[llvm] [AArch64] Add flag to control unrolling for small multi-exit loops (PR #131998)

[Florian Hahn via llvm-commits]

================
@@ -4237,6 +4242,70 @@ getFalkorUnrollingPreferences(Loop *L, ScalarEvolution &SE,
   }
 }
 
+static bool shouldUnrollLoopWithInstruction(Instruction &I,
+                                            AArch64TTIImpl &TTI) {
+  // Don't unroll vectorised loop.
+  if (I.getType()->isVectorTy())
+    return false;
+
+  if (isa<CallInst>(I) || isa<InvokeInst>(I)) {
+    if (const Function *F = cast<CallBase>(I).getCalledFunction())
+      if (!TTI.isLoweredToCall(F))
+        return true;
+    return false;
+  }
+
+  return true;
+}
+
+static bool shouldUnrollSmallMultiExitLoop(Loop *L, ScalarEvolution &SE,
----------------
fhahn wrote:

The code block should handle small multi exit loops as advertised (tests are in `llvm/test/Transforms/LoopUnroll/AArch64/apple-unrolling-multi-exit.ll`). `getExitBlock()` should return the single exit block if the loop has a single exit & exiting block. 

If there are multiple exiting blocks to the same exit, the exit block will be included multiple times in getExitBlocks(); This is different from `getUniqueExitBlock`, which would return the common exit block, even if there are multiple exiting blocks branching to it.

https://github.com/llvm/llvm-project/pull/131998