[llvm] [LoopVectorize][LAA] Hoist load in memory IV to allow vectorization (PR #168312)

[Florian Hahn via llvm-commits]

================
@@ -25,7 +25,7 @@ loop:
   store i32 %l, ptr %gep
   %iv.next = add i32 %iv, 1
   %ec = icmp eq i32 %iv.next, 100
-  br i1 %ec, label %exit, label %loop
+  br i1 %ec, label %exit, label %loop, !llvm.loop !0
----------------
fhahn wrote:

why is this needed?

https://github.com/llvm/llvm-project/pull/168312