apple.accelerate/documentation/Accelerate/64-bit-unsigned-integer-vectors>

### Floating-Point Vectors

  <doc://com.apple.accelerate/documentation/Accelerate/working-with-vectors>

  <doc://com.apple.accelerate/documentation/Accelerate/half-precision-floating-point-vectors>

  <doc://com.apple.accelerate/documentation/Accelerate/single-precision-floating-point-vectors>

  <doc://com.apple.accelerate/documentation/Accelerate/double-precision-floating-point-vectors>

### Matrices

  <doc://com.apple.accelerate/documentation/Accelerate/working-with-matrices>

  <doc://com.apple.accelerate/documentation/Accelerate/half-precision-floating-point-matrices>

  <doc://com.apple.accelerate/documentation/Accelerate/single-precision-floating-point-matrices>

  <doc://com.apple.accelerate/documentation/Accelerate/double-precision-floating-point-matrices>

### Quaternions

  <doc://com.apple.accelerate/documentation/Accelerate/working-with-quaternions>

  <doc://com.apple.accelerate/documentation/Accelerate/rotating-a-cube-by-transforming-its-vertices>

[`simd_quatf`](/documentation/simd/simd_quatf)

A single-precision quaternion.

[`simd_quatd`](/documentation/simd/simd_quatd)

A double-precision quaternion.

### Constants

[`SIMD_COMPILER_HAS_REQUIRED_FEATURES`](/documentation/simd/SIMD_COMPILER_HAS_REQUIRED_FEATURES)

[`SIMD_LIBRARY_VERSION`](/documentation/simd/SIMD_LIBRARY_VERSION)

### Macros

  <doc://com.apple.accelerate/documentation/Accelerate/simd-macros>


---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)