[llvm] InstCombine: improve optimizations for ceiling division with no overflow (PR #142869)

[Yingwei Zheng via llvm-commits]

================
@@ -1787,6 +1787,50 @@ Instruction *InstCombinerImpl::visitAdd(BinaryOperator &I) {
   if (Instruction *Ashr = foldAddToAshr(I))
     return Ashr;
 
+  // Ceiling division by power-of-2:
+  // (X >> log2(N)) + zext(X & (N-1) != 0) --> (X + (N-1)) >> log2(N)
+  // This is valid when adding (N-1) to X doesn't overflow.
+  {
+    Value *X = nullptr, *Cmp = nullptr;
+    const APInt *ShiftAmt = nullptr, *Mask = nullptr;
+    CmpPredicate Pred;
+
+    // Match: (X >> C) + zext((X & Mask) != 0)
+    // or:    zext((X & Mask) != 0) + (X >> C)
+    Value *Op0 = I.getOperand(0);
+    Value *Op1 = I.getOperand(1);
+
+    // Try matching with shift on left, zext on right
+    bool Matched = false;
+    if (match(Op0, m_LShr(m_Value(X), m_APInt(ShiftAmt))) &&
----------------
dtcxzyw wrote:

Please use `m_c_Add(m_LShr(xxx), m_ZExt(xxx))` instead.


https://github.com/llvm/llvm-project/pull/142869