[LAA] Don't assume libcalls with output/input pointers can be vectorized (#108980)

LoopAccessAnalysis currently does not check/track aliasing from the
output pointers, but assumes vectorizing library calls with a mapping is
safe.

This can result in incorrect codegen if something like the following is
vectorized:

```
for(int i=0; i<N; i++) {
  // No aliasing between input and output pointers detected.
  sincos(cos_out[0], sin_out+i, cos_out+i);
}
```

Where for VF >= 2 `cos_out[1]` to `cos_out[VF-1]` is the cosine of the
original value of `cos_out[0]` not the updated value.

1 files changed, 12 insertions, 5 deletions

diff --git a/llvm/lib/Analysis/LoopAccessAnalysis.cpp b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
index 980f142..3f18972 100644
--- a/llvm/lib/Analysis/LoopAccessAnalysis.cpp
+++ b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
@@ -2449,13 +2449,20 @@ bool LoopAccessInfo::analyzeLoop(AAResults *AA, const LoopInfo *LI,
         continue;
 
       // If this is a load, save it. If this instruction can read from memory
-      // but is not a load, then we quit. Notice that we don't handle function
-      // calls that read or write.
+      // but is not a load, we only allow it if it's a call to a function with a
+      // vector mapping and no pointer arguments.
       if (I.mayReadFromMemory()) {
-        // If the function has an explicit vectorized counterpart, we can safely
-        // assume that it can be vectorized.
+        auto hasPointerArgs = [](CallBase *CB) {
+          return any_of(CB->args(), [](Value const *Arg) {
+            return Arg->getType()->isPointerTy();
+          });
+        };
+
+        // If the function has an explicit vectorized counterpart, and does not
+        // take output/input pointers, we can safely assume that it can be
+        // vectorized.
         if (Call && !Call->isNoBuiltin() && Call->getCalledFunction() &&
-            !VFDatabase::getMappings(*Call).empty())
+            !hasPointerArgs(Call) && !VFDatabase::getMappings(*Call).empty())
           continue;
 
         auto *Ld = dyn_cast<LoadInst>(&I);