[InstSimplify] Drop leftover "division-by-zero guard" around `@llvm.umul.with.overflow` overflow bit

Summary:
Now that with D65143/D65144 we've produce `@llvm.umul.with.overflow`,
and with D65147 we've flattened the CFG, we now can see that
the guard may have been there to prevent division by zero is redundant.
We can simply drop it:
```
----------------------------------------
Name: no overflow and not zero
  %iszero = icmp ne i4 %y, 0
  %umul = umul_overflow i4 %x, %y
  %umul.ov = extractvalue {i4, i1} %umul, 1
  %retval.0 = and i1 %iszero, %umul.ov
  ret i1 %retval.0
=>
  %iszero = icmp ne i4 %y, 0
  %umul = umul_overflow i4 %x, %y
  %umul.ov = extractvalue {i4, i1} %umul, 1
  %retval.0 = and i1 %iszero, %umul.ov
  ret %umul.ov

Done: 1
Optimization is correct!
```

Reviewers: nikic, spatel, xbolva00

Reviewed By: spatel

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D65150

llvm-svn: 370350

4 files changed, 52 insertions, 24 deletions

diff --git a/llvm/lib/Analysis/InstructionSimplify.cpp b/llvm/lib/Analysis/InstructionSimplify.cpp
index 85002aafa85..d320333aaa0 100644
--- a/llvm/lib/Analysis/InstructionSimplify.cpp
+++ b/llvm/lib/Analysis/InstructionSimplify.cpp
@@ -1759,6 +1759,38 @@ static Value *simplifyAndOrOfCmps(const SimplifyQuery &Q,
   return nullptr;
 }
 
+/// The @llvm.[us]mul.with.overflow intrinsic could have been folded from some
+/// other form of check, e.g. one that was using division; it may have been
+/// guarded against division-by-zero. We can drop that check now.
+/// Look for:
+///   %Op0 = icmp ne i4 %X, 0
+///   %Agg = tail call { i4, i1 } @llvm.[us]mul.with.overflow.i4(i4 %X, i4 %???)
+///   %Op1 = extractvalue { i4, i1 } %Agg, 1
+///   %??? = and i1 %Op0, %Op1
+/// We can just return  %Op1
+static Value *omitCheckForZeroBeforeMulWithOverflow(Value *Op0, Value *Op1) {
+  ICmpInst::Predicate Pred;
+  Value *X;
+  if (!match(Op0, m_ICmp(Pred, m_Value(X), m_Zero())) ||
+      Pred != ICmpInst::Predicate::ICMP_NE)
+    return nullptr;
+  auto *Extract = dyn_cast<ExtractValueInst>(Op1);
+  // We should only be extracting the overflow bit.
+  if (!Extract || !Extract->getIndices().equals(1))
+    return nullptr;
+  Value *Agg = Extract->getAggregateOperand();
+  // This should be a multiplication-with-overflow intrinsic.
+  if (!match(Agg, m_CombineOr(m_Intrinsic<Intrinsic::umul_with_overflow>(),
+                              m_Intrinsic<Intrinsic::smul_with_overflow>())))
+    return nullptr;
+  // One of its multipliers should be the value we checked for zero before.
+  if (!match(Agg, m_CombineOr(m_Argument<0>(m_Specific(X)),
+                              m_Argument<1>(m_Specific(X)))))
+    return nullptr;
+  // Can omit 'and', and just return the overflow bit.
+  return Op1;
+}
+
 /// Given operands for an And, see if we can fold the result.
 /// If not, this returns null.
 static Value *SimplifyAndInst(Value *Op0, Value *Op1, const SimplifyQuery &Q,
@@ -1813,6 +1845,14 @@ static Value *SimplifyAndInst(Value *Op0, Value *Op1, const SimplifyQuery &Q,
       return Op0;
   }
 
+  // If we have a multiplication overflow check that is being 'and'ed with a
+  // check that one of the multipliers is not zero, we can omit the 'and', and
+  // only keep the overflow check.
+  if (Value *V = omitCheckForZeroBeforeMulWithOverflow(Op0, Op1))
+    return V;
+  if (Value *V = omitCheckForZeroBeforeMulWithOverflow(Op1, Op0))
+    return V;
+
   // A & (-A) = A if A is a power of two or zero.
   if (match(Op0, m_Neg(m_Specific(Op1))) ||
       match(Op1, m_Neg(m_Specific(Op0)))) {
diff --git a/llvm/test/Transforms/InstSimplify/div-by-0-guard-before-smul_ov.ll b/llvm/test/Transforms/InstSimplify/div-by-0-guard-before-smul_ov.ll
index 440256d1d8a..004c365608f 100644
--- a/llvm/test/Transforms/InstSimplify/div-by-0-guard-before-smul_ov.ll
+++ b/llvm/test/Transforms/InstSimplify/div-by-0-guard-before-smul_ov.ll
@@ -5,11 +5,9 @@ declare { i4, i1 } @llvm.smul.with.overflow.i4(i4, i4) #1
 
 define i1 @t0_smul(i4 %size, i4 %nmemb) {
 ; CHECK-LABEL: @t0_smul(
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i4 [[SIZE:%.*]], 0
-; CHECK-NEXT:    [[SMUL:%.*]] = tail call { i4, i1 } @llvm.smul.with.overflow.i4(i4 [[SIZE]], i4 [[NMEMB:%.*]])
+; CHECK-NEXT:    [[SMUL:%.*]] = tail call { i4, i1 } @llvm.smul.with.overflow.i4(i4 [[SIZE:%.*]], i4 [[NMEMB:%.*]])
 ; CHECK-NEXT:    [[SMUL_OV:%.*]] = extractvalue { i4, i1 } [[SMUL]], 1
-; CHECK-NEXT:    [[AND:%.*]] = and i1 [[SMUL_OV]], [[CMP]]
-; CHECK-NEXT:    ret i1 [[AND]]
+; CHECK-NEXT:    ret i1 [[SMUL_OV]]
 ;
   %cmp = icmp ne i4 %size, 0
   %smul = tail call { i4, i1 } @llvm.smul.with.overflow.i4(i4 %size, i4 %nmemb)
@@ -20,11 +18,9 @@ define i1 @t0_smul(i4 %size, i4 %nmemb) {
 
 define i1 @t1_commutative(i4 %size, i4 %nmemb) {
 ; CHECK-LABEL: @t1_commutative(
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i4 [[SIZE:%.*]], 0
-; CHECK-NEXT:    [[SMUL:%.*]] = tail call { i4, i1 } @llvm.smul.with.overflow.i4(i4 [[SIZE]], i4 [[NMEMB:%.*]])
+; CHECK-NEXT:    [[SMUL:%.*]] = tail call { i4, i1 } @llvm.smul.with.overflow.i4(i4 [[SIZE:%.*]], i4 [[NMEMB:%.*]])
 ; CHECK-NEXT:    [[SMUL_OV:%.*]] = extractvalue { i4, i1 } [[SMUL]], 1
-; CHECK-NEXT:    [[AND:%.*]] = and i1 [[CMP]], [[SMUL_OV]]
-; CHECK-NEXT:    ret i1 [[AND]]
+; CHECK-NEXT:    ret i1 [[SMUL_OV]]
 ;
   %cmp = icmp ne i4 %size, 0
   %smul = tail call { i4, i1 } @llvm.smul.with.overflow.i4(i4 %size, i4 %nmemb)
diff --git a/llvm/test/Transforms/InstSimplify/div-by-0-guard-before-umul_ov.ll b/llvm/test/Transforms/InstSimplify/div-by-0-guard-before-umul_ov.ll
index 63cf1015ffa..337de40f5d5 100644
--- a/llvm/test/Transforms/InstSimplify/div-by-0-guard-before-umul_ov.ll
+++ b/llvm/test/Transforms/InstSimplify/div-by-0-guard-before-umul_ov.ll
@@ -5,11 +5,9 @@ declare { i4, i1 } @llvm.umul.with.overflow.i4(i4, i4) #1
 
 define i1 @t0_umul(i4 %size, i4 %nmemb) {
 ; CHECK-LABEL: @t0_umul(
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i4 [[SIZE:%.*]], 0
-; CHECK-NEXT:    [[UMUL:%.*]] = tail call { i4, i1 } @llvm.umul.with.overflow.i4(i4 [[SIZE]], i4 [[NMEMB:%.*]])
+; CHECK-NEXT:    [[UMUL:%.*]] = tail call { i4, i1 } @llvm.umul.with.overflow.i4(i4 [[SIZE:%.*]], i4 [[NMEMB:%.*]])
 ; CHECK-NEXT:    [[UMUL_OV:%.*]] = extractvalue { i4, i1 } [[UMUL]], 1
-; CHECK-NEXT:    [[AND:%.*]] = and i1 [[UMUL_OV]], [[CMP]]
-; CHECK-NEXT:    ret i1 [[AND]]
+; CHECK-NEXT:    ret i1 [[UMUL_OV]]
 ;
   %cmp = icmp ne i4 %size, 0
   %umul = tail call { i4, i1 } @llvm.umul.with.overflow.i4(i4 %size, i4 %nmemb)
@@ -20,11 +18,9 @@ define i1 @t0_umul(i4 %size, i4 %nmemb) {
 
 define i1 @t1_commutative(i4 %size, i4 %nmemb) {
 ; CHECK-LABEL: @t1_commutative(
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i4 [[SIZE:%.*]], 0
-; CHECK-NEXT:    [[UMUL:%.*]] = tail call { i4, i1 } @llvm.umul.with.overflow.i4(i4 [[SIZE]], i4 [[NMEMB:%.*]])
+; CHECK-NEXT:    [[UMUL:%.*]] = tail call { i4, i1 } @llvm.umul.with.overflow.i4(i4 [[SIZE:%.*]], i4 [[NMEMB:%.*]])
 ; CHECK-NEXT:    [[UMUL_OV:%.*]] = extractvalue { i4, i1 } [[UMUL]], 1
-; CHECK-NEXT:    [[AND:%.*]] = and i1 [[CMP]], [[UMUL_OV]]
-; CHECK-NEXT:    ret i1 [[AND]]
+; CHECK-NEXT:    ret i1 [[UMUL_OV]]
 ;
   %cmp = icmp ne i4 %size, 0
   %umul = tail call { i4, i1 } @llvm.umul.with.overflow.i4(i4 %size, i4 %nmemb)
diff --git a/llvm/test/Transforms/PhaseOrdering/unsigned-multiply-overflow-check.ll b/llvm/test/Transforms/PhaseOrdering/unsigned-multiply-overflow-check.ll
index 34dbfc4f186..cbebaa289c3 100644
--- a/llvm/test/Transforms/PhaseOrdering/unsigned-multiply-overflow-check.ll
+++ b/llvm/test/Transforms/PhaseOrdering/unsigned-multiply-overflow-check.ll
@@ -52,11 +52,9 @@ define i1 @will_not_overflow(i64 %arg, i64 %arg1) {
 ;
 ; INSTCOMBINESIMPLIFYCFGINSTCOMBINE-LABEL: @will_not_overflow(
 ; INSTCOMBINESIMPLIFYCFGINSTCOMBINE-NEXT:  bb:
-; INSTCOMBINESIMPLIFYCFGINSTCOMBINE-NEXT:    [[T0:%.*]] = icmp ne i64 [[ARG:%.*]], 0
-; INSTCOMBINESIMPLIFYCFGINSTCOMBINE-NEXT:    [[UMUL:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 [[ARG]], i64 [[ARG1:%.*]])
+; INSTCOMBINESIMPLIFYCFGINSTCOMBINE-NEXT:    [[UMUL:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 [[ARG:%.*]], i64 [[ARG1:%.*]])
 ; INSTCOMBINESIMPLIFYCFGINSTCOMBINE-NEXT:    [[UMUL_OV:%.*]] = extractvalue { i64, i1 } [[UMUL]], 1
-; INSTCOMBINESIMPLIFYCFGINSTCOMBINE-NEXT:    [[T6:%.*]] = and i1 [[UMUL_OV]], [[T0]]
-; INSTCOMBINESIMPLIFYCFGINSTCOMBINE-NEXT:    ret i1 [[T6]]
+; INSTCOMBINESIMPLIFYCFGINSTCOMBINE-NEXT:    ret i1 [[UMUL_OV]]
 ;
 ; INSTCOMBINESIMPLIFYCFGCOSTLYONLY-LABEL: @will_not_overflow(
 ; INSTCOMBINESIMPLIFYCFGCOSTLYONLY-NEXT:  bb:
@@ -68,11 +66,9 @@ define i1 @will_not_overflow(i64 %arg, i64 %arg1) {
 ;
 ; INSTCOMBINESIMPLIFYCFGCOSTLYINSTCOMBINE-LABEL: @will_not_overflow(
 ; INSTCOMBINESIMPLIFYCFGCOSTLYINSTCOMBINE-NEXT:  bb:
-; INSTCOMBINESIMPLIFYCFGCOSTLYINSTCOMBINE-NEXT:    [[T0:%.*]] = icmp ne i64 [[ARG:%.*]], 0
-; INSTCOMBINESIMPLIFYCFGCOSTLYINSTCOMBINE-NEXT:    [[UMUL:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 [[ARG]], i64 [[ARG1:%.*]])
+; INSTCOMBINESIMPLIFYCFGCOSTLYINSTCOMBINE-NEXT:    [[UMUL:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 [[ARG:%.*]], i64 [[ARG1:%.*]])
 ; INSTCOMBINESIMPLIFYCFGCOSTLYINSTCOMBINE-NEXT:    [[UMUL_OV:%.*]] = extractvalue { i64, i1 } [[UMUL]], 1
-; INSTCOMBINESIMPLIFYCFGCOSTLYINSTCOMBINE-NEXT:    [[T6:%.*]] = and i1 [[UMUL_OV]], [[T0]]
-; INSTCOMBINESIMPLIFYCFGCOSTLYINSTCOMBINE-NEXT:    ret i1 [[T6]]
+; INSTCOMBINESIMPLIFYCFGCOSTLYINSTCOMBINE-NEXT:    ret i1 [[UMUL_OV]]
 ;
 bb:
   %t0 = icmp eq i64 %arg, 0