[PATCH] D42756: AMDGPU: Remove the s_buffer workaround for GFX9 chips

[Marek Olšák via Phabricator via llvm-commits]

mareko added a comment.

In https://reviews.llvm.org/D42756#995101, @arsenm wrote:

> In https://reviews.llvm.org/D42756#995044, @mareko wrote:
>
> > In https://reviews.llvm.org/D42756#995040, @arsenm wrote:
> >
> > > We probably do want to do that optimization at some point, although in that case I would hope we would avoid producing them in the buggy case. Can you add more details to the comment here, and possibly leave it?
> >
> >
> > What details? Can you be more specific about what you're asking here?
>
>
> Like you mentioned in the commit message that there is a problem with x3 loads only.


SMEM x3 opcodes don't exist, and instead there is a possibility to use x4 with the last component being unused. If the last component is out of buffer bounds and falls on the next 4K page, the hw hangs.


Repository:
  rL LLVM

https://reviews.llvm.org/D42756