[X86][SSE] Fix for getScalarValueForVectorElement to detect scalar sources requiring...

The fix ensures that scalar sources inserted into a vector are the correct bit size.

Integer scalar sources from BUILD_VECTOR and SCALAR_TO_VECTOR nodes may require truncation that this function doesn't currently support.

llvm-svn: 235281

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index c32412a..fd7a60d 100644 (file)
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -6918,8 +6918,13 @@ static SDValue getScalarValueForVectorElement(SDValue V, int Idx,
     return SDValue();
 
   if (V.getOpcode() == ISD::BUILD_VECTOR ||
-      (Idx == 0 && V.getOpcode() == ISD::SCALAR_TO_VECTOR))
-    return DAG.getNode(ISD::BITCAST, SDLoc(V), EltVT, V.getOperand(Idx));
+      (Idx == 0 && V.getOpcode() == ISD::SCALAR_TO_VECTOR)) {
+    // Ensure the scalar operand is the same size as the destination.
+    // FIXME: Add support for scalar truncation where possible.
+    SDValue S = V.getOperand(Idx);
+    if (EltVT.getSizeInBits() == S.getSimpleValueType().getSizeInBits())
+      return DAG.getNode(ISD::BITCAST, SDLoc(V), EltVT, S);
+  }
 
   return SDValue();
 }

diff --git a/llvm/test/CodeGen/X86/fold-vector-shuffle-crash.ll b/llvm/test/CodeGen/X86/fold-vector-shuffle-crash.ll
new file mode 100644 (file)
index 0000000..0bb150b
--- /dev/null
+++ b/llvm/test/CodeGen/X86/fold-vector-shuffle-crash.ll
@@ -0,0 +1,16 @@
+; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=corei7
+
+define void @autogen_SD13708(i32) {
+BB:
+ %Shuff7 = shufflevector <8 x i32> zeroinitializer, <8 x i32> zeroinitializer, <8 x i32> <i32 8, i32 10, i32 12, i32 14, i32 undef, i32 2, i32 4, i32 undef>
+ br label %CF
+
+CF:
+ %Tr = trunc <8 x i64> zeroinitializer to <8 x i32>
+ %Shuff20 = shufflevector <8 x i32> %Shuff7, <8 x i32> %Tr, <8 x i32> <i32 13, i32 15, i32 1, i32 3, i32 5, i32 7, i32 undef, i32 11>
+ br i1 undef, label %CF, label %CF247
+
+CF247:
+ %I171 = insertelement <8 x i32> %Shuff20, i32 %0, i32 0
+ br i1 undef, label %CF, label %CF247
+}
\ No newline at end of file