# AMDGPU.jl and AMD Instinct MI300A APUs

**URL:** <https://discourse.julialang.org/t/amdgpu-jl-and-amd-instinct-mi300a-apus/114850>\
**Category:** GPU\
**Tags:** question, compatibility, amdgpu\
**Created:** [May 28, 2024, 3:24pm UTC](https://discourse.julialang.org/t/amdgpu-jl-and-amd-instinct-mi300a-apus/114850 "2024-05-28T15:24:17Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![cameg27](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/cameg27/32/209558_2.png) [@cameg27](https://discourse.julialang.org/u/cameg27)\
**Post date:** [May 28, 2024, 3:24pm UTC](https://discourse.julialang.org/t/amdgpu-jl-and-amd-instinct-mi300a-apus/114850/1 "2024-05-28T15:24:17Z")

</div>

Hi everyone,

At my research institute, we’re considering purchasing a server equipped with four AMD Instinct MI300A APUs. Our numerical code is entirely written in Julia and currently runs smoothly on NVIDIA GPUs using `CUDA.jl`. However, we’re concerned about the compatibility of `AMDGPU.jl` with the MI300A.

As discussed in [this GitHub issue](https://github.com/JuliaGPU/AMDGPU.jl/issues/621), support for the gfx942 architecture was added in LLVM v17. The upgrade to LLVM v17 appears to have been merged into the master branch of Julia a few weeks ago ([Bump LLVM to v17](https://github.com/JuliaLang/julia/pull/53070)), so I suppose it will be available in one of the upcoming releases.

Does anyone see any additional issues with using the MI300A with `AMDGPU.jl`, especially considering the unified memory structure of these new APUs?

Thanks in advance for your help!

---

<div class="post-metadata">

**Author:** ![gbaraldi](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/gbaraldi/32/22101_2.png) [@gbaraldi](https://discourse.julialang.org/u/gbaraldi)\
**Post date:** [May 28, 2024, 4:18pm UTC](https://discourse.julialang.org/t/amdgpu-jl-and-amd-instinct-mi300a-apus/114850/2 "2024-05-28T16:18:28Z")

</div>

Regarding unified memory, AMDGPU already uses it on normal (non mi300A/300x) gpus. So it should work the same except faster.  
IIRC amdgpu arches are backwards compatible so you might lose on a couple of features before llvm17 is there but it should all work. If you have any further questions I believe the `#gpu` channel in slack will get you better/faster answers.