[PATCH] D129690: [LLVM][AMDGPU] Specialize 32-bit atomic fadd instruction for generic address space

[Shilei Tian via Phabricator via llvm-commits]

tianshilei1992 added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:12804
       if (AS == AMDGPUAS::FLAT_ADDRESS)
-        return AtomicExpansionKind::CmpXChg;
+        return AtomicExpansionKind::Expand;
 
----------------
rampitec wrote:
> tianshilei1992 wrote:
> > rampitec wrote:
> > > At this point this is gfx908 and gfx11. Then gfx11 has flat_atomic_add_f32.
> > > 
> > > It also appears to return Expand for double, but emitExpandAtomicRMW does not support doubles.
> > Thanks for the info. I'll make the change accordingly.
> > Is there any place listing those support among different versions? In that way I can have a complete picture?
> I was checking our own MC tests. I found it easiest.
K, gotcha. Thx!


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D129690/new/

https://reviews.llvm.org/D129690