# Implementing OpenCL backend for pytorch

**URL:** https://dev-discuss.pytorch.org/t/implementing-opencl-backend-for-pytorch/283
**Category:** hardware-backends
**Created:** [July 26, 2021, 1:05pm UTC](https://dev-discuss.pytorch.org/t/implementing-opencl-backend-for-pytorch/283 "2021-07-26T13:05:05Z")
**Posts on this page:** 1
**Showing post:** 9

<div class="post-metadata">

### Author: ![artyom-beilis](https://yyz2.discourse-cdn.com/flex036/user_avatar/dev-discuss.pytorch.org/artyom-beilis/32/207_2.png) [@artyom-beilis](https://dev-discuss.pytorch.org/u/artyom-beilis)
#### Post date: [October 10, 2021, 7:07am UTC](https://dev-discuss.pytorch.org/t/implementing-opencl-backend-for-pytorch/283/9 "2021-10-10T07:07:11Z")

</div>

Small updated: I implemented GPU memory caching + asynchronous execution and got performance results virtually identical for my static graph dlprimitives execution.

Now it works efficiently for all GPUs I tested AMD, 6600XT NVidia 960 and Intel GPUs 530.  
Also I fixed pytorch benchmark that by accident didn’t include copy to gpu time and now run times on 960 are ~15ms on pytorch cuda/cudnn 960 and ~22ms on dlprimitives

---

_[View the full topic](https://dev-discuss.pytorch.org/t/implementing-opencl-backend-for-pytorch/283)._