---
title: "run(on:inputs:results:executionDescriptor:)"
framework: metalperformanceshadersgraph
role: symbol
role_heading: Instance Method
path: "metalperformanceshadersgraph/mpsgraphexecutable/run(on:inputs:results:executiondescriptor:)"
---

# run(on:inputs:results:executionDescriptor:)

Runs the graph for the given feeds and returns the target tensor values, ensuring all target operations also executed.

## Declaration

```swift
func run(on commandQueue: any MTL4CommandQueue, inputs inputsArray: [MPSGraphTensorData], results resultsArray: [MPSGraphTensorData]?, executionDescriptor: MPSGraphExecutableExecutionDescriptor?) -> [MPSGraphTensorData]
```

## Parameters

- `commandQueue`: MTL4CommandQueue passed to exectute the graph on.
- `inputsArray`: Feeds tensorData for the placeholder tensors, same order as arguments of main function.
- `resultsArray`: Results tensorData for which the caller wishes MPSGraphTensorData to be returned.

## Return Value

Return Value A valid MPSGraphTensorData array with results synchronized to the CPU memory if MPSGraphOptionsSynchronizeResults set.

## Discussion

Discussion This call is synchronous and will return on completion of execution.