Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -16402,6 +16402,23 @@
   SDValue R = Op.getOperand(0);
   SDValue Amt = Op.getOperand(1);
 
+  if (Subtarget->hasSSE2() &&
+      (VT == MVT::v8i16 || VT == MVT::v4i32 || VT == MVT::v2i16) &&
+      (VT != MVT::v2i64 || Op.getOpcode() != ISD::SRA)) {
+    assert((VT == R.getSimpleValueType() && VT == Amt.getSimpleValueType()) &&
+           "Unexpected operand type");
+    switch (Op.getOpcode()) {
+    default:
+      llvm_unreachable("Unknown shift opcode!");
+    case ISD::SHL:
+      return DAG.getNode(X86ISD::VSHL, dl, VT, R, Op.getOperand(1));
+    case ISD::SRL:
+      return DAG.getNode(X86ISD::VSRL, dl, VT, R, Op.getOperand(1));
+    case ISD::SRA:
+      return DAG.getNode(X86ISD::VSRA, dl, VT, R, Op.getOperand(1));
+    }
+  }
+
   if ((VT == MVT::v2i64 && Op.getOpcode() != ISD::SRA) ||
       VT == MVT::v4i32 || VT == MVT::v8i16 ||
       (Subtarget->hasInt256() &&
Index: lib/Target/X86/X86TargetTransformInfo.cpp
===================================================================
--- lib/Target/X86/X86TargetTransformInfo.cpp
+++ lib/Target/X86/X86TargetTransformInfo.cpp
@@ -248,19 +248,19 @@
     // used for vectorization and we don't want to make vectorized code worse
     // than scalar code.
     { ISD::SHL,  MVT::v16i8,  30 }, // cmpeqb sequence.
-    { ISD::SHL,  MVT::v8i16,  8*10 }, // Scalarized.
-    { ISD::SHL,  MVT::v4i32,  2*5 }, // We optimized this using mul.
-    { ISD::SHL,  MVT::v2i64,  2*10 }, // Scalarized.
+    { ISD::SHL,  MVT::v8i16,  1 },
+    { ISD::SHL,  MVT::v4i32,  1 },
+    { ISD::SHL,  MVT::v2i64,  1 },
     { ISD::SHL,  MVT::v4i64,  4*10 }, // Scalarized.
 
     { ISD::SRL,  MVT::v16i8,  16*10 }, // Scalarized.
-    { ISD::SRL,  MVT::v8i16,  8*10 }, // Scalarized.
-    { ISD::SRL,  MVT::v4i32,  4*10 }, // Scalarized.
-    { ISD::SRL,  MVT::v2i64,  2*10 }, // Scalarized.
+    { ISD::SRL,  MVT::v8i16,  1 },
+    { ISD::SRL,  MVT::v4i32,  1 },
+    { ISD::SRL,  MVT::v2i64,  1 },
 
     { ISD::SRA,  MVT::v16i8,  16*10 }, // Scalarized.
-    { ISD::SRA,  MVT::v8i16,  8*10 }, // Scalarized.
-    { ISD::SRA,  MVT::v4i32,  4*10 }, // Scalarized.
+    { ISD::SRA,  MVT::v8i16,  1 },
+    { ISD::SRA,  MVT::v4i32,  1 },
     { ISD::SRA,  MVT::v2i64,  2*10 }, // Scalarized.
 
     // It is not a good idea to vectorize division. We have to scalarize it and