---
title: Single-precision floating-point matrices
framework: accelerate
role: collectionGroup
role_heading: API Collection
path: accelerate/single-precision-floating-point-matrices
---

# Single-precision floating-point matrices

Perform operations on matrices that contain single-precision floating-point elements.

## Overview

Overview A matrix is a 2D array of values arranged in rows and columns. The simd library provides support for matrices of up to four rows and four columns. It uses a column-major naming convention; for example, a simd_float4x2 is a matrix that contains four columns and two rows.

## Topics

### Matrix structures

- [simd_float2x2](simd/simd_float2x2.md)
- [simd_float2x3](simd/simd_float2x3.md)
- [simd_float2x4](simd/simd_float2x4.md)
- [simd_float3x2](simd/simd_float3x2.md)
- [simd_float3x3](simd/simd_float3x3.md)
- [simd_float3x4](simd/simd_float3x4.md)
- [simd_float4x2](simd/simd_float4x2.md)
- [simd_float4x3](simd/simd_float4x3.md)
- [simd_float4x4](simd/simd_float4x4.md)

## See Also

### Matrices

- [Working with Matrices](accelerate/working-with-matrices.md)
- [Half-precision floating-point matrices](accelerate/half-precision-floating-point-matrices.md)
- [Double-precision floating-point matrices](accelerate/double-precision-floating-point-matrices.md)