1 files changed, 29 insertions, 0 deletions
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 71ccb1a..0f29b51 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -13573,6 +13573,35 @@ static SDValue LowerVSETCC(SDValue Op, const X86Subtarget *Subtarget,
                        DAG.getConstant(SSECC, dl, MVT::i8));
   }
 
+  MVT VTOp0 = Op0.getSimpleValueType();
+  assert(VTOp0 == Op1.getSimpleValueType() &&
+         "Expected operands with same type!");
+  assert(VT.getVectorNumElements() == VTOp0.getVectorNumElements() &&
+         "Invalid number of packed elements for source and destination!");
+
+  if (VT.is128BitVector() && VTOp0.is256BitVector()) {
+    // On non-AVX512 targets, a vector of MVT::i1 is promoted by the type
+    // legalizer to a wider vector type.  In the case of 'vsetcc' nodes, the
+    // legalizer firstly checks if the first operand in input to the setcc has
+    // a legal type. If so, then it promotes the return type to that same type.
+    // Otherwise, the return type is promoted to the 'next legal type' which,
+    // for a vector of MVT::i1 is always a 128-bit integer vector type.
+    //
+    // We reach this code only if the following two conditions are met:
+    // 1. Both return type and operand type have been promoted to wider types
+    //    by the type legalizer.
+    // 2. The original operand type has been promoted to a 256-bit vector.
+    //
+    // Note that condition 2. only applies for AVX targets.
+    SDValue NewOp = DAG.getSetCC(dl, VTOp0, Op0, Op1, SetCCOpcode);
+    return DAG.getZExtOrTrunc(NewOp, dl, VT);
+  }
+
+  // The non-AVX512 code below works under the assumption that source and
+  // destination types are the same.
+  assert((Subtarget->hasAVX512() || (VT == VTOp0)) &&
+         "Value types for source and destination must be the same!");
+
   // Break 256-bit integer vector compare into smaller ones.
   if (VT.is256BitVector() && !Subtarget->hasInt256())
     return Lower256IntVSETCC(Op, DAG);