# Portability of Fortran's \`do concurrent' on GPUs

**URL:** <https://fortran-lang.discourse.group/t/portability-of-fortrans-do-concurrent-on-gpus/8487>\
**Category:** Compilers\
**Created:** [August 16, 2024, 2:26pm UTC](https://fortran-lang.discourse.group/t/portability-of-fortrans-do-concurrent-on-gpus/8487 "2024-08-16T14:26:56Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![Pranavchiku](https://avatars.discourse-cdn.com/v4/letter/p/cab0a1/32.png) [@Pranavchiku](https://fortran-lang.discourse.group/u/Pranavchiku)\
**Post date:** [August 18, 2024, 6:07am UTC](https://fortran-lang.discourse.group/t/portability-of-fortrans-do-concurrent-on-gpus/8487/2 "2024-08-18T06:07:12Z")

</div>

You may wish to check [LFortran-supports-do-concurrent](https://fortran-lang.discourse.group/t/lfortran-supports-openmp-pragmas-and-do-concurrent/8415) and the plan to start implementing GPU offloading, here are the issues for that:

- NVIDIA: [NVIDIA GPU support · Issue #4497 · lfortran/lfortran · GitHub](https://github.com/lfortran/lfortran/issues/4497)
- AMD: [Offload do concurrent to AMD GPUs · Issue #4535 · lfortran/lfortran · GitHub](https://github.com/lfortran/lfortran/issues/4535)

---

_[View the full topic](https://fortran-lang.discourse.group/t/portability-of-fortrans-do-concurrent-on-gpus/8487)._