[llvm] [AArch64] Tune unrolling prefs for more patterns on Apple CPUs (PR #149358)

[Florian Hahn via llvm-commits]

================
@@ -4802,16 +4802,17 @@ getAppleRuntimeUnrollPreferences(Loop *L, ScalarEvolution &SE,
   // Limit to loops with trip counts that are cheap to expand.
   UP.SCEVExpansionBudget = 1;
 
-  // Try to unroll small, single block loops, if they have load/store
-  // dependencies, to expose more parallel memory access streams.
+  // Try to unroll small loops, of few-blocks with low budget, if they have
+  // load/store dependencies, to expose more parallel memory access streams,
+  // or if they do little work inside a block (i.e. load -> X -> store pattern).
   BasicBlock *Header = L->getHeader();
   if (Header == L->getLoopLatch()) {
     // Estimate the size of the loop.
-    unsigned Size;
-    if (!isLoopSizeWithinBudget(L, TTI, 8, &Size))
+    unsigned Size, Width=10;
----------------
fhahn wrote:

```suggestion
    unsigned Size;
    unsigned Width =10;
```

LLVM style generally avoids declaring multiple variables in the same line.

https://github.com/llvm/llvm-project/pull/149358