Reland `[CodeGenPrepare] Convert `ctpop(X) ==/!= 1` into `ctpop(X) u</u> 2/1` (#111284)` (#111998)

Relands #111284. Test failure with stage2 build has been fixed by
https://github.com/llvm/llvm-project/pull/111946.


Some targets have better codegen for `ctpop(X) u< 2` than `ctpop(X) ==
1`. After https://github.com/llvm/llvm-project/pull/100899, we set the
range of ctpop's return value to indicate the argument/result is
non-zero.

This patch converts `ctpop(X) ==/!= 1` into `ctpop(X) u</u> 2/1` in CGP
to fix https://github.com/llvm/llvm-project/issues/95255.

1 files changed, 28 insertions, 0 deletions

diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp
index 3e09fba..86f2829 100644
--- a/llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ b/llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -2111,6 +2111,31 @@ bool CodeGenPrepare::optimizeURem(Instruction *Rem) {
   return false;
 }
 
+/// Some targets have better codegen for `ctpop(X) u< 2` than `ctpop(X) == 1`.
+/// This function converts `ctpop(X) ==/!= 1` into `ctpop(X) u</u> 2/1` if the
+/// result cannot be zero.
+static bool adjustIsPower2Test(CmpInst *Cmp, const TargetLowering &TLI,
+                               const TargetTransformInfo &TTI,
+                               const DataLayout &DL) {
+  ICmpInst::Predicate Pred;
+  if (!match(Cmp, m_ICmp(Pred, m_Intrinsic<Intrinsic::ctpop>(), m_One())))
+    return false;
+  if (!ICmpInst::isEquality(Pred))
+    return false;
+  auto *II = cast<IntrinsicInst>(Cmp->getOperand(0));
+
+  if (isKnownNonZero(II, DL)) {
+    if (Pred == ICmpInst::ICMP_EQ) {
+      Cmp->setOperand(1, ConstantInt::get(II->getType(), 2));
+      Cmp->setPredicate(ICmpInst::ICMP_ULT);
+    } else {
+      Cmp->setPredicate(ICmpInst::ICMP_UGT);
+    }
+    return true;
+  }
+  return false;
+}
+
 bool CodeGenPrepare::optimizeCmp(CmpInst *Cmp, ModifyDT &ModifiedDT) {
   if (sinkCmpExpression(Cmp, *TLI))
     return true;
@@ -2130,6 +2155,9 @@ bool CodeGenPrepare::optimizeCmp(CmpInst *Cmp, ModifyDT &ModifiedDT) {
   if (foldFCmpToFPClassTest(Cmp, *TLI, *DL))
     return true;
 
+  if (adjustIsPower2Test(Cmp, *TLI, *TTI, *DL))
+    return true;
+
   return false;
 }