[InstCombine] Fold min(X+1, Y) - min(X, Y) --> zext X < Y

llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp

@@ -2719,6 +2719,24 @@ Instruction *InstCombinerImpl::visitSub(BinaryOperator &I) {
     return BinaryOperator::CreateSub(X, Not);
   }
 
+  // min(X+1, Y) - min(X, Y) --> zext X < Y
+  // Replacing a sub and at least one min with an icmp
+  // and a zext is a potential improvement.
+  if (match(Op0, m_c_SMin(m_c_NSWAdd(m_Value(X), m_One()), m_Value(Y))) &&
+      match(Op1, m_c_SMin(m_Value(X), m_Value(Y))) &&
+      I.getType()->getScalarSizeInBits() != 1 &&
+      (Op0->hasOneUse() || Op1->hasOneUse())) {
+    Value *Cond = Builder.CreateICmpSLT(X, Y);
+    return new ZExtInst(Cond, I.getType());
+  }
+  if (match(Op0, m_c_UMin(m_c_NUWAdd(m_Value(X), m_One()), m_Value(Y))) &&
+      match(Op1, m_c_UMin(m_Value(X), m_Value(Y))) &&
+      I.getType()->getScalarSizeInBits() != 1 &&
+      (Op0->hasOneUse() || Op1->hasOneUse())) {
+    Value *Cond = Builder.CreateICmpULT(X, Y);
+    return new ZExtInst(Cond, I.getType());
+  }
+
   // Optimize pointer differences into the same array into a size.  Consider:
   //  &A[10] - &A[0]: we should compile this to "10".
   Value *LHSOp, *RHSOp;

llvm/test/Transforms/InstCombine/min-zext.ll

@@ -0,0 +1,116 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt < %s -passes=instcombine -S | FileCheck %s
+
+define i32 @test_smin(i32 %arg0, i32 %arg1) {
+; CHECK-LABEL: define i32 @test_smin(
+; CHECK-SAME: i32 [[ARG0:%.*]], i32 [[ARG1:%.*]]) {
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp slt i32 [[ARG0]], [[ARG1]]
+; CHECK-NEXT:    [[V3:%.*]] = zext i1 [[TMP1]] to i32
+; CHECK-NEXT:    ret i32 [[V3]]
+;
+  %v0 = tail call i32 @llvm.smin.i32(i32 %arg0, i32 %arg1)
+  %v1 = add nsw i32 %arg0, 1
+  %v2 = tail call i32 @llvm.smin.i32(i32 %v1, i32 %arg1)
+  %v3 = sub i32 %v2, %v0
+  ret i32 %v3
+}
+
+define i32 @test_umin(i32 %arg0, i32 %arg1) {
+; CHECK-LABEL: define i32 @test_umin(
+; CHECK-SAME: i32 [[ARG0:%.*]], i32 [[ARG1:%.*]]) {
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i32 [[ARG0]], [[ARG1]]
+; CHECK-NEXT:    [[V3:%.*]] = zext i1 [[TMP1]] to i32
+; CHECK-NEXT:    ret i32 [[V3]]
+;
+  %v0 = tail call i32 @llvm.umin.i32(i32 %arg0, i32 %arg1)
+  %v1 = add nuw i32 %arg0, 1
+  %v2 = tail call i32 @llvm.umin.i32(i32 %v1, i32 %arg1)
+  %v3 = sub i32 %v2, %v0
+  ret i32 %v3
+}
+
+define i1 @test_smin_i1(i1 %arg0, i1 %arg1) {
+; CHECK-LABEL: define i1 @test_smin_i1(
+; CHECK-SAME: i1 [[ARG0:%.*]], i1 [[ARG1:%.*]]) {
+; CHECK-NEXT:    [[V0:%.*]] = or i1 [[ARG0]], [[ARG1]]
+; CHECK-NEXT:    [[V3:%.*]] = xor i1 [[V0]], true
+; CHECK-NEXT:    ret i1 [[V3]]
+;
+  %v0 = tail call i1 @llvm.smin.i1(i1 %arg0, i1 %arg1)
+  %v1 = add nsw i1 %arg0, 1
+  %v2 = tail call i1 @llvm.smin.i1(i1 %v1, i1 %arg1)
+  %v3 = sub i1 %v2, %v0
+  ret i1 %v3
+}
+
+declare void @use(i2)
+
+define i2 @test_smin_use_operands(i2 %arg0, i2 %arg1) {
+; CHECK-LABEL: define i2 @test_smin_use_operands(
+; CHECK-SAME: i2 [[ARG0:%.*]], i2 [[ARG1:%.*]]) {
+; CHECK-NEXT:    [[V0:%.*]] = tail call i2 @llvm.smin.i2(i2 [[ARG0]], i2 [[ARG1]])
+; CHECK-NEXT:    [[V1:%.*]] = add nsw i2 [[ARG0]], 1
+; CHECK-NEXT:    [[V2:%.*]] = tail call i2 @llvm.smin.i2(i2 [[V1]], i2 [[ARG1]])
+; CHECK-NEXT:    [[V3:%.*]] = sub i2 [[V2]], [[V0]]
+; CHECK-NEXT:    call void @use(i2 [[V2]])
+; CHECK-NEXT:    call void @use(i2 [[V0]])
+; CHECK-NEXT:    ret i2 [[V3]]
+;
+  %v0 = tail call i2 @llvm.smin.i2(i2 %arg0, i2 %arg1)
+  %v1 = add nsw i2 %arg0, 1
+  %v2 = tail call i2 @llvm.smin.i2(i2 %v1, i2 %arg1)
+  %v3 = sub i2 %v2, %v0
+  call void @use(i2 %v2)
+  call void @use(i2 %v0)
+  ret i2 %v3
+}
+
+define i2 @test_smin_use_operand(i2 %arg0, i2 %arg1) {
+; CHECK-LABEL: define i2 @test_smin_use_operand(
+; CHECK-SAME: i2 [[ARG0:%.*]], i2 [[ARG1:%.*]]) {
+; CHECK-NEXT:    [[V1:%.*]] = add nsw i2 [[ARG0]], 1
+; CHECK-NEXT:    [[V2:%.*]] = tail call i2 @llvm.smin.i2(i2 [[V1]], i2 [[ARG1]])
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp slt i2 [[ARG0]], [[ARG1]]
+; CHECK-NEXT:    [[V3:%.*]] = zext i1 [[TMP1]] to i2
+; CHECK-NEXT:    call void @use(i2 [[V2]])
+; CHECK-NEXT:    ret i2 [[V3]]
+;
+  %v0 = tail call i2 @llvm.smin.i2(i2 %arg0, i2 %arg1)
+  %v1 = add nsw i2 %arg0, 1
+  %v2 = tail call i2 @llvm.smin.i2(i2 %v1, i2 %arg1)
+  %v3 = sub i2 %v2, %v0
+  call void @use(i2 %v2)
+  ret i2 %v3
+}
+
+define i32 @test_smin_missing_nsw(i32 %arg0, i32 %arg1) {
+; CHECK-LABEL: define i32 @test_smin_missing_nsw(
+; CHECK-SAME: i32 [[ARG0:%.*]], i32 [[ARG1:%.*]]) {
+; CHECK-NEXT:    [[V0:%.*]] = tail call i32 @llvm.smin.i32(i32 [[ARG0]], i32 [[ARG1]])
+; CHECK-NEXT:    [[V1:%.*]] = add i32 [[ARG0]], 1
+; CHECK-NEXT:    [[V2:%.*]] = tail call i32 @llvm.smin.i32(i32 [[V1]], i32 [[ARG1]])
+; CHECK-NEXT:    [[V3:%.*]] = sub i32 [[V2]], [[V0]]
+; CHECK-NEXT:    ret i32 [[V3]]
+;
+  %v0 = tail call i32 @llvm.smin.i32(i32 %arg0, i32 %arg1)
+  %v1 = add i32 %arg0, 1
+  %v2 = tail call i32 @llvm.smin.i32(i32 %v1, i32 %arg1)
+  %v3 = sub i32 %v2, %v0
+  ret i32 %v3
+}
+
+define i32 @test_umin_missing_nuw(i32 %arg0, i32 %arg1) {
+; CHECK-LABEL: define i32 @test_umin_missing_nuw(
+; CHECK-SAME: i32 [[ARG0:%.*]], i32 [[ARG1:%.*]]) {
+; CHECK-NEXT:    [[V0:%.*]] = tail call i32 @llvm.umin.i32(i32 [[ARG0]], i32 [[ARG1]])
+; CHECK-NEXT:    [[V1:%.*]] = add i32 [[ARG0]], 1
+; CHECK-NEXT:    [[V2:%.*]] = tail call i32 @llvm.umin.i32(i32 [[V1]], i32 [[ARG1]])
+; CHECK-NEXT:    [[V3:%.*]] = sub i32 [[V2]], [[V0]]
+; CHECK-NEXT:    ret i32 [[V3]]
+;
+  %v0 = tail call i32 @llvm.umin.i32(i32 %arg0, i32 %arg1)
+  %v1 = add i32 %arg0, 1
+  %v2 = tail call i32 @llvm.umin.i32(i32 %v1, i32 %arg1)
+  %v3 = sub i32 %v2, %v0
+  ret i32 %v3
+}