[InstCombine] Fold add nsw + sadd.with.overflow

Fold `add nsw` and `sadd.with.overflow` with constants if the addition
does not overflow.

Part of https://bugs.llvm.org/show_bug.cgi?id=38146.

Patch by Dan Robertson.

Differential Revision: https://reviews.llvm.org/D58881

llvm-svn: 355530

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 56d5c89..02cf906 100644 (file)
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -1814,6 +1814,19 @@ static Instruction *canonicalizeConstantArg0ToArg1(CallInst &Call) {
   return nullptr;
 }
 
+Instruction *InstCombiner::foldIntrinsicWithOverflowCommon(IntrinsicInst *II) {
+  OverflowCheckFlavor OCF =
+      IntrinsicIDToOverflowCheckFlavor(II->getIntrinsicID());
+  assert(OCF != OCF_INVALID && "unexpected!");
+
+  Value *OperationResult = nullptr;
+  Constant *OverflowResult = nullptr;
+  if (OptimizeOverflowCheck(OCF, II->getArgOperand(0), II->getArgOperand(1),
+                            *II, OperationResult, OverflowResult))
+    return CreateOverflowTuple(II, OperationResult, OverflowResult);
+  return nullptr;
+}
+
 /// CallInst simplification. This mostly only handles folding of intrinsic
 /// instructions. For normal calls, it allows visitCallBase to do the heavy
 /// lifting.
@@ -2016,8 +2029,32 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
       return &CI;
     break;
   }
+  case Intrinsic::sadd_with_overflow: {
+    if (Instruction *I = canonicalizeConstantArg0ToArg1(CI))
+      return I;
+    if (Instruction *I = foldIntrinsicWithOverflowCommon(II))
+      return I;
+
+    // Given 2 constant operands whose sum does not overflow:
+    // saddo (X +nsw C0), C1 -> saddo X, C0 + C1
+    Value *X;
+    const APInt *C0, *C1;
+    Value *Arg0 = II->getArgOperand(0);
+    Value *Arg1 = II->getArgOperand(1);
+    if (match(Arg0, m_NSWAdd(m_Value(X), m_APInt(C0))) &&
+        match(Arg1, m_APInt(C1))) {
+      bool Overflow;
+      APInt NewC = C1->sadd_ov(*C0, Overflow);
+      if (!Overflow)
+        return replaceInstUsesWith(
+            *II, Builder.CreateBinaryIntrinsic(
+                     Intrinsic::sadd_with_overflow, X,
+                     ConstantInt::get(Arg1->getType(), NewC)));
+    }
+
+    break;
+  }
   case Intrinsic::uadd_with_overflow:
-  case Intrinsic::sadd_with_overflow:
   case Intrinsic::umul_with_overflow:
   case Intrinsic::smul_with_overflow:
     if (Instruction *I = canonicalizeConstantArg0ToArg1(CI))
@@ -2026,15 +2063,8 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
 
   case Intrinsic::usub_with_overflow:
   case Intrinsic::ssub_with_overflow: {
-    OverflowCheckFlavor OCF =
-        IntrinsicIDToOverflowCheckFlavor(II->getIntrinsicID());
-    assert(OCF != OCF_INVALID && "unexpected!");
-
-    Value *OperationResult = nullptr;
-    Constant *OverflowResult = nullptr;
-    if (OptimizeOverflowCheck(OCF, II->getArgOperand(0), II->getArgOperand(1),
-                              *II, OperationResult, OverflowResult))
-      return CreateOverflowTuple(II, OperationResult, OverflowResult);
+    if (Instruction *I = foldIntrinsicWithOverflowCommon(II))
+      return I;
 
     break;
   }

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineInternal.h b/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
index 5b0c7fc..e4e6228 100644 (file)
--- a/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
+++ b/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
@@ -592,6 +592,8 @@ private:
   Value *matchSelectFromAndOr(Value *A, Value *B, Value *C, Value *D);
   Value *getSelectCondition(Value *A, Value *B);
 
+  Instruction *foldIntrinsicWithOverflowCommon(IntrinsicInst *II);
+
 public:
   /// Inserts an instruction \p New before instruction \p Old
   ///

diff --git a/llvm/test/Transforms/InstCombine/sadd-with-overflow.ll b/llvm/test/Transforms/InstCombine/sadd-with-overflow.ll
index ecbe647..c2c5543 100644 (file)
--- a/llvm/test/Transforms/InstCombine/sadd-with-overflow.ll
+++ b/llvm/test/Transforms/InstCombine/sadd-with-overflow.ll
@@ -9,9 +9,8 @@ declare { i8, i1 } @llvm.sadd.with.overflow.i8(i8, i8)
 
 define { i32, i1 } @simple_fold(i32) {
 ; CHECK-LABEL: @simple_fold(
-; CHECK-NEXT:    [[TMP2:%.*]] = add nsw i32 [[TMP0:%.*]], 7
-; CHECK-NEXT:    [[TMP3:%.*]] = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 [[TMP2]], i32 13)
-; CHECK-NEXT:    ret { i32, i1 } [[TMP3]]
+; CHECK-NEXT:    [[TMP2:%.*]] = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 [[TMP0:%.*]], i32 20)
+; CHECK-NEXT:    ret { i32, i1 } [[TMP2]]
 ;
   %2 = add nsw i32 %0, 7
   %3 = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 %2, i32 13)
@@ -20,31 +19,39 @@ define { i32, i1 } @simple_fold(i32) {
 
 define { i32, i1 } @fold_mixed_signs(i32) {
 ; CHECK-LABEL: @fold_mixed_signs(
-; CHECK-NEXT:    [[TMP2:%.*]] = add nsw i32 [[TMP0:%.*]], 13
-; CHECK-NEXT:    [[TMP3:%.*]] = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 [[TMP2]], i32 -7)
-; CHECK-NEXT:    ret { i32, i1 } [[TMP3]]
+; CHECK-NEXT:    [[TMP2:%.*]] = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 [[TMP0:%.*]], i32 6)
+; CHECK-NEXT:    ret { i32, i1 } [[TMP2]]
 ;
   %2 = add nsw i32 %0, 13
   %3 = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 %2, i32 -7)
   ret { i32, i1 } %3
 }
 
+define { i8, i1 } @fold_on_constant_add_no_overflow(i8) {
+; CHECK-LABEL: @fold_on_constant_add_no_overflow(
+; CHECK-NEXT:    [[TMP2:%.*]] = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 [[TMP0:%.*]], i8 127)
+; CHECK-NEXT:    ret { i8, i1 } [[TMP2]]
+;
+  %2 = add nsw i8 %0, 100
+  %3 = tail call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 %2, i8 27)
+  ret { i8, i1 } %3
+}
+
 define { i8, i1 } @no_fold_on_constant_add_overflow(i8) {
 ; CHECK-LABEL: @no_fold_on_constant_add_overflow(
-; CHECK-NEXT:    [[TMP2:%.*]] = add nsw i8 [[TMP0:%.*]], 127
-; CHECK-NEXT:    [[TMP3:%.*]] = tail call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 [[TMP2]], i8 127)
+; CHECK-NEXT:    [[TMP2:%.*]] = add nsw i8 [[TMP0:%.*]], 100
+; CHECK-NEXT:    [[TMP3:%.*]] = tail call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 [[TMP2]], i8 28)
 ; CHECK-NEXT:    ret { i8, i1 } [[TMP3]]
 ;
-  %2 = add nsw i8 %0, 127
-  %3 = tail call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 %2, i8 127)
+  %2 = add nsw i8 %0, 100
+  %3 = tail call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 %2, i8 28)
   ret { i8, i1 } %3
 }
 
 define { <2 x i32>, <2 x i1> } @fold_simple_splat_constant(<2 x i32>) {
 ; CHECK-LABEL: @fold_simple_splat_constant(
-; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <2 x i32> [[TMP0:%.*]], <i32 12, i32 12>
-; CHECK-NEXT:    [[TMP3:%.*]] = tail call { <2 x i32>, <2 x i1> } @llvm.sadd.with.overflow.v2i32(<2 x i32> [[TMP2]], <2 x i32> <i32 30, i32 30>)
-; CHECK-NEXT:    ret { <2 x i32>, <2 x i1> } [[TMP3]]
+; CHECK-NEXT:    [[TMP2:%.*]] = call { <2 x i32>, <2 x i1> } @llvm.sadd.with.overflow.v2i32(<2 x i32> [[TMP0:%.*]], <2 x i32> <i32 42, i32 42>)
+; CHECK-NEXT:    ret { <2 x i32>, <2 x i1> } [[TMP2]]
 ;
   %2 = add nsw <2 x i32> %0, <i32 12, i32 12>
   %3 = tail call { <2 x i32>, <2 x i1> } @llvm.sadd.with.overflow.v2i32(<2 x i32> %2, <2 x i32> <i32 30, i32 30>)
@@ -75,9 +82,8 @@ define { <2 x i32>, <2 x i1> } @no_fold_splat_not_constant(<2 x i32>, <2 x i32>)
 
 define { i32, i1 } @fold_nuwnsw(i32) {
 ; CHECK-LABEL: @fold_nuwnsw(
-; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i32 [[TMP0:%.*]], 12
-; CHECK-NEXT:    [[TMP3:%.*]] = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 [[TMP2]], i32 30)
-; CHECK-NEXT:    ret { i32, i1 } [[TMP3]]
+; CHECK-NEXT:    [[TMP2:%.*]] = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 [[TMP0:%.*]], i32 42)
+; CHECK-NEXT:    ret { i32, i1 } [[TMP2]]
 ;
   %2 = add nuw nsw i32 %0, 12
   %3 = tail call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 %2, i32 30)