[PATCH] D96386: [AMDGPU] Fix promote alloca with double use in a same insn

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/promote-alloca-mem-intrinsics.ll:79
+}
+
 attributes #0 = { nounwind "amdgpu-flat-work-group-size"="64,64" "amdgpu-waves-per-eu"="1,3" }
----------------
arsenm wrote:
> Can you also add tests with select and phi both derived from the same
We have these tests. One in promote-alloca-to-lds-select.ll @lds_promote_alloca_select_two_derived_pointers, one in the promote-alloca-to-lds-phi.ll @branch_ptr_var_same_alloca. This works because we only update operands not replacing the instruction. Problem with the memcpy is that we actually create a new call which is not going to be hit when we touch second operand.

One possible solution I am exploring is to postpone patching memory intrinsics until the end. Another is to patch the call in place.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D96386/new/

https://reviews.llvm.org/D96386