[InstCombine] Fold `select Cond, not X, X` into `Cond ^ X` (#93591)

See the following example:
```
define i1 @src(i64 %x, i1 %y) {
  %1526 = icmp ne i64 %x, 0
  %1527 = icmp eq i64 %x, 0
  %sel = select i1 %y, i1 %1526, i1 %1527
  ret i1 %sel
}

define i1 @tgt(i64 %x, i1 %y) {
  %1527 = icmp eq i64 %x, 0
  %sel = xor i1 %y, %1527
  ret i1 %sel
}
```
I find that this pattern is common in C/C++/Rust code base.
This patch folds `select Cond, Y, X` into `Cond ^ X` iff:
1. X has the same type as Cond
2. X is poison -> Y is poison
3. X == !Y

Alive2: https://alive2.llvm.org/ce/z/hSmkHS

2 files changed, 166 insertions, 0 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp b/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
index a9aba55..313beb7 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
@@ -3505,6 +3505,33 @@ static bool matchFMulByZeroIfResultEqZero(InstCombinerImpl &IC, Value *Cmp0,
   return false;
 }
 
+/// Return true iff:
+/// 1. X is poison implies Y is poison.
+/// 2. X is true implies Y is false.
+/// 3. X is false implies Y is true.
+/// Otherwise, return false.
+static bool isKnownInversion(Value *X, Value *Y) {
+  // Handle X = icmp pred A, B, Y = icmp pred A, C.
+  Value *A, *B, *C;
+  ICmpInst::Predicate Pred1, Pred2;
+  if (!match(X, m_ICmp(Pred1, m_Value(A), m_Value(B))) ||
+      !match(Y, m_c_ICmp(Pred2, m_Specific(A), m_Value(C))))
+    return false;
+
+  if (B == C)
+    return Pred1 == ICmpInst::getInversePredicate(Pred2);
+
+  // Try to infer the relationship from constant ranges.
+  const APInt *RHSC1, *RHSC2;
+  if (!match(B, m_APInt(RHSC1)) || !match(C, m_APInt(RHSC2)))
+    return false;
+
+  const auto CR1 = ConstantRange::makeExactICmpRegion(Pred1, *RHSC1);
+  const auto CR2 = ConstantRange::makeExactICmpRegion(Pred2, *RHSC2);
+
+  return CR1.inverse() == CR2;
+}
+
 Instruction *InstCombinerImpl::visitSelectInst(SelectInst &SI) {
   Value *CondVal = SI.getCondition();
   Value *TrueVal = SI.getTrueValue();
@@ -3999,5 +4026,9 @@ Instruction *InstCombinerImpl::visitSelectInst(SelectInst &SI) {
     }
   }
 
+  // select Cond, !X, X -> xor Cond, X
+  if (CondVal->getType() == SI.getType() && isKnownInversion(FalseVal, TrueVal))
+    return BinaryOperator::CreateXor(CondVal, FalseVal);
+
   return nullptr;
 }
diff --git a/llvm/test/Transforms/InstCombine/select-cmp.ll b/llvm/test/Transforms/InstCombine/select-cmp.ll
index 711fac5..4f75745 100644
--- a/llvm/test/Transforms/InstCombine/select-cmp.ll
+++ b/llvm/test/Transforms/InstCombine/select-cmp.ll
@@ -345,4 +345,139 @@ define i1 @icmp_no_common(i1 %c, i8 %x, i8 %y, i8 %z) {
   ret i1 %r
 }
 
+define i1 @test_select_inverse_eq(i64 %x, i1 %y) {
+; CHECK-LABEL: @test_select_inverse_eq(
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp eq i64 [[X:%.*]], 0
+; CHECK-NEXT:    [[SEL:%.*]] = xor i1 [[CMP2]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[SEL]]
+;
+  %cmp1 = icmp ne i64 %x, 0
+  %cmp2 = icmp eq i64 %x, 0
+  %sel = select i1 %y, i1 %cmp1, i1 %cmp2
+  ret i1 %sel
+}
+
+define i1 @test_select_inverse_signed(i64 %x, i1 %y) {
+; CHECK-LABEL: @test_select_inverse_signed(
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp slt i64 [[X:%.*]], 0
+; CHECK-NEXT:    [[SEL:%.*]] = xor i1 [[CMP2]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[SEL]]
+;
+  %cmp1 = icmp sgt i64 %x, -1
+  %cmp2 = icmp slt i64 %x, 0
+  %sel = select i1 %y, i1 %cmp1, i1 %cmp2
+  ret i1 %sel
+}
+
+define i1 @test_select_inverse_unsigned(i64 %x, i1 %y) {
+; CHECK-LABEL: @test_select_inverse_unsigned(
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp ugt i64 [[X:%.*]], 10
+; CHECK-NEXT:    [[SEL:%.*]] = xor i1 [[CMP2]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[SEL]]
+;
+  %cmp1 = icmp ult i64 %x, 11
+  %cmp2 = icmp ugt i64 %x, 10
+  %sel = select i1 %y, i1 %cmp1, i1 %cmp2
+  ret i1 %sel
+}
+
+define i1 @test_select_inverse_eq_ptr(ptr %x, i1 %y) {
+; CHECK-LABEL: @test_select_inverse_eq_ptr(
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp ne ptr [[X:%.*]], null
+; CHECK-NEXT:    [[SEL:%.*]] = xor i1 [[CMP2]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[SEL]]
+;
+  %cmp1 = icmp eq ptr %x, null
+  %cmp2 = icmp ne ptr %x, null
+  %sel = select i1 %y, i1 %cmp1, i1 %cmp2
+  ret i1 %sel
+}
+
+define i1 @test_select_inverse_fail(i64 %x, i1 %y) {
+; CHECK-LABEL: @test_select_inverse_fail(
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp sgt i64 [[X:%.*]], 0
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp slt i64 [[X]], 0
+; CHECK-NEXT:    [[SEL:%.*]] = select i1 [[Y:%.*]], i1 [[CMP1]], i1 [[CMP2]]
+; CHECK-NEXT:    ret i1 [[SEL]]
+;
+  %cmp1 = icmp sgt i64 %x, 0
+  %cmp2 = icmp slt i64 %x, 0
+  %sel = select i1 %y, i1 %cmp1, i1 %cmp2
+  ret i1 %sel
+}
+
+define <2 x i1> @test_select_inverse_vec(<2 x i64> %x, <2 x i1> %y) {
+; CHECK-LABEL: @test_select_inverse_vec(
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp eq <2 x i64> [[X:%.*]], zeroinitializer
+; CHECK-NEXT:    [[SEL:%.*]] = xor <2 x i1> [[CMP2]], [[Y:%.*]]
+; CHECK-NEXT:    ret <2 x i1> [[SEL]]
+;
+  %cmp1 = icmp ne <2 x i64> %x, zeroinitializer
+  %cmp2 = icmp eq <2 x i64> %x, zeroinitializer
+  %sel = select <2 x i1> %y, <2 x i1> %cmp1, <2 x i1> %cmp2
+  ret <2 x i1> %sel
+}
+
+define <2 x i1> @test_select_inverse_vec_fail(<2 x i64> %x, i1 %y) {
+; CHECK-LABEL: @test_select_inverse_vec_fail(
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp ne <2 x i64> [[X:%.*]], zeroinitializer
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp eq <2 x i64> [[X]], zeroinitializer
+; CHECK-NEXT:    [[SEL:%.*]] = select i1 [[Y:%.*]], <2 x i1> [[CMP1]], <2 x i1> [[CMP2]]
+; CHECK-NEXT:    ret <2 x i1> [[SEL]]
+;
+  %cmp1 = icmp ne <2 x i64> %x, zeroinitializer
+  %cmp2 = icmp eq <2 x i64> %x, zeroinitializer
+  %sel = select i1 %y, <2 x i1> %cmp1, <2 x i1> %cmp2
+  ret <2 x i1> %sel
+}
+
+define i1 @test_select_inverse_nonconst1(i64 %x, i64 %y, i1 %cond) {
+; CHECK-LABEL: @test_select_inverse_nonconst1(
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp eq i64 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[SEL:%.*]] = xor i1 [[CMP2]], [[COND:%.*]]
+; CHECK-NEXT:    ret i1 [[SEL]]
+;
+  %cmp1 = icmp ne i64 %x, %y
+  %cmp2 = icmp eq i64 %x, %y
+  %sel = select i1 %cond, i1 %cmp1, i1 %cmp2
+  ret i1 %sel
+}
+
+define i1 @test_select_inverse_nonconst2(i64 %x, i64 %y, i1 %cond) {
+; CHECK-LABEL: @test_select_inverse_nonconst2(
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp eq i64 [[Y:%.*]], [[X:%.*]]
+; CHECK-NEXT:    [[SEL:%.*]] = xor i1 [[CMP2]], [[COND:%.*]]
+; CHECK-NEXT:    ret i1 [[SEL]]
+;
+  %cmp1 = icmp ne i64 %x, %y
+  %cmp2 = icmp eq i64 %y, %x
+  %sel = select i1 %cond, i1 %cmp1, i1 %cmp2
+  ret i1 %sel
+}
+
+define i1 @test_select_inverse_nonconst3(i64 %x, i64 %y, i1 %cond) {
+; CHECK-LABEL: @test_select_inverse_nonconst3(
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp uge i64 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[SEL:%.*]] = xor i1 [[CMP2]], [[COND:%.*]]
+; CHECK-NEXT:    ret i1 [[SEL]]
+;
+  %cmp1 = icmp ult i64 %x, %y
+  %cmp2 = icmp uge i64 %x, %y
+  %sel = select i1 %cond, i1 %cmp1, i1 %cmp2
+  ret i1 %sel
+}
+
+define i1 @test_select_inverse_nonconst4(i64 %x, i64 %y, i64 %z, i1 %cond) {
+; CHECK-LABEL: @test_select_inverse_nonconst4(
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp ult i64 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[CMP2:%.*]] = icmp uge i64 [[Z:%.*]], [[Y]]
+; CHECK-NEXT:    [[SEL:%.*]] = select i1 [[COND:%.*]], i1 [[CMP1]], i1 [[CMP2]]
+; CHECK-NEXT:    ret i1 [[SEL]]
+;
+  %cmp1 = icmp ult i64 %x, %y
+  %cmp2 = icmp uge i64 %z, %y
+  %sel = select i1 %cond, i1 %cmp1, i1 %cmp2
+  ret i1 %sel
+}
+
 declare void @use(i1)