Fix 9173.

Add more folding patterns to constant expressions of vector selects and vector
bitcasts.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125393 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/VMCore/ConstantFold.cpp b/lib/VMCore/ConstantFold.cpp
index f2129c08d2b790ed6337f5881888a56c250f7be3..0ec343f07d2a0a40e6c13062885c38f0e9bd2f42 100644 (file)
--- a/lib/VMCore/ConstantFold.cpp
+++ b/lib/VMCore/ConstantFold.cpp
@@ -42,6 +42,10 @@ using namespace llvm;
 /// input vector constant are all simple integer or FP values.
 static Constant *BitCastConstantVector(ConstantVector *CV,
                                        const VectorType *DstTy) {
+
+  if (CV->isAllOnesValue()) return Constant::getAllOnesValue(DstTy);
+  if (CV->isNullValue()) return Constant::getNullValue(DstTy);
+
   // If this cast changes element count then we can't handle it here:
   // doing so requires endianness information.  This should be handled by
   // Analysis/ConstantFolding.cpp
@@ -689,6 +693,42 @@ Constant *llvm::ConstantFoldSelectInstruction(Constant *Cond,
   if (ConstantInt *CB = dyn_cast<ConstantInt>(Cond))
     return CB->getZExtValue() ? V1 : V2;
 
+  // Check for zero aggregate and ConstantVector of zeros
+  if (Cond->isNullValue()) return V2;
+
+  if (ConstantVector* CondV = dyn_cast<ConstantVector>(Cond)) {
+
+    if (CondV->isAllOnesValue()) return V1;
+
+    const VectorType *VTy = cast<VectorType>(V1->getType());
+    ConstantVector *CP1 = dyn_cast<ConstantVector>(V1);
+    ConstantVector *CP2 = dyn_cast<ConstantVector>(V2);
+
+    if ((CP1 || isa<ConstantAggregateZero>(V1)) &&
+        (CP2 || isa<ConstantAggregateZero>(V2))) {
+
+      // Find the element type of the returned vector
+      const Type *EltTy = VTy->getElementType();
+      unsigned NumElem = VTy->getNumElements();
+      std::vector<Constant*> Res(NumElem);
+
+      bool Valid = true;
+      for (unsigned i = 0; i < NumElem; ++i) {
+        ConstantInt* c = dyn_cast<ConstantInt>(CondV->getOperand(i));
+        if (!c) {
+          Valid = false;
+          break;
+        }
+        Constant *C1 = CP1 ? CP1->getOperand(i) : Constant::getNullValue(EltTy);
+        Constant *C2 = CP2 ? CP2->getOperand(i) : Constant::getNullValue(EltTy);
+        Res[i] = c->getZExtValue() ? C1 : C2;
+      }
+      // If we were able to build the vector, return it
+      if (Valid) return ConstantVector::get(Res);
+    }
+  }
+
+
   if (isa<UndefValue>(V1)) return V2;
   if (isa<UndefValue>(V2)) return V1;
   if (isa<UndefValue>(Cond)) return V1;

diff --git a/test/Transforms/InstCombine/bitcast-vec-uniform.ll b/test/Transforms/InstCombine/bitcast-vec-uniform.ll
new file mode 100644 (file)
index 0000000..1fba163
--- /dev/null
+++ b/test/Transforms/InstCombine/bitcast-vec-uniform.ll
@@ -0,0 +1,14 @@
+; RUN: opt < %s -instcombine -S | not grep bitcast
+
+define <4 x i32> @a(<1 x i64> %y) {
+  %c = bitcast <2 x i64> <i64 0, i64 0> to <4 x i32>
+  ret <4 x i32> %c
+}
+
+define <4 x i32> @b(<1 x i64> %y) {
+  %c = bitcast <2 x i64> <i64 -1, i64 -1> to <4 x i32>
+  ret <4 x i32> %c
+}
+
+
+

diff --git a/test/Transforms/InstCombine/fold-vector-select.ll b/test/Transforms/InstCombine/fold-vector-select.ll
new file mode 100644 (file)
index 0000000..3f22522
--- /dev/null
+++ b/test/Transforms/InstCombine/fold-vector-select.ll
@@ -0,0 +1,13 @@
+; RUN: opt < %s -instcombine -S | not grep select
+
+define void @foo(<4 x i32> *%A, <4 x i32> *%B, <4 x i32> *%C, <4 x i32> *%D) {
+ %r = select <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> <i32 1, i32 2, i32 3, i32 4>, <4 x i32> zeroinitializer
+ %g = select <4 x i1> <i1 false, i1 false, i1 false, i1 false>,  <4 x i32> zeroinitializer, <4 x i32> <i32 3, i32 6, i32 9, i32 1>
+ %b = select <4 x i1> <i1 false, i1 true, i1 false, i1 true>,  <4 x i32> zeroinitializer, <4 x i32> <i32 7, i32 1, i32 4, i32 9>
+ %a = select <4 x i1> zeroinitializer,  <4 x i32> zeroinitializer, <4 x i32> <i32 3, i32 2, i32 8, i32 5>
+ store <4 x i32> %r, <4 x i32>* %A
+ store <4 x i32> %g, <4 x i32>* %B
+ store <4 x i32> %b, <4 x i32>* %C
+ store <4 x i32> %a, <4 x i32>* %D
+ ret void
+}