<!--
{
  "availability" : [
    "iOS: 15.0.0 - 18.0.0",
    "iPadOS: 15.0.0 - 18.0.0",
    "macCatalyst: 15.0.0 - 18.0.0",
    "macOS: 12.0.0 - 15.0.0",
    "tvOS: 15.0.0 - 18.0.0",
    "visionOS: 1.0.0 - 2.0.0",
    "watchOS: 8.0.0 - 11.0.0"
  ],
  "documentType" : "symbol",
  "framework" : "Accelerate",
  "identifier" : "/documentation/Accelerate/BNNSComputeNormBackward(_:_:_:_:_:_:)",
  "metadataVersion" : "0.1.0",
  "role" : "Function",
  "symbol" : {
    "kind" : "Function",
    "modules" : [
      "Accelerate"
    ],
    "preciseIdentifier" : "c:@F@BNNSComputeNormBackward"
  },
  "title" : "BNNSComputeNormBackward(_:_:_:_:_:_:)"
}
-->

# BNNSComputeNormBackward(_:_:_:_:_:_:)

Backpropogates gradients for the compute norm function.

```
func BNNSComputeNormBackward(_ in: UnsafeRawPointer, _ in_delta: UnsafeMutablePointer<BNNSNDArrayDescriptor>, _ out: UnsafeRawPointer, _ out_delta: UnsafePointer<BNNSNDArrayDescriptor>, _ norm_type: BNNSNormType, _ axis_flags: UInt32) -> Int32
```

## Parameters

`in`

The descriptor of the input.

`in_delta`

The descriptor of the input delta.

`out`

The descriptor of the output.

`out_delta`

The descriptor of the output delta.

`norm_type`

The type of the norm. This function supports only [`BNNSL2Norm`](/documentation/Accelerate/BNNSL2Norm).

`axis_flags`

The dimensions that the function uses to compute the norm. Set to `0` to specify that the function computes the norm over all dimensions.

## Discussion

---

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)