[CVP] Simplify umulo and smulo that cannot overflow

If a umul.with.overflow or smul.with.overflow operation cannot
overflow, simplify it to a simple mul nuw / mul nsw. After the
refactoring in D60668 this is just a matter of removing an
explicit check against multiplications.

Differential Revision: https://reviews.llvm.org/D60791

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@358521 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Scalar/CorrelatedValuePropagation.cpp b/lib/Transforms/Scalar/CorrelatedValuePropagation.cpp
index bc4daf1c9c1186c36c2952439e9f0cfbe3de164e..b650971624a75146bcedd0f755e9bab64910f7ae 100644 (file)
--- a/lib/Transforms/Scalar/CorrelatedValuePropagation.cpp
+++ b/lib/Transforms/Scalar/CorrelatedValuePropagation.cpp
@@ -400,15 +400,10 @@ static bool processSwitch(SwitchInst *SI, LazyValueInfo *LVI,
 
 // See if we can prove that the given overflow intrinsic will not overflow.
 static bool willNotOverflow(WithOverflowInst *WO, LazyValueInfo *LVI) {
-  // TODO: Also support multiplication.
-  Instruction::BinaryOps BinOp = WO->getBinaryOp();
-  if (BinOp == Instruction::Mul)
-    return false;
-
   Value *RHS = WO->getRHS();
   ConstantRange RRange = LVI->getConstantRange(RHS, WO->getParent(), WO);
   ConstantRange NWRegion = ConstantRange::makeGuaranteedNoWrapRegion(
-      BinOp, RRange, WO->getNoWrapKind());
+      WO->getBinaryOp(), RRange, WO->getNoWrapKind());
   // As an optimization, do not compute LRange if we do not need it.
   if (NWRegion.isEmptySet())
     return false;

diff --git a/test/Transforms/CorrelatedValuePropagation/overflows.ll b/test/Transforms/CorrelatedValuePropagation/overflows.ll
index ed020124279eb452e4b0cb7cee8c455c518336cf..db758b8459b7fca1a3568efc097665e453dbf38d 100644 (file)
--- a/test/Transforms/CorrelatedValuePropagation/overflows.ll
+++ b/test/Transforms/CorrelatedValuePropagation/overflows.ll
@@ -507,9 +507,11 @@ define i32 @unsigned_mul(i32 %x) {
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp ugt i32 [[X:%.*]], 10000
 ; CHECK-NEXT:    br i1 [[CMP]], label [[COND_END:%.*]], label [[COND_FALSE:%.*]]
 ; CHECK:       cond.false:
-; CHECK-NEXT:    [[MULO:%.*]] = tail call { i32, i1 } @llvm.umul.with.overflow.i32(i32 [[X]], i32 100)
-; CHECK-NEXT:    [[RES:%.*]] = extractvalue { i32, i1 } [[MULO]], 0
-; CHECK-NEXT:    [[OV:%.*]] = extractvalue { i32, i1 } [[MULO]], 1
+; CHECK-NEXT:    [[MULO1:%.*]] = mul nuw i32 [[X]], 100
+; CHECK-NEXT:    [[TMP0:%.*]] = insertvalue { i32, i1 } undef, i32 [[MULO1]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = insertvalue { i32, i1 } [[TMP0]], i1 false, 1
+; CHECK-NEXT:    [[RES:%.*]] = extractvalue { i32, i1 } [[TMP1]], 0
+; CHECK-NEXT:    [[OV:%.*]] = extractvalue { i32, i1 } [[TMP1]], 1
 ; CHECK-NEXT:    br i1 [[OV]], label [[TRAP:%.*]], label [[COND_END]]
 ; CHECK:       trap:
 ; CHECK-NEXT:    tail call void @llvm.trap()
@@ -545,9 +547,11 @@ define i32 @signed_mul(i32 %x) {
 ; CHECK-NEXT:    [[CMP3:%.*]] = or i1 [[CMP1]], [[CMP2]]
 ; CHECK-NEXT:    br i1 [[CMP3]], label [[COND_END:%.*]], label [[COND_FALSE:%.*]]
 ; CHECK:       cond.false:
-; CHECK-NEXT:    [[MULO:%.*]] = tail call { i32, i1 } @llvm.smul.with.overflow.i32(i32 [[X]], i32 100)
-; CHECK-NEXT:    [[RES:%.*]] = extractvalue { i32, i1 } [[MULO]], 0
-; CHECK-NEXT:    [[OV:%.*]] = extractvalue { i32, i1 } [[MULO]], 1
+; CHECK-NEXT:    [[MULO1:%.*]] = mul nsw i32 [[X]], 100
+; CHECK-NEXT:    [[TMP0:%.*]] = insertvalue { i32, i1 } undef, i32 [[MULO1]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = insertvalue { i32, i1 } [[TMP0]], i1 false, 1
+; CHECK-NEXT:    [[RES:%.*]] = extractvalue { i32, i1 } [[TMP1]], 0
+; CHECK-NEXT:    [[OV:%.*]] = extractvalue { i32, i1 } [[TMP1]], 1
 ; CHECK-NEXT:    br i1 [[OV]], label [[TRAP:%.*]], label [[COND_END]]
 ; CHECK:       trap:
 ; CHECK-NEXT:    tail call void @llvm.trap()