[InstCombine] Simplify with.overflow intrinsics with assumption infor…

…mation
llvm · Mar 5, 2024 · fc350f0 · fc350f0
1 parent 96ab2a0
commit fc350f0
Show file tree

Hide file tree

Showing 2 changed files with 31 additions and 12 deletions.
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -818,6 +818,33 @@ InstCombinerImpl::foldIntrinsicWithOverflowCommon(IntrinsicInst *II) {
   if (OptimizeOverflowCheck(WO->getBinaryOp(), WO->isSigned(), WO->getLHS(),
                             WO->getRHS(), *WO, OperationResult, OverflowResult))
     return createOverflowTuple(WO, OperationResult, OverflowResult);
+
+  // See whether we can optimize the overflow check with assumption information.
+  for (User *U : WO->users()) {
+    if (!match(U, m_ExtractValue<1>(m_Value())))
+      continue;
+
+    for (auto &AssumeVH : AC.assumptionsFor(U)) {
+      if (!AssumeVH)
+        continue;
+      CallInst *I = cast<CallInst>(AssumeVH);
+      if (!match(I->getArgOperand(0), m_Not(m_Specific(U))))
+        continue;
+      if (!isValidAssumeForContext(I, II, &DT))
+        continue;
+      Value *Result =
+          Builder.CreateBinOp(WO->getBinaryOp(), WO->getLHS(), WO->getRHS());
+      if (auto *Inst = dyn_cast<Instruction>(Result)) {
+        if (WO->isSigned())
+          Inst->setHasNoSignedWrap();
+        else
+          Inst->setHasNoUnsignedWrap();
+      }
+      return createOverflowTuple(WO, Result,
+                                 ConstantInt::getFalse(U->getType()));
+    }
+  }
+
   return nullptr;
 }
 

diff --git a/llvm/test/Transforms/InstCombine/overflow.ll b/llvm/test/Transforms/InstCombine/overflow.ll
@@ -173,12 +173,8 @@ if.end:
 
 define i32 @uadd_no_overflow(i32 %a, i32 %b) {
 ; CHECK-LABEL: @uadd_no_overflow(
-; CHECK-NEXT:    [[VAL:%.*]] = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 [[A:%.*]], i32 [[B:%.*]])
-; CHECK-NEXT:    [[OV:%.*]] = extractvalue { i32, i1 } [[VAL]], 1
-; CHECK-NEXT:    [[NOWRAP:%.*]] = xor i1 [[OV]], true
-; CHECK-NEXT:    tail call void @llvm.assume(i1 [[NOWRAP]])
-; CHECK-NEXT:    [[RES:%.*]] = extractvalue { i32, i1 } [[VAL]], 0
-; CHECK-NEXT:    ret i32 [[RES]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add nuw i32 [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    ret i32 [[TMP1]]
 ;
   %val = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
   %ov = extractvalue { i32, i1 } %val, 1
@@ -190,12 +186,8 @@ define i32 @uadd_no_overflow(i32 %a, i32 %b) {
 
 define i32 @smul_no_overflow(i32 %a, i32 %b) {
 ; CHECK-LABEL: @smul_no_overflow(
-; CHECK-NEXT:    [[VAL:%.*]] = tail call { i32, i1 } @llvm.smul.with.overflow.i32(i32 [[A:%.*]], i32 [[B:%.*]])
-; CHECK-NEXT:    [[OV:%.*]] = extractvalue { i32, i1 } [[VAL]], 1
-; CHECK-NEXT:    [[NOWRAP:%.*]] = xor i1 [[OV]], true
-; CHECK-NEXT:    tail call void @llvm.assume(i1 [[NOWRAP]])
-; CHECK-NEXT:    [[RES:%.*]] = extractvalue { i32, i1 } [[VAL]], 0
-; CHECK-NEXT:    ret i32 [[RES]]
+; CHECK-NEXT:    [[TMP1:%.*]] = mul nsw i32 [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    ret i32 [[TMP1]]
 ;
   %val = tail call { i32, i1 } @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
   %ov = extractvalue { i32, i1 } %val, 1