# Numba-MLIR GPU offload

**URL:** <https://numba.discourse.group/t/numba-mlir-gpu-offload/1981>\
**Category:** Numba\
**Created:** [June 8, 2023, 6:36pm UTC](https://numba.discourse.group/t/numba-mlir-gpu-offload/1981 "2023-06-08T18:36:04Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![pauljurczak](https://yyz2.discourse-cdn.com/free1/user_avatar/numba.discourse.group/pauljurczak/32/479_2.png) [@pauljurczak](https://numba.discourse.group/u/pauljurczak)\
**Post date:** [June 8, 2023, 6:36pm UTC](https://numba.discourse.group/t/numba-mlir-gpu-offload/1981/1 "2023-06-08T18:36:04Z")

</div>

I watched the presentation announced in [Numba Meeting June 6 2023: Presentation on Numba-MLIR - #2 by sklam](https://numba.discourse.group/t/numba-meeting-june-6-2023-presentation-on-numba-mlir/1959/2) and installed Numba-MLIR with:

```auto
conda install numba-mlir -c dppy/label/dev -c intel -c conda-forge -c numba

```

A simple example:

```auto
from numba_mlir import njit
import numpy as np

@njit (parallel=True)
def foo(a, b):
    return a + b

result = foo(np.array([1,2,3]), np.array([4,5,6]))
print(result)

```

runs fine. There is no documentation yet and I don’t know how to control where this script is run: CPU vs. GPU. What is the way to offload it to an Intel integrated GPU?

* * *

Cross-posted to [How to offload to Intel integrated GPU? · Issue #131 · numba/numba-mlir · GitHub](https://github.com/numba/numba-mlir/issues/131)