[PatternMatch] Handle undef vectors consistently

This patch fixes the issue noticed in D54532. 
The problem is that cst_pred_ty-based matchers like m_Zero() currently do not match 
scalar undefs (as expected), but *do* match vector undefs. This may lead to optimization 
inconsistencies in rare cases.

There is only one existing test for which output changes, reverting the change from D53205. 
The reason here is that vector fsub undef, %x is no longer matched as an m_FNeg(). While I 
think that the new output is technically worse than the previous one, it is consistent with 
scalar, and I don't think it's really important either way (generally that undef should have 
been folded away prior to reassociation.)

I've also added another test case for this issue based on InstructionSimplify. It took some 
effort to find that one, as in most cases undef folds are either checked first -- and in the 
cases where they aren't it usually happens to not make a difference in the end. This is the 
only case I was able to come up with. Prior to this patch the test case simplified to undef 
in the scalar case, but zeroinitializer in the vector case.

Patch by: @nikic (Nikita Popov)

Differential Revision: https://reviews.llvm.org/D54631

llvm-svn: 347318

4 files changed, 65 insertions, 5 deletions

diff --git a/llvm/include/llvm/IR/PatternMatch.h b/llvm/include/llvm/IR/PatternMatch.h
index dd30072ce57..e1e7c7268b5 100644
--- a/llvm/include/llvm/IR/PatternMatch.h
+++ b/llvm/include/llvm/IR/PatternMatch.h
@@ -215,6 +215,7 @@ template <typename Predicate> struct cst_pred_ty : public Predicate {
         // Non-splat vector constant: check each element for a match.
         unsigned NumElts = V->getType()->getVectorNumElements();
         assert(NumElts != 0 && "Constant vector with no elements?");
+        bool HasNonUndefElements = false;
         for (unsigned i = 0; i != NumElts; ++i) {
           Constant *Elt = C->getAggregateElement(i);
           if (!Elt)
@@ -224,8 +225,9 @@ template <typename Predicate> struct cst_pred_ty : public Predicate {
           auto *CI = dyn_cast<ConstantInt>(Elt);
           if (!CI || !this->isValue(CI->getValue()))
             return false;
+          HasNonUndefElements = true;
         }
-        return true;
+        return HasNonUndefElements;
       }
     }
     return false;
@@ -272,6 +274,7 @@ template <typename Predicate> struct cstfp_pred_ty : public Predicate {
         // Non-splat vector constant: check each element for a match.
         unsigned NumElts = V->getType()->getVectorNumElements();
         assert(NumElts != 0 && "Constant vector with no elements?");
+        bool HasNonUndefElements = false;
         for (unsigned i = 0; i != NumElts; ++i) {
           Constant *Elt = C->getAggregateElement(i);
           if (!Elt)
@@ -281,8 +284,9 @@ template <typename Predicate> struct cstfp_pred_ty : public Predicate {
           auto *CF = dyn_cast<ConstantFP>(Elt);
           if (!CF || !this->isValue(CF->getValueAPF()))
             return false;
+          HasNonUndefElements = true;
         }
-        return true;
+        return HasNonUndefElements;
       }
     }
     return false;
diff --git a/llvm/test/Transforms/InstSimplify/shr-scalar-vector-consistency.ll b/llvm/test/Transforms/InstSimplify/shr-scalar-vector-consistency.ll
index f1bba37ff99..90725a153a2 100644
--- a/llvm/test/Transforms/InstSimplify/shr-scalar-vector-consistency.ll
+++ b/llvm/test/Transforms/InstSimplify/shr-scalar-vector-consistency.ll
@@ -16,7 +16,7 @@ define i32 @test_scalar(i32 %a, i1 %b) {
 
 define <2 x i32> @test_vector(<2 x i32> %a, <2 x i1> %b) {
 ; CHECK-LABEL: @test_vector(
-; CHECK-NEXT:    ret <2 x i32> zeroinitializer
+; CHECK-NEXT:    ret <2 x i32> undef
 ;
   %c = sext <2 x i1> %b to <2 x i32>
   %d = ashr <2 x i32> undef, %c
diff --git a/llvm/test/Transforms/Reassociate/fp-expr.ll b/llvm/test/Transforms/Reassociate/fp-expr.ll
index dcbf835ba54..e616c52f28e 100644
--- a/llvm/test/Transforms/Reassociate/fp-expr.ll
+++ b/llvm/test/Transforms/Reassociate/fp-expr.ll
@@ -4,8 +4,8 @@
 define void @test1() {
 ; CHECK-LABEL: @test1(
 ; CHECK-NEXT:    [[T1:%.*]] = tail call <4 x float> @blam()
-; CHECK-NEXT:    [[T23:%.*]] = fsub fast <4 x float> undef, [[T1]]
-; CHECK-NEXT:    [[T24:%.*]] = fadd fast <4 x float> [[T23]], undef
+; CHECK-NEXT:    [[T1_NEG:%.*]] = fsub fast <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, [[T1]]
+; CHECK-NEXT:    [[T24:%.*]] = fadd fast <4 x float> [[T1_NEG]], undef
 ; CHECK-NEXT:    tail call void @wombat(<4 x float> [[T24]])
 ; CHECK-NEXT:    ret void
 ;
diff --git a/llvm/unittests/IR/PatternMatch.cpp b/llvm/unittests/IR/PatternMatch.cpp
index 6b5686d53c6..976e42d0dbb 100644
--- a/llvm/unittests/IR/PatternMatch.cpp
+++ b/llvm/unittests/IR/PatternMatch.cpp
@@ -534,6 +534,62 @@ TEST_F(PatternMatchTest, VectorOps) {
   EXPECT_TRUE(A == Val);
 }
 
+TEST_F(PatternMatchTest, VectorUndefInt) {
+  Type *ScalarTy = IRB.getInt8Ty();
+  Type *VectorTy = VectorType::get(ScalarTy, 4);
+  Constant *ScalarUndef = UndefValue::get(ScalarTy);
+  Constant *VectorUndef = UndefValue::get(VectorTy);
+  Constant *ScalarZero = Constant::getNullValue(ScalarTy);
+  Constant *VectorZero = Constant::getNullValue(VectorTy);
+
+  SmallVector<Constant *, 4> Elems;
+  Elems.push_back(ScalarUndef);
+  Elems.push_back(ScalarZero);
+  Elems.push_back(ScalarUndef);
+  Elems.push_back(ScalarZero);
+  Constant *VectorZeroUndef = ConstantVector::get(Elems);
+
+  EXPECT_TRUE(match(ScalarUndef, m_Undef()));
+  EXPECT_TRUE(match(VectorUndef, m_Undef()));
+  EXPECT_FALSE(match(ScalarZero, m_Undef()));
+  EXPECT_FALSE(match(VectorZero, m_Undef()));
+  EXPECT_FALSE(match(VectorZeroUndef, m_Undef()));
+
+  EXPECT_FALSE(match(ScalarUndef, m_Zero()));
+  EXPECT_FALSE(match(VectorUndef, m_Zero()));
+  EXPECT_TRUE(match(ScalarZero, m_Zero()));
+  EXPECT_TRUE(match(VectorZero, m_Zero()));
+  EXPECT_TRUE(match(VectorZeroUndef, m_Zero()));
+}
+
+TEST_F(PatternMatchTest, VectorUndefFloat) {
+  Type *ScalarTy = IRB.getFloatTy();
+  Type *VectorTy = VectorType::get(ScalarTy, 4);
+  Constant *ScalarUndef = UndefValue::get(ScalarTy);
+  Constant *VectorUndef = UndefValue::get(VectorTy);
+  Constant *ScalarZero = Constant::getNullValue(ScalarTy);
+  Constant *VectorZero = Constant::getNullValue(VectorTy);
+
+  SmallVector<Constant *, 4> Elems;
+  Elems.push_back(ScalarUndef);
+  Elems.push_back(ScalarZero);
+  Elems.push_back(ScalarUndef);
+  Elems.push_back(ScalarZero);
+  Constant *VectorZeroUndef = ConstantVector::get(Elems);
+
+  EXPECT_TRUE(match(ScalarUndef, m_Undef()));
+  EXPECT_TRUE(match(VectorUndef, m_Undef()));
+  EXPECT_FALSE(match(ScalarZero, m_Undef()));
+  EXPECT_FALSE(match(VectorZero, m_Undef()));
+  EXPECT_FALSE(match(VectorZeroUndef, m_Undef()));
+
+  EXPECT_FALSE(match(ScalarUndef, m_AnyZeroFP()));
+  EXPECT_FALSE(match(VectorUndef, m_AnyZeroFP()));
+  EXPECT_TRUE(match(ScalarZero, m_AnyZeroFP()));
+  EXPECT_TRUE(match(VectorZero, m_AnyZeroFP()));
+  EXPECT_TRUE(match(VectorZeroUndef, m_AnyZeroFP()));
+}
+
 template <typename T> struct MutableConstTest : PatternMatchTest { };
 
 typedef ::testing::Types<std::tuple<Value*, Instruction*>,