# Update on using Fortran Standard on NVIDIA, Intel, and AMD GPUs

**URL:** <https://fortran-lang.discourse.group/t/update-on-using-fortran-standard-on-nvidia-intel-and-amd-gpus/11064>\
**Category:** Announcements\
**Created:** [August 25, 2026, 1:38am UTC](https://fortran-lang.discourse.group/t/update-on-using-fortran-standard-on-nvidia-intel-and-amd-gpus/11064 "2026-08-25T01:38:13Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![sumseq](https://yyz2.discourse-cdn.com/free1/user_avatar/fortran-lang.discourse.group/sumseq/32/3083_2.png) [@sumseq](https://fortran-lang.discourse.group/u/sumseq)\
**Post date:** [August 25, 2026, 1:38am UTC](https://fortran-lang.discourse.group/t/update-on-using-fortran-standard-on-nvidia-intel-and-amd-gpus/11064/1 "2026-08-25T01:38:13Z")

</div>

Want to run your Fortran codes on GPUs but don’t want to add external APIs or directives?  
Check out our new paper on using Fortran’s “do concurrent” to run on NVIDIA, AMD, and Intel GPUs!

[https://arxiv.org/abs/2608.20586](https://t.co/4mhLnoYs54)

Adding OpenMP data movement directives can help with efficiency (on Intel GPUs) and for some GPUs are required (AMD consumer GPUs), but for many cases, “Fortran-only” works great - even across multiple multi-GPU nodes!

- Ron

---

<div class="post-metadata">

**Author:** ![RJaBi](https://yyz2.discourse-cdn.com/free1/user_avatar/fortran-lang.discourse.group/rjabi/32/5161_2.png) [@RJaBi](https://fortran-lang.discourse.group/u/RJaBi)\
**Post date:** [August 25, 2026, 2:29am UTC](https://fortran-lang.discourse.group/t/update-on-using-fortran-standard-on-nvidia-intel-and-amd-gpus/11064/2 "2026-08-25T02:29:33Z")

</div>

I’m excited to see the improvements in Unified Shared Memory – Now I just need to get around to installing linux on my Intel B580 Machine… (I have confidence that by the time the code is production ready, that the efficiency will have been improved 😅 )