[PATCH] D83862: [AMDGPU] Add missing test prefixes

[Jay Foad via Phabricator via llvm-commits]

foad abandoned this revision.
foad marked an inline comment as done.
foad added a comment.

All changes have been committed or split out into another review.



================
Comment at: llvm/test/CodeGen/AMDGPU/perfhint.ll:87
+; GCN: MemoryBound: 0
+; GCN: WaveLimiterHint : 0
 define amdgpu_kernel void @test_indirect_through_phi(float addrspace(1)* %arg) {
----------------
rampitec wrote:
> foad wrote:
> > rampitec wrote:
> > > foad wrote:
> > > > This check fails. Perhaps D47740 never worked?
> > > Looks like it did not :(
> > > 
> > > Anyway, this case is not memory bound even though it is indirect. This is because we have a single load followed by multiple stores, that was the point of the check.
> > The problem is that after AMDGPULowerKernelArguments, the load from %arg looks like this:
> > ```
> >   %arg.load = load float addrspace(1)*, float addrspace(1)* addrspace(4)* %arg.kernarg.offset.cast, align 4, !invariant.load !0
> >   %load = load float, float addrspace(1)* %arg.load, align 8
> > ```
> > which is indirect. Any ideas?
> A-ha! The representation changed, but we did not catch it because of the broken test.
> 
> The first load is from constant, so it is uniform. I suppose we can ignore constant address space for this purpose. It creates much less memory traffic.
I've done this in D84301.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D83862/new/

https://reviews.llvm.org/D83862