A fix for 9165.

The DAGCombiner created illegal BUILD_VECTOR operations.
The patch added a check that either illegal operations are
allowed or that the created operation is legal.

llvm-svn: 125435

2 files changed, 41 insertions, 4 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 5a7eebddf80..f2d3195e2fc 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -6375,6 +6375,12 @@ SDValue DAGCombiner::visitINSERT_VECTOR_ELT(SDNode *N) {
   if (InVal.getOpcode() == ISD::UNDEF)
     return InVec;
 
+  EVT VT = InVec.getValueType();
+
+  // If we can't generate a legal BUILD_VECTOR, exit 
+  if (LegalOperations && !TLI.isOperationLegal(ISD::BUILD_VECTOR, VT))
+    return SDValue();
+
   // If the invec is a BUILD_VECTOR and if EltNo is a constant, build a new
   // vector with the inserted element.
   if (InVec.getOpcode() == ISD::BUILD_VECTOR && isa<ConstantSDNode>(EltNo)) {
@@ -6384,13 +6390,12 @@ SDValue DAGCombiner::visitINSERT_VECTOR_ELT(SDNode *N) {
     if (Elt < Ops.size())
       Ops[Elt] = InVal;
     return DAG.getNode(ISD::BUILD_VECTOR, N->getDebugLoc(),
-                       InVec.getValueType(), &Ops[0], Ops.size());
+                       VT, &Ops[0], Ops.size());
   }
   // If the invec is an UNDEF and if EltNo is a constant, create a new
   // BUILD_VECTOR with undef elements and the inserted element.
-  if (!LegalOperations && InVec.getOpcode() == ISD::UNDEF &&
+  if (InVec.getOpcode() == ISD::UNDEF &&
       isa<ConstantSDNode>(EltNo)) {
-    EVT VT = InVec.getValueType();
     EVT EltVT = VT.getVectorElementType();
     unsigned NElts = VT.getVectorNumElements();
     SmallVector<SDValue, 8> Ops(NElts, DAG.getUNDEF(EltVT));
@@ -6399,7 +6404,7 @@ SDValue DAGCombiner::visitINSERT_VECTOR_ELT(SDNode *N) {
     if (Elt < Ops.size())
       Ops[Elt] = InVal;
     return DAG.getNode(ISD::BUILD_VECTOR, N->getDebugLoc(),
-                       InVec.getValueType(), &Ops[0], Ops.size());
+                       VT, &Ops[0], Ops.size());
   }
   return SDValue();
 }
diff --git a/llvm/test/CodeGen/Generic/2011-02-12-shuffle.ll b/llvm/test/CodeGen/Generic/2011-02-12-shuffle.ll
new file mode 100644
index 00000000000..b4d56d193ca
--- /dev/null
+++ b/llvm/test/CodeGen/Generic/2011-02-12-shuffle.ll
@@ -0,0 +1,32 @@
+; RUN: llc < %s
+; PR9165
+
+target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f80:128:128-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32"
+target triple = "i686-pc-win32"
+
+define void @m_387() nounwind {
+entry:
+  br i1 undef, label %if.end, label %UnifiedReturnBlock
+
+if.end:                                           ; preds = %entry
+  %tmp1067 = load <16 x i32> addrspace(1)* null, align 64
+  %tmp1082 = shufflevector         <16 x i32> <i32 0, i32 0, i32 0, i32 undef, i32 undef, i32 0, i32 0, i32 undef, i32 0, i32 0, i32 undef, i32 undef, i32 0, i32 undef, i32 undef, i32 undef>, 
+                                                                                                                <16 x i32> %tmp1067, 
+                                                                                                                <16 x i32> <i32 0, i32 1, i32 2, i32 undef, i32 26, i32 5, i32 6, i32 undef, i32 8, i32 9, i32 31, i32 30, i32 12, i32 undef, i32 undef, i32 undef>
+  
+  %tmp1100 = shufflevector         <16 x i32> %tmp1082, 
+                                                                                                                <16 x i32> %tmp1067, 
+                                                                                                                <16 x i32> <i32 0, i32 1, i32 2, i32 undef, i32 4, i32 5, i32 6, i32 18, i32 8, i32 9, i32 10, i32 11, i32 12, i32 25, i32 undef, i32 17>
+  
+  %tmp1112 = shufflevector         <16 x i32> %tmp1100, 
+                                                                                                                <16 x i32> %tmp1067, 
+                                                                                                                <16 x i32> <i32 0, i32 1, i32 2, i32 24, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 18, i32 15>
+  
+  store <16 x i32> %tmp1112, <16 x i32> addrspace(1)* undef, align 64
+  
+  ret void
+
+UnifiedReturnBlock:                               ; preds = %entry
+  ret void
+}
+