# GROMACS SYCL for NVIDIA GPUs

**URL:** https://gromacs.bioexcel.eu/t/gromacs-sycl-for-nvidia-gpus/6441
**Category:** User discussions
**Created:** [May 18, 2023, 8:51pm UTC](https://gromacs.bioexcel.eu/t/gromacs-sycl-for-nvidia-gpus/6441 "2023-05-18T20:51:29Z")
**Posts on this page:** 1
**Showing post:** 26

<div class="post-metadata">

### Author: ![al42and](https://dub1.discourse-cdn.com/flex017/user_avatar/gromacs.bioexcel.eu/al42and/32/1393_2.png) [@al42and](https://gromacs.bioexcel.eu/u/al42and)
#### Post date: [October 3, 2023, 5:03pm UTC](https://gromacs.bioexcel.eu/t/gromacs-sycl-for-nvidia-gpus/6441/26 "2023-10-03T17:03:18Z")

</div>

Hi!

Sorry for not following up, I could not reproduce the issue with our available software at the time, but we only had CUDA 11.8 installed. I guess you managed to get it working? Did the new oneAPI version fix things?

> [@kaleyogeshs](#):
>
> I have one question is this regard, when running workflows via SYCL are these sub-groups automatically enabled ?

Sub-groups are hardware property, so they are always enabled :) We do use sub-group level functionality on all GPUs in both CUDA and SYCL, so this should not cause any performance discrepancy.

> [@kaleyogeshs](#):
>
> and also are there any benchmarking results out ? so that we can compare against it.

A very extensive performance review has been recently shared by @Entropy_YU: [A series of performance benchmarks for MD Apps, including GROMACS](https://gromacs.bioexcel.eu/t/a-series-of-performance-benchmarks-for-md-apps-including-gromacs/7078)

Here’s the comparison with CUDA from their post:

 ![image](https://europe1.discourse-cdn.com/flex017/uploads/bioexcel1/original/2X/f/f901b994391ec6aae4a5932a791d6fb93ceff4c5.png)

80-85% is consistent with our internal measurements for systems of similar size (we did not run a thorough comparison)

---

_[View the full topic](https://gromacs.bioexcel.eu/t/gromacs-sycl-for-nvidia-gpus/6441)._