[PATCH] D106891: [AMDGPU] [Remarks] Emit optimization remarks for FP atomics

[Stanislav Mekhanoshin via Phabricator via cfe-commits]

rampitec added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:12155
+          OptimizationRemark Remark(DEBUG_TYPE, "Passed", RMW->getFunction());
+          Remark << "A floating-point atomic instruction with no following use"
+                    " will generate an unsafe hardware instruction";
----------------
gandhi21299 wrote:
> rampitec wrote:
> > I do not understand this message about the use. We are checking the use below simply because there was no return version of global_atomic_add_f32 on gfx908, so we are forced to expand it.
> right, I forgot to erase that part. How does the following look:
> 
> "A floating-point atomic instruction will generate an unsafe hardware instruction"
> 
> I am not sure what other details I could put in here
In this place it might fail to update memory. But it is difficult to read and understand with all of that big ORE->emit blobs all over the place.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D106891/new/

https://reviews.llvm.org/D106891