Index: lib/Target/PowerPC/PPCISelLowering.cpp
===================================================================
--- lib/Target/PowerPC/PPCISelLowering.cpp
+++ lib/Target/PowerPC/PPCISelLowering.cpp
@@ -542,15 +542,21 @@
 
     if (Subtarget.hasVSX()) {
       setOperationAction(ISD::SCALAR_TO_VECTOR, MVT::v2f64, Legal);
-      if (Subtarget.hasP8Vector())
+      setOperationAction(ISD::EXTRACT_VECTOR_ELT, MVT::v2f64, Legal);
+      if (Subtarget.hasP8Vector()) {
         setOperationAction(ISD::SCALAR_TO_VECTOR, MVT::v4f32, Legal);
+        setOperationAction(ISD::EXTRACT_VECTOR_ELT, MVT::v4f32, Legal);
+      }
       if (Subtarget.hasDirectMove()) {
         setOperationAction(ISD::SCALAR_TO_VECTOR, MVT::v16i8, Legal);
         setOperationAction(ISD::SCALAR_TO_VECTOR, MVT::v8i16, Legal);
         setOperationAction(ISD::SCALAR_TO_VECTOR, MVT::v4i32, Legal);
         setOperationAction(ISD::SCALAR_TO_VECTOR, MVT::v2i64, Legal);
+        setOperationAction(ISD::EXTRACT_VECTOR_ELT, MVT::v16i8, Legal);
+        setOperationAction(ISD::EXTRACT_VECTOR_ELT, MVT::v8i16, Legal);
+        setOperationAction(ISD::EXTRACT_VECTOR_ELT, MVT::v4i32, Legal);
+        setOperationAction(ISD::EXTRACT_VECTOR_ELT, MVT::v2i64, Legal);
       }
-      setOperationAction(ISD::EXTRACT_VECTOR_ELT, MVT::v2f64, Legal);
 
       setOperationAction(ISD::FFLOOR, MVT::v2f64, Legal);
       setOperationAction(ISD::FCEIL, MVT::v2f64, Legal);
Index: lib/Target/PowerPC/PPCInstrVSX.td
===================================================================
--- lib/Target/PowerPC/PPCInstrVSX.td
+++ lib/Target/PowerPC/PPCInstrVSX.td
@@ -1222,59 +1222,317 @@
                                [(set f64:$XT, (PPCmtvsrz i32:$rA))]>;
 } // HasDirectMove, HasVSX
 
-/*  Direct moves of various size entities from GPR's into VSR's. Each lines
+/*  Direct moves of various widths from GPR's into VSR's. Each move lines
     the value up into element 0 (both BE and LE). Namely, entities smaller than
     a doubleword are shifted left and moved for BE. For LE, they're moved, then
     swapped to go into the least significant element of the VSR.
 */
-def Moves {
-  dag BE_BYTE_0 = (MTVSRD
-                  (RLDICR
-                    (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 56, 7));
-  dag BE_HALF_0 = (MTVSRD
-                  (RLDICR
-                    (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 48, 15));
-  dag BE_WORD_0 = (MTVSRD
-                  (RLDICR
-                    (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 32, 31));
+def MovesToVSR {
+  dag BE_BYTE_0 =
+    (MTVSRD
+      (RLDICR
+        (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 56, 7));
+  dag BE_HALF_0 =
+    (MTVSRD
+      (RLDICR
+        (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 48, 15));
+  dag BE_WORD_0 =
+    (MTVSRD
+      (RLDICR
+        (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32), 32, 31));
   dag BE_DWORD_0 = (MTVSRD $A);
 
   dag LE_MTVSRW = (MTVSRD (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $A, sub_32));
-  dag LE_WORD_1 = (v2i64 (COPY_TO_REGCLASS LE_MTVSRW, VSRC));
+  dag LE_WORD_1 = (v2i64 (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)),
+                                        LE_MTVSRW, sub_64));
   dag LE_WORD_0 = (XXPERMDI LE_WORD_1, LE_WORD_1, 2);
-  dag LE_DWORD_1 = (v2i64 (COPY_TO_REGCLASS BE_DWORD_0, VSRC));
+  dag LE_DWORD_1 = (v2i64 (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)),
+                                         BE_DWORD_0, sub_64));
   dag LE_DWORD_0 = (XXPERMDI LE_DWORD_1, LE_DWORD_1, 2);
 }
 
+/*  Direct moves of various widths from VSR's to GPR's. Each moves the
+    respective element out of the VSR and ensures that it is lined up
+    to the right side of the GPR. In addition to the extraction from positions
+    specified by a constant, a pattern for extracting from a variable position
+    is provided. This is useful when the element number is not known at
+    compile time.
+    The numbering for the DAG's is for LE, but when used on BE, the correct
+    LE element can just be used (i.e. LE_BYTE_2 == BE_BYTE_13).
+*/
+def MovesFromVSR {
+  // Doubleword extraction
+  dag LE_DWORD_0 =
+    (MFVSRD
+      (EXTRACT_SUBREG
+        (XXPERMDI (COPY_TO_REGCLASS $S, VSRC),
+                  (COPY_TO_REGCLASS $S, VSRC), 2), sub_64));
+  dag LE_DWORD_1 = (MFVSRD
+                     (EXTRACT_SUBREG
+                       (v2i64 (COPY_TO_REGCLASS $S, VSRC)), sub_64));
+
+  // Word extraction
+  dag LE_WORD_0 = (MFVSRWZ (EXTRACT_SUBREG (XXSLDWI $S, $S, 2), sub_64));
+  dag LE_WORD_1 = (MFVSRWZ (EXTRACT_SUBREG (XXSLDWI $S, $S, 1), sub_64));
+  dag LE_WORD_2 = (MFVSRWZ (EXTRACT_SUBREG
+                             (v2i64 (COPY_TO_REGCLASS $S, VSRC)), sub_64));
+  dag LE_WORD_3 = (MFVSRWZ (EXTRACT_SUBREG (XXSLDWI $S, $S, 3), sub_64));
+
+  // Byte extraction (used for halfwords as well)
+  dag LE_BYTE_0 = (EXTRACT_SUBREG LE_DWORD_0, sub_32);
+  dag LE_BYTE_1 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 56, 8), sub_32));
+  dag LE_BYTE_2 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 48, 16), sub_32));
+  dag LE_BYTE_3 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 40, 24), sub_32));
+  dag LE_BYTE_4 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 32, 32), sub_32));
+  dag LE_BYTE_5 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 24, 40), sub_32));
+  dag LE_BYTE_6 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 16, 48), sub_32));
+  dag LE_BYTE_7 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_0, 8, 56), sub_32));
+  dag LE_BYTE_8 = (EXTRACT_SUBREG LE_DWORD_1, sub_32);
+  dag LE_BYTE_9 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 56, 8), sub_32));
+  dag LE_BYTE_10 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 48, 16), sub_32));
+  dag LE_BYTE_11 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 40, 24), sub_32));
+  dag LE_BYTE_12 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 32, 32), sub_32));
+  dag LE_BYTE_13 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 24, 40), sub_32));
+  dag LE_BYTE_14 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 16, 48), sub_32));
+  dag LE_BYTE_15 = (i32 (EXTRACT_SUBREG (RLDICL LE_DWORD_1, 8, 56), sub_32));
+
+  /* Variable element number (BE and LE patterns must be specified separately)
+     This is a rather involved process. We do not have any register based shift
+     or permute instructions in VSX. What we do is set up the index by masking
+     off bits we don't need and shifting accordingly. Then we set up a VMX
+     permute vector, peform the permute, move the permuted value and finally
+     shift it to the right so the correct byte is on the right of the GPR.
+     Of course, the index is an element number which has a different meaning
+     on LE/BE so the patterns have to be specified separately.
+  */
+  // LE variable byte
+  dag LE_VBYTE_PERM_VEC = (LVSL ZERO8, (ANDC8 (LI8 8), $Idx));
+  dag LE_VBYTE_PERMUTE = (VPERM $S, $S, LE_VBYTE_PERM_VEC);
+  dag LE_MV_VBYTE = (MFVSRD
+                      (EXTRACT_SUBREG
+                        (v2i64 (COPY_TO_REGCLASS LE_VBYTE_PERMUTE, VSRC)),
+                        sub_64));
+  dag LE_VBYTE_SHIFT = (EXTRACT_SUBREG (RLDICR (AND8 (LI8 7), $Idx), 3, 60),
+                                       sub_32);
+  dag LE_VARIABLE_BYTE = (EXTRACT_SUBREG (SRD LE_MV_VBYTE, LE_VBYTE_SHIFT),
+                                         sub_32);
+
+  // BE variable byte
+  dag BE_VBYTE_PERM_VEC = (LVSL ZERO8, (ANDIo8 $Idx, 8));
+  dag BE_VBYTE_PERMUTE = (VPERM $S, $S, BE_VBYTE_PERM_VEC);
+  dag BE_MV_VBYTE = (MFVSRD
+                      (EXTRACT_SUBREG
+                        (v2i64 (COPY_TO_REGCLASS BE_VBYTE_PERMUTE, VSRC)),
+                        sub_64));
+  dag BE_VBYTE_SHIFT = (EXTRACT_SUBREG (RLDICR (ANDC8 (LI8 7), $Idx), 3, 60),
+                                       sub_32);
+  dag BE_VARIABLE_BYTE = (EXTRACT_SUBREG (SRD BE_MV_VBYTE, BE_VBYTE_SHIFT),
+                                         sub_32);
+
+  // LE variable halfword
+  dag LE_VHALF_PERM_VEC = (LVSL ZERO8, (RLDICR (ANDC8 (LI8 4), $Idx), 1, 62));
+  dag LE_VHALF_PERMUTE = (VPERM $S, $S, LE_VHALF_PERM_VEC);
+  dag LE_MV_VHALF = (MFVSRD
+                      (EXTRACT_SUBREG
+                        (v2i64 (COPY_TO_REGCLASS LE_VHALF_PERMUTE, VSRC)),
+                        sub_64));
+  dag LE_VHALF_SHIFT = (EXTRACT_SUBREG (RLDICR (AND8 (LI8 3), $Idx), 4, 59),
+                                       sub_32);
+  dag LE_VARIABLE_HALF = (EXTRACT_SUBREG (SRD LE_MV_VHALF, LE_VHALF_SHIFT),
+                                         sub_32);
+
+  // BE variable halfword
+  dag BE_VHALF_PERM_VEC = (LVSL ZERO8, (RLDICR (ANDIo8 $Idx, 4), 1, 62));
+  dag BE_VHALF_PERMUTE = (VPERM $S, $S, BE_VHALF_PERM_VEC);
+  dag BE_MV_VHALF = (MFVSRD
+                      (EXTRACT_SUBREG
+                        (v2i64 (COPY_TO_REGCLASS BE_VHALF_PERMUTE, VSRC)),
+                        sub_64));
+  dag BE_VHALF_SHIFT = (EXTRACT_SUBREG (RLDICR (ANDC8 (LI8 3), $Idx), 4, 60),
+                                       sub_32);
+  dag BE_VARIABLE_HALF = (EXTRACT_SUBREG (SRD BE_MV_VHALF, BE_VHALF_SHIFT),
+                                         sub_32);
+}
+
+// v4f32 scalar <-> vector conversions (BE)
 let Predicates = [IsBigEndian, HasP8Vector] in {
   def : Pat<(v4f32 (scalar_to_vector f32:$A)),
             (v4f32 (XSCVDPSPN $A))>;
+  def : Pat<(f32 (vector_extract v4f32:$S, 0)),
+            (f32 (XSCVSPDPN $S))>;
+  def : Pat<(f32 (vector_extract v4f32:$S, 1)),
+            (f32 (XSCVSPDPN (XXSLDWI $S, $S, 1)))>;
+  def : Pat<(f32 (vector_extract v4f32:$S, 2)),
+            (f32 (XSCVSPDPN (XXSLDWI $S, $S, 2)))>;
+  def : Pat<(f32 (vector_extract v4f32:$S, 3)),
+            (f32 (XSCVSPDPN (XXSLDWI $S, $S, 3)))>;
 } // IsBigEndian, HasP8Vector
 
 let Predicates = [IsBigEndian, HasDirectMove] in {
   def : Pat<(v16i8 (scalar_to_vector i32:$A)),
-            (v16i8 (COPY_TO_REGCLASS Moves.BE_BYTE_0, VSRC))>;
+            (v16i8 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_BYTE_0, sub_64))>;
   def : Pat<(v8i16 (scalar_to_vector i32:$A)),
-            (v8i16 (COPY_TO_REGCLASS Moves.BE_HALF_0, VSRC))>;
+            (v8i16 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_HALF_0, sub_64))>;
   def : Pat<(v4i32 (scalar_to_vector i32:$A)),
-            (v4i32 (COPY_TO_REGCLASS Moves.BE_WORD_0, VSRC))>;
+            (v4i32 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_WORD_0, sub_64))>;
   def : Pat<(v2i64 (scalar_to_vector i64:$A)),
-            (v2i64 (COPY_TO_REGCLASS Moves.BE_DWORD_0, VSRC))>;
+            (v2i64 (SUBREG_TO_REG (i64 1), MovesToVSR.BE_DWORD_0, sub_64))>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 0)),
+            (i32 MovesFromVSR.LE_BYTE_15)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 1)),
+            (i32 MovesFromVSR.LE_BYTE_14)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 2)),
+            (i32 MovesFromVSR.LE_BYTE_13)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 3)),
+            (i32 MovesFromVSR.LE_BYTE_12)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 4)),
+            (i32 MovesFromVSR.LE_BYTE_11)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 5)),
+            (i32 MovesFromVSR.LE_BYTE_10)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 6)),
+            (i32 MovesFromVSR.LE_BYTE_9)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 7)),
+            (i32 MovesFromVSR.LE_BYTE_8)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 8)),
+            (i32 MovesFromVSR.LE_BYTE_7)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 9)),
+            (i32 MovesFromVSR.LE_BYTE_6)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 10)),
+            (i32 MovesFromVSR.LE_BYTE_5)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 11)),
+            (i32 MovesFromVSR.LE_BYTE_4)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 12)),
+            (i32 MovesFromVSR.LE_BYTE_3)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 13)),
+            (i32 MovesFromVSR.LE_BYTE_2)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 14)),
+            (i32 MovesFromVSR.LE_BYTE_1)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 15)),
+            (i32 MovesFromVSR.LE_BYTE_0)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, i64:$Idx)),
+            (i32 MovesFromVSR.BE_VARIABLE_BYTE)>;
+
+  def : Pat<(i32 (vector_extract v8i16:$S, 0)),
+            (i32 MovesFromVSR.LE_BYTE_14)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 1)),
+            (i32 MovesFromVSR.LE_BYTE_12)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 2)),
+            (i32 MovesFromVSR.LE_BYTE_10)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 3)),
+            (i32 MovesFromVSR.LE_BYTE_8)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 4)),
+            (i32 MovesFromVSR.LE_BYTE_6)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 5)),
+            (i32 MovesFromVSR.LE_BYTE_4)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 6)),
+            (i32 MovesFromVSR.LE_BYTE_2)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 7)),
+            (i32 MovesFromVSR.LE_BYTE_0)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, i64:$Idx)),
+            (i32 MovesFromVSR.BE_VARIABLE_HALF)>;
+
+  def : Pat<(i32 (vector_extract v4i32:$S, 0)),
+            (i32 MovesFromVSR.LE_WORD_3)>;
+  def : Pat<(i32 (vector_extract v4i32:$S, 1)),
+            (i32 MovesFromVSR.LE_WORD_2)>;
+  def : Pat<(i32 (vector_extract v4i32:$S, 2)),
+            (i32 MovesFromVSR.LE_WORD_1)>;
+  def : Pat<(i32 (vector_extract v4i32:$S, 3)),
+            (i32 MovesFromVSR.LE_WORD_0)>;
+
+  def : Pat<(i64 (vector_extract v2i64:$S, 0)),
+            (i64 MovesFromVSR.LE_DWORD_1)>;
+  def : Pat<(i64 (vector_extract v2i64:$S, 1)),
+            (i64 MovesFromVSR.LE_DWORD_0)>;
 } // IsBigEndian, HasDirectMove
 
 let Predicates = [IsLittleEndian, HasP8Vector] in {
   def : Pat<(v4f32 (scalar_to_vector f32:$A)),
             (v4f32 (XXSLDWI (XSCVDPSPN $A), (XSCVDPSPN $A), 1))>;
+  def : Pat<(f32 (vector_extract v4f32:$S, 0)),
+            (f32 (XSCVSPDPN (XXSLDWI $S, $S, 3)))>;
+  def : Pat<(f32 (vector_extract v4f32:$S, 1)),
+            (f32 (XSCVSPDPN (XXSLDWI $S, $S, 2)))>;
+  def : Pat<(f32 (vector_extract v4f32:$S, 2)),
+            (f32 (XSCVSPDPN (XXSLDWI $S, $S, 1)))>;
+  def : Pat<(f32 (vector_extract v4f32:$S, 3)),
+            (f32 (XSCVSPDPN $S))>;
 } // IsLittleEndian, HasP8Vector
 
 let Predicates = [IsLittleEndian, HasDirectMove] in {
   def : Pat<(v16i8 (scalar_to_vector i32:$A)),
-            (v16i8 (COPY_TO_REGCLASS Moves.LE_WORD_0, VSRC))>;
+            (v16i8 (COPY_TO_REGCLASS MovesToVSR.LE_WORD_0, VSRC))>;
   def : Pat<(v8i16 (scalar_to_vector i32:$A)),
-            (v8i16 (COPY_TO_REGCLASS Moves.LE_WORD_0, VSRC))>;
+            (v8i16 (COPY_TO_REGCLASS MovesToVSR.LE_WORD_0, VSRC))>;
   def : Pat<(v4i32 (scalar_to_vector i32:$A)),
-            (v4i32 (COPY_TO_REGCLASS Moves.LE_WORD_0, VSRC))>;
+            (v4i32 MovesToVSR.LE_WORD_0)>;
   def : Pat<(v2i64 (scalar_to_vector i64:$A)),
-            (v2i64 Moves.LE_DWORD_0)>;
+            (v2i64 MovesToVSR.LE_DWORD_0)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 0)),
+            (i32 MovesFromVSR.LE_BYTE_0)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 1)),
+            (i32 MovesFromVSR.LE_BYTE_1)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 2)),
+            (i32 MovesFromVSR.LE_BYTE_2)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 3)),
+            (i32 MovesFromVSR.LE_BYTE_3)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 4)),
+            (i32 MovesFromVSR.LE_BYTE_4)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 5)),
+            (i32 MovesFromVSR.LE_BYTE_5)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 6)),
+            (i32 MovesFromVSR.LE_BYTE_6)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 7)),
+            (i32 MovesFromVSR.LE_BYTE_7)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 8)),
+            (i32 MovesFromVSR.LE_BYTE_8)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 9)),
+            (i32 MovesFromVSR.LE_BYTE_9)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 10)),
+            (i32 MovesFromVSR.LE_BYTE_10)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 11)),
+            (i32 MovesFromVSR.LE_BYTE_11)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 12)),
+            (i32 MovesFromVSR.LE_BYTE_12)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 13)),
+            (i32 MovesFromVSR.LE_BYTE_13)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 14)),
+            (i32 MovesFromVSR.LE_BYTE_14)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, 15)),
+            (i32 MovesFromVSR.LE_BYTE_15)>;
+  def : Pat<(i32 (vector_extract v16i8:$S, i64:$Idx)),
+            (i32 MovesFromVSR.LE_VARIABLE_BYTE)>;
+
+  def : Pat<(i32 (vector_extract v8i16:$S, 0)),
+            (i32 MovesFromVSR.LE_BYTE_0)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 1)),
+            (i32 MovesFromVSR.LE_BYTE_2)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 2)),
+            (i32 MovesFromVSR.LE_BYTE_4)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 3)),
+            (i32 MovesFromVSR.LE_BYTE_6)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 4)),
+            (i32 MovesFromVSR.LE_BYTE_8)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 5)),
+            (i32 MovesFromVSR.LE_BYTE_10)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 6)),
+            (i32 MovesFromVSR.LE_BYTE_12)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, 7)),
+            (i32 MovesFromVSR.LE_BYTE_14)>;
+  def : Pat<(i32 (vector_extract v8i16:$S, i64:$Idx)),
+            (i32 MovesFromVSR.LE_VARIABLE_HALF)>;
+
+  def : Pat<(i32 (vector_extract v4i32:$S, 0)),
+            (i32 MovesFromVSR.LE_WORD_0)>;
+  def : Pat<(i32 (vector_extract v4i32:$S, 1)),
+            (i32 MovesFromVSR.LE_WORD_1)>;
+  def : Pat<(i32 (vector_extract v4i32:$S, 2)),
+            (i32 MovesFromVSR.LE_WORD_2)>;
+  def : Pat<(i32 (vector_extract v4i32:$S, 3)),
+            (i32 MovesFromVSR.LE_WORD_3)>;
+
+  def : Pat<(i64 (vector_extract v2i64:$S, 0)),
+            (i64 MovesFromVSR.LE_DWORD_0)>;
+  def : Pat<(i64 (vector_extract v2i64:$S, 1)),
+            (i64 MovesFromVSR.LE_DWORD_1)>;
 } // IsLittleEndian, HasDirectMove
-
Index: lib/Target/PowerPC/PPCVSXCopy.cpp
===================================================================
--- lib/Target/PowerPC/PPCVSXCopy.cpp
+++ lib/Target/PowerPC/PPCVSXCopy.cpp
@@ -128,6 +128,7 @@
             IsVRReg(DstMO.getReg(), MRI) ? &PPC::VSHRCRegClass :
                                            &PPC::VSLRCRegClass;
           assert((IsF8Reg(DstMO.getReg(), MRI) ||
+                  IsVSFReg(DstMO.getReg(), MRI) ||
                   IsVRReg(DstMO.getReg(), MRI)) &&
                  "Unknown destination for a VSX copy");
 
Index: test/CodeGen/PowerPC/p8-scalar_vector_conversions.ll
===================================================================
--- test/CodeGen/PowerPC/p8-scalar_vector_conversions.ll
+++ test/CodeGen/PowerPC/p8-scalar_vector_conversions.ll
@@ -77,3 +77,1377 @@
 ; CHECK-LE: xscvdpspn [[REG1:[0-9]+]], 1
 ; CHECK-LE: xxsldwi {{[0-9]+}}, [[REG1]], [[REG1]], 1
 }
+
+; Function Attrs: nounwind
+define signext i8 @getsc0(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 0
+  ret i8 %vecext
+; CHECK-LABEL: @getsc0
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 8, 56
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc0
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc1(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 1
+  ret i8 %vecext
+; CHECK-LABEL: @getsc1
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 16, 48
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc1
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 56, 8
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc2(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 2
+  ret i8 %vecext
+; CHECK-LABEL: @getsc2
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 24, 40
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc2
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 48, 16
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc3(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 3
+  ret i8 %vecext
+; CHECK-LABEL: @getsc3
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 32, 32
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc3
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 40, 24
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc4(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 4
+  ret i8 %vecext
+; CHECK-LABEL: @getsc4
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 40, 24
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc4
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 32, 32
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc5(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 5
+  ret i8 %vecext
+; CHECK-LABEL: @getsc5
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 48, 16
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc5
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 24, 40
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc6(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 6
+  ret i8 %vecext
+; CHECK-LABEL: @getsc6
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 56, 8
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc6
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 16, 48
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc7(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 7
+  ret i8 %vecext
+; CHECK-LABEL: @getsc7
+; CHECK: mfvsrd 3, 34
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc7
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 8, 56
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc8(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 8
+  ret i8 %vecext
+; CHECK-LABEL: @getsc8
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 8, 56
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc8
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc9(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 9
+  ret i8 %vecext
+; CHECK-LABEL: @getsc9
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 16, 48
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc9
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 56, 8
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc10(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 10
+  ret i8 %vecext
+; CHECK-LABEL: @getsc10
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 24, 40
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc10
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 48, 16
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc11(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 11
+  ret i8 %vecext
+; CHECK-LABEL: @getsc11
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 32, 32
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc11
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 40, 24
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc12(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 12
+  ret i8 %vecext
+; CHECK-LABEL: @getsc12
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 40, 24
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc12
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 32, 32
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc13(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 13
+  ret i8 %vecext
+; CHECK-LABEL: @getsc13
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 48, 16
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc13
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 24, 40
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc14(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 14
+  ret i8 %vecext
+; CHECK-LABEL: @getsc14
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 56, 8
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc14
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 16, 48
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i8 @getsc15(<16 x i8> %vsc) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 15
+  ret i8 %vecext
+; CHECK-LABEL: @getsc15
+; CHECK: mfvsrd 3,
+; CHECK: extsb 3, 3
+; CHECK-LABEL-LE: @getsc15
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 8, 56
+; CHECK-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc0(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 0
+  ret i8 %vecext
+; CHECK-LABEL: @getuc0
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 8, 56
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc0
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc1(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 1
+  ret i8 %vecext
+; CHECK-LABEL: @getuc1
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 16, 48
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc1
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 56, 8
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc2(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 2
+  ret i8 %vecext
+; CHECK-LABEL: @getuc2
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 24, 40
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc2
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 48, 16
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc3(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 3
+  ret i8 %vecext
+; CHECK-LABEL: @getuc3
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 32, 32
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc3
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 40, 24
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc4(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 4
+  ret i8 %vecext
+; CHECK-LABEL: @getuc4
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 40, 24
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc4
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 32, 32
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc5(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 5
+  ret i8 %vecext
+; CHECK-LABEL: @getuc5
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 48, 16
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc5
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 24, 40
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc6(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 6
+  ret i8 %vecext
+; CHECK-LABEL: @getuc6
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 56, 8
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc6
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 16, 48
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc7(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 7
+  ret i8 %vecext
+; CHECK-LABEL: @getuc7
+; CHECK: mfvsrd 3, 34
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc7
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 8, 56
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc8(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 8
+  ret i8 %vecext
+; CHECK-LABEL: @getuc8
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 8, 56
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc8
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc9(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 9
+  ret i8 %vecext
+; CHECK-LABEL: @getuc9
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 16, 48
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc9
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 56, 8
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc10(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 10
+  ret i8 %vecext
+; CHECK-LABEL: @getuc10
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 24, 40
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc10
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 48, 16
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc11(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 11
+  ret i8 %vecext
+; CHECK-LABEL: @getuc11
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 32, 32
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc11
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 40, 24
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc12(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 12
+  ret i8 %vecext
+; CHECK-LABEL: @getuc12
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 40, 24
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc12
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 32, 32
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc13(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 13
+  ret i8 %vecext
+; CHECK-LABEL: @getuc13
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 48, 16
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc13
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 24, 40
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc14(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 14
+  ret i8 %vecext
+; CHECK-LABEL: @getuc14
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 56, 8
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc14
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 16, 48
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getuc15(<16 x i8> %vuc) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %vecext = extractelement <16 x i8> %0, i32 15
+  ret i8 %vecext
+; CHECK-LABEL: @getuc15
+; CHECK: mfvsrd 3,
+; CHECK: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getuc15
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 8, 56
+; CHECK-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define signext i8 @getvelsc(<16 x i8> %vsc, i32 signext %i) {
+entry:
+  %vsc.addr = alloca <16 x i8>, align 16
+  %i.addr = alloca i32, align 4
+  store <16 x i8> %vsc, <16 x i8>* %vsc.addr, align 16
+  store i32 %i, i32* %i.addr, align 4
+  %0 = load <16 x i8>, <16 x i8>* %vsc.addr, align 16
+  %1 = load i32, i32* %i.addr, align 4
+  %vecext = extractelement <16 x i8> %0, i32 %1
+  ret i8 %vecext
+; CHECK-LABEL: @getvelsc
+; CHECK-DAG: andi. [[ANDI:[0-9]+]], {{[0-9]+}}, 8
+; CHECK-DAG: lvsl [[SHMSK:[0-9]+]], 0, [[ANDI]]
+; CHECK-DAG: vperm [[PERMD:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, [[SHMSK]]
+; CHECK-DAG: mfvsrd [[MOV:[0-9]+]],
+; CHECK-DAG: li [[IMM7:[0-9]+]], 7
+; CHECK-DAG: andc [[ANDC:[0-9]+]], [[IMM7]]
+; CHECK-DAG: sldi [[SHL:[0-9]+]], [[ANDC]], 3
+; CHECK-DAG: srd 3, [[MOV]], [[SHL]]
+; CHECK-DAG: extsb 3, 3
+; CHECK-LABEL-LE: @getvelsc
+; CHECK-DAG-LE: li [[IMM8:[0-9]+]], 8
+; CHECK-DAG-LE: andc [[ANDC:[0-9]+]], [[IMM8]]
+; CHECK-DAG-LE: lvsl [[SHMSK:[0-9]+]], 0, [[ANDC]]
+; CHECK-DAG-LE: vperm [[PERMD:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, [[SHMSK]]
+; CHECK-DAG-LE: mfvsrd [[MOV:[0-9]+]],
+; CHECK-DAG-LE: li [[IMM7:[0-9]+]], 7
+; CHECK-DAG-LE: and [[AND:[0-9]+]], [[IMM7]]
+; CHECK-DAG-LE: sldi [[SHL:[0-9]+]], [[AND]], 3
+; CHECK-DAG-LE: srd 3, [[MOV]], [[SHL]]
+; CHECK-DAG-LE: extsb 3, 3
+}
+
+; Function Attrs: nounwind
+define zeroext i8 @getveluc(<16 x i8> %vuc, i32 signext %i) {
+entry:
+  %vuc.addr = alloca <16 x i8>, align 16
+  %i.addr = alloca i32, align 4
+  store <16 x i8> %vuc, <16 x i8>* %vuc.addr, align 16
+  store i32 %i, i32* %i.addr, align 4
+  %0 = load <16 x i8>, <16 x i8>* %vuc.addr, align 16
+  %1 = load i32, i32* %i.addr, align 4
+  %vecext = extractelement <16 x i8> %0, i32 %1
+  ret i8 %vecext
+; CHECK-LABEL: @getveluc
+; CHECK-DAG: andi. [[ANDI:[0-9]+]], {{[0-9]+}}, 8
+; CHECK-DAG: lvsl [[SHMSK:[0-9]+]], 0, [[ANDI]]
+; CHECK-DAG: vperm [[PERMD:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, [[SHMSK]]
+; CHECK-DAG: mfvsrd [[MOV:[0-9]+]],
+; CHECK-DAG: li [[IMM7:[0-9]+]], 7
+; CHECK-DAG: andc [[ANDC:[0-9]+]], [[IMM7]]
+; CHECK-DAG: sldi [[SHL:[0-9]+]], [[ANDC]], 3
+; CHECK-DAG: srd 3, [[MOV]], [[SHL]]
+; CHECK-DAG: clrldi   3, 3, 56
+; CHECK-LABEL-LE: @getveluc
+; CHECK-DAG-LE: li [[IMM8:[0-9]+]], 8
+; CHECK-DAG-LE: andc [[ANDC:[0-9]+]], [[IMM8]]
+; CHECK-DAG-LE: lvsl [[SHMSK:[0-9]+]], 0, [[ANDC]]
+; CHECK-DAG-LE: vperm [[PERMD:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, [[SHMSK]]
+; CHECK-DAG-LE: mfvsrd [[MOV:[0-9]+]],
+; CHECK-DAG-LE: li [[IMM7:[0-9]+]], 7
+; CHECK-DAG-LE: and [[AND:[0-9]+]], [[IMM7]]
+; CHECK-DAG-LE: sldi [[SHL:[0-9]+]], [[AND]], 3
+; CHECK-DAG-LE: srd 3, [[MOV]], [[SHL]]
+; CHECK-DAG-LE: clrldi   3, 3, 56
+}
+
+; Function Attrs: nounwind
+define signext i16 @getss0(<8 x i16> %vss) {
+entry:
+  %vss.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vss, <8 x i16>* %vss.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vss.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 0
+  ret i16 %vecext
+; CHECK-LABEL: @getss0
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 16, 48
+; CHECK: extsh 3, 3
+; CHECK-LABEL-LE: @getss0
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: extsh 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i16 @getss1(<8 x i16> %vss) {
+entry:
+  %vss.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vss, <8 x i16>* %vss.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vss.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 1
+  ret i16 %vecext
+; CHECK-LABEL: @getss1
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 32, 32
+; CHECK: extsh 3, 3
+; CHECK-LABEL-LE: @getss1
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 48, 16
+; CHECK-LE: extsh 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i16 @getss2(<8 x i16> %vss) {
+entry:
+  %vss.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vss, <8 x i16>* %vss.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vss.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 2
+  ret i16 %vecext
+; CHECK-LABEL: @getss2
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 48, 16
+; CHECK: extsh 3, 3
+; CHECK-LABEL-LE: @getss2
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 32, 32
+; CHECK-LE: extsh 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i16 @getss3(<8 x i16> %vss) {
+entry:
+  %vss.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vss, <8 x i16>* %vss.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vss.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 3
+  ret i16 %vecext
+; CHECK-LABEL: @getss3
+; CHECK: mfvsrd 3, 34
+; CHECK: extsh 3, 3
+; CHECK-LABEL-LE: @getss3
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 16, 48
+; CHECK-LE: extsh 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i16 @getss4(<8 x i16> %vss) {
+entry:
+  %vss.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vss, <8 x i16>* %vss.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vss.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 4
+  ret i16 %vecext
+; CHECK-LABEL: @getss4
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 16, 48
+; CHECK: extsh 3, 3
+; CHECK-LABEL-LE: @getss4
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: extsh 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i16 @getss5(<8 x i16> %vss) {
+entry:
+  %vss.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vss, <8 x i16>* %vss.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vss.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 5
+  ret i16 %vecext
+; CHECK-LABEL: @getss5
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 32, 32
+; CHECK: extsh 3, 3
+; CHECK-LABEL-LE: @getss5
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 48, 16
+; CHECK-LE: extsh 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i16 @getss6(<8 x i16> %vss) {
+entry:
+  %vss.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vss, <8 x i16>* %vss.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vss.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 6
+  ret i16 %vecext
+; CHECK-LABEL: @getss6
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 48, 16
+; CHECK: extsh 3, 3
+; CHECK-LABEL-LE: @getss6
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 32, 32
+; CHECK-LE: extsh 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i16 @getss7(<8 x i16> %vss) {
+entry:
+  %vss.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vss, <8 x i16>* %vss.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vss.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 7
+  ret i16 %vecext
+; CHECK-LABEL: @getss7
+; CHECK: mfvsrd 3,
+; CHECK: extsh 3, 3
+; CHECK-LABEL-LE: @getss7
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 16, 48
+; CHECK-LE: extsh 3, 3
+}
+
+; Function Attrs: nounwind
+define zeroext i16 @getus0(<8 x i16> %vus) {
+entry:
+  %vus.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vus, <8 x i16>* %vus.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vus.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 0
+  ret i16 %vecext
+; CHECK-LABEL: @getus0
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 16, 48
+; CHECK: clrldi   3, 3, 48
+; CHECK-LABEL-LE: @getus0
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: clrldi   3, 3, 48
+}
+
+; Function Attrs: nounwind
+define zeroext i16 @getus1(<8 x i16> %vus) {
+entry:
+  %vus.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vus, <8 x i16>* %vus.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vus.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 1
+  ret i16 %vecext
+; CHECK-LABEL: @getus1
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 32, 32
+; CHECK: clrldi   3, 3, 48
+; CHECK-LABEL-LE: @getus1
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 48, 16
+; CHECK-LE: clrldi   3, 3, 48
+}
+
+; Function Attrs: nounwind
+define zeroext i16 @getus2(<8 x i16> %vus) {
+entry:
+  %vus.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vus, <8 x i16>* %vus.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vus.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 2
+  ret i16 %vecext
+; CHECK-LABEL: @getus2
+; CHECK: mfvsrd 3, 34
+; CHECK: rldicl 3, 3, 48, 16
+; CHECK: clrldi   3, 3, 48
+; CHECK-LABEL-LE: @getus2
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 32, 32
+; CHECK-LE: clrldi   3, 3, 48
+}
+
+; Function Attrs: nounwind
+define zeroext i16 @getus3(<8 x i16> %vus) {
+entry:
+  %vus.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vus, <8 x i16>* %vus.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vus.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 3
+  ret i16 %vecext
+; CHECK-LABEL: @getus3
+; CHECK: mfvsrd 3, 34
+; CHECK: clrldi   3, 3, 48
+; CHECK-LABEL-LE: @getus3
+; CHECK-LE: mfvsrd 3,
+; CHECK-LE: rldicl 3, 3, 16, 48
+; CHECK-LE: clrldi   3, 3, 48
+}
+
+; Function Attrs: nounwind
+define zeroext i16 @getus4(<8 x i16> %vus) {
+entry:
+  %vus.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vus, <8 x i16>* %vus.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vus.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 4
+  ret i16 %vecext
+; CHECK-LABEL: @getus4
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 16, 48
+; CHECK: clrldi   3, 3, 48
+; CHECK-LABEL-LE: @getus4
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: clrldi   3, 3, 48
+}
+
+; Function Attrs: nounwind
+define zeroext i16 @getus5(<8 x i16> %vus) {
+entry:
+  %vus.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vus, <8 x i16>* %vus.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vus.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 5
+  ret i16 %vecext
+; CHECK-LABEL: @getus5
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 32, 32
+; CHECK: clrldi   3, 3, 48
+; CHECK-LABEL-LE: @getus5
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 48, 16
+; CHECK-LE: clrldi   3, 3, 48
+}
+
+; Function Attrs: nounwind
+define zeroext i16 @getus6(<8 x i16> %vus) {
+entry:
+  %vus.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vus, <8 x i16>* %vus.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vus.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 6
+  ret i16 %vecext
+; CHECK-LABEL: @getus6
+; CHECK: mfvsrd 3,
+; CHECK: rldicl 3, 3, 48, 16
+; CHECK: clrldi   3, 3, 48
+; CHECK-LABEL-LE: @getus6
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 32, 32
+; CHECK-LE: clrldi   3, 3, 48
+}
+
+; Function Attrs: nounwind
+define zeroext i16 @getus7(<8 x i16> %vus) {
+entry:
+  %vus.addr = alloca <8 x i16>, align 16
+  store <8 x i16> %vus, <8 x i16>* %vus.addr, align 16
+  %0 = load <8 x i16>, <8 x i16>* %vus.addr, align 16
+  %vecext = extractelement <8 x i16> %0, i32 7
+  ret i16 %vecext
+; CHECK-LABEL: @getus7
+; CHECK: mfvsrd 3,
+; CHECK: clrldi   3, 3, 48
+; CHECK-LABEL-LE: @getus7
+; CHECK-LE: mfvsrd 3, 34
+; CHECK-LE: rldicl 3, 3, 16, 48
+; CHECK-LE: clrldi   3, 3, 48
+}
+
+; Function Attrs: nounwind
+define signext i16 @getvelss(<8 x i16> %vss, i32 signext %i) {
+entry:
+  %vss.addr = alloca <8 x i16>, align 16
+  %i.addr = alloca i32, align 4
+  store <8 x i16> %vss, <8 x i16>* %vss.addr, align 16
+  store i32 %i, i32* %i.addr, align 4
+  %0 = load <8 x i16>, <8 x i16>* %vss.addr, align 16
+  %1 = load i32, i32* %i.addr, align 4
+  %vecext = extractelement <8 x i16> %0, i32 %1
+  ret i16 %vecext
+; CHECK-LABEL: @getvelss
+; CHECK-DAG: andi. [[ANDI:[0-9]+]], {{[0-9]+}}, 4
+; CHECK-DAG: sldi [[MUL2:[0-9]+]], [[ANDI]], 1
+; CHECK-DAG: lvsl [[SHMSK:[0-9]+]], 0, [[MUL2]]
+; CHECK-DAG: vperm [[PERMD:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, [[SHMSK]]
+; CHECK-DAG: mfvsrd [[MOV:[0-9]+]],
+; CHECK-DAG: li [[IMM3:[0-9]+]], 3
+; CHECK-DAG: andc [[ANDC:[0-9]+]], [[IMM3]]
+; CHECK-DAG: rldicr [[SHL:[0-9]+]], [[ANDC]], 4, 60
+; CHECK-DAG: srd 3, [[MOV]], [[SHL]]
+; CHECK-DAG: extsh 3, 3
+; CHECK-LABEL-LE: @getvelss
+; CHECK-DAG-LE: li [[IMM4:[0-9]+]], 4
+; CHECK-DAG-LE: andc [[ANDC:[0-9]+]], [[IMM4]]
+; CHECK-DAG-LE: sldi [[MUL2:[0-9]+]], [[ANDC]], 1
+; CHECK-DAG-LE: lvsl [[SHMSK:[0-9]+]], 0, [[MUL2]]
+; CHECK-DAG-LE: vperm [[PERMD:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, [[SHMSK]]
+; CHECK-DAG-LE: mfvsrd [[MOV:[0-9]+]],
+; CHECK-DAG-LE: li [[IMM3:[0-9]+]], 3
+; CHECK-DAG-LE: and [[AND:[0-9]+]], [[IMM3]]
+; CHECK-DAG-LE: sldi [[SHL:[0-9]+]], [[AND]], 4
+; CHECK-DAG-LE: srd 3, [[MOV]], [[SHL]]
+; CHECK-DAG-LE: extsh 3, 3
+}
+
+; Function Attrs: nounwind
+define zeroext i16 @getvelus(<8 x i16> %vus, i32 signext %i) {
+entry:
+  %vus.addr = alloca <8 x i16>, align 16
+  %i.addr = alloca i32, align 4
+  store <8 x i16> %vus, <8 x i16>* %vus.addr, align 16
+  store i32 %i, i32* %i.addr, align 4
+  %0 = load <8 x i16>, <8 x i16>* %vus.addr, align 16
+  %1 = load i32, i32* %i.addr, align 4
+  %vecext = extractelement <8 x i16> %0, i32 %1
+  ret i16 %vecext
+; CHECK-LABEL: @getvelus
+; CHECK-DAG: andi. [[ANDI:[0-9]+]], {{[0-9]+}}, 4
+; CHECK-DAG: sldi [[MUL2:[0-9]+]], [[ANDI]], 1
+; CHECK-DAG: lvsl [[SHMSK:[0-9]+]], 0, [[MUL2]]
+; CHECK-DAG: vperm [[PERMD:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, [[SHMSK]]
+; CHECK-DAG: mfvsrd [[MOV:[0-9]+]],
+; CHECK-DAG: li [[IMM3:[0-9]+]], 3
+; CHECK-DAG: andc [[ANDC:[0-9]+]], [[IMM3]]
+; CHECK-DAG: rldicr [[SHL:[0-9]+]], [[ANDC]], 4, 60
+; CHECK-DAG: srd 3, [[MOV]], [[SHL]]
+; CHECK-DAG: clrldi   3, 3, 48
+; CHECK-LABEL-LE: @getvelus
+; CHECK-DAG-LE: li [[IMM4:[0-9]+]], 4
+; CHECK-DAG-LE: andc [[ANDC:[0-9]+]], [[IMM4]]
+; CHECK-DAG-LE: sldi [[MUL2:[0-9]+]], [[ANDC]], 1
+; CHECK-DAG-LE: lvsl [[SHMSK:[0-9]+]], 0, [[MUL2]]
+; CHECK-DAG-LE: vperm [[PERMD:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, [[SHMSK]]
+; CHECK-DAG-LE: mfvsrd [[MOV:[0-9]+]],
+; CHECK-DAG-LE: li [[IMM3:[0-9]+]], 3
+; CHECK-DAG-LE: and [[AND:[0-9]+]], [[IMM3]]
+; CHECK-DAG-LE: sldi [[SHL:[0-9]+]], [[AND]], 4
+; CHECK-DAG-LE: srd 3, [[MOV]], [[SHL]]
+; CHECK-DAG-LE: clrldi   3, 3, 48
+}
+
+; Function Attrs: nounwind
+define signext i32 @getsi0(<4 x i32> %vsi) {
+entry:
+  %vsi.addr = alloca <4 x i32>, align 16
+  store <4 x i32> %vsi, <4 x i32>* %vsi.addr, align 16
+  %0 = load <4 x i32>, <4 x i32>* %vsi.addr, align 16
+  %vecext = extractelement <4 x i32> %0, i32 0
+  ret i32 %vecext
+; CHECK-LABEL: @getsi0
+; CHECK: xxsldwi [[SHL:[0-9]+]], 34, 34, 3
+; CHECK: mfvsrwz 3, [[SHL]]
+; CHECK: extsw 3, 3
+; CHECK-LABEL-LE: @getsi0
+; CHECK-LE: xxsldwi [[SHL:[0-9]+]], 34, 34, 2
+; CHECK-LE: mfvsrwz 3, [[SHL]]
+; CHECK-LE: extsw 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i32 @getsi1(<4 x i32> %vsi) {
+entry:
+  %vsi.addr = alloca <4 x i32>, align 16
+  store <4 x i32> %vsi, <4 x i32>* %vsi.addr, align 16
+  %0 = load <4 x i32>, <4 x i32>* %vsi.addr, align 16
+  %vecext = extractelement <4 x i32> %0, i32 1
+  ret i32 %vecext
+; CHECK-LABEL: @getsi1
+; CHECK: mfvsrwz 3, 34
+; CHECK: extsw 3, 3
+; CHECK-LABEL-LE: @getsi1
+; CHECK-LE: xxsldwi [[SHL:[0-9]+]], 34, 34, 1
+; CHECK-LE: mfvsrwz 3, [[SHL]]
+; CHECK-LE: extsw 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i32 @getsi2(<4 x i32> %vsi) {
+entry:
+  %vsi.addr = alloca <4 x i32>, align 16
+  store <4 x i32> %vsi, <4 x i32>* %vsi.addr, align 16
+  %0 = load <4 x i32>, <4 x i32>* %vsi.addr, align 16
+  %vecext = extractelement <4 x i32> %0, i32 2
+  ret i32 %vecext
+; CHECK-LABEL: @getsi2
+; CHECK: xxsldwi [[SHL:[0-9]+]], 34, 34, 1
+; CHECK: mfvsrwz 3, [[SHL]]
+; CHECK: extsw 3, 3
+; CHECK-LABEL-LE: @getsi2
+; CHECK-LE: mfvsrwz 3, 34
+; CHECK-LE: extsw 3, 3
+}
+
+; Function Attrs: nounwind
+define signext i32 @getsi3(<4 x i32> %vsi) {
+entry:
+  %vsi.addr = alloca <4 x i32>, align 16
+  store <4 x i32> %vsi, <4 x i32>* %vsi.addr, align 16
+  %0 = load <4 x i32>, <4 x i32>* %vsi.addr, align 16
+  %vecext = extractelement <4 x i32> %0, i32 3
+  ret i32 %vecext
+; CHECK-LABEL: @getsi3
+; CHECK: xxsldwi [[SHL:[0-9]+]], 34, 34, 2
+; CHECK: mfvsrwz 3, [[SHL]]
+; CHECK: extsw 3, 3
+; CHECK-LABEL-LE: @getsi3
+; CHECK-LE: xxsldwi [[SHL:[0-9]+]], 34, 34, 3
+; CHECK-LE: mfvsrwz 3, [[SHL]]
+; CHECK-LE: extsw 3, 3
+}
+
+; Function Attrs: nounwind
+define zeroext i32 @getui0(<4 x i32> %vui) {
+entry:
+  %vui.addr = alloca <4 x i32>, align 16
+  store <4 x i32> %vui, <4 x i32>* %vui.addr, align 16
+  %0 = load <4 x i32>, <4 x i32>* %vui.addr, align 16
+  %vecext = extractelement <4 x i32> %0, i32 0
+  ret i32 %vecext
+; CHECK-LABEL: @getui0
+; CHECK: xxsldwi [[SHL:[0-9]+]], 34, 34, 3
+; CHECK: mfvsrwz 3, [[SHL]]
+; CHECK: clrldi   3, 3, 32
+; CHECK-LABEL-LE: @getui0
+; CHECK-LE: xxsldwi [[SHL:[0-9]+]], 34, 34, 2
+; CHECK-LE: mfvsrwz 3, [[SHL]]
+; CHECK-LE: clrldi   3, 3, 32
+}
+
+; Function Attrs: nounwind
+define zeroext i32 @getui1(<4 x i32> %vui) {
+entry:
+  %vui.addr = alloca <4 x i32>, align 16
+  store <4 x i32> %vui, <4 x i32>* %vui.addr, align 16
+  %0 = load <4 x i32>, <4 x i32>* %vui.addr, align 16
+  %vecext = extractelement <4 x i32> %0, i32 1
+  ret i32 %vecext
+; CHECK-LABEL: @getui1
+; CHECK: mfvsrwz 3, 34
+; CHECK: clrldi   3, 3, 32
+; CHECK-LABEL-LE: @getui1
+; CHECK-LE: xxsldwi [[SHL:[0-9]+]], 34, 34, 1
+; CHECK-LE: mfvsrwz 3, [[SHL]]
+; CHECK-LE: clrldi   3, 3, 32
+}
+
+; Function Attrs: nounwind
+define zeroext i32 @getui2(<4 x i32> %vui) {
+entry:
+  %vui.addr = alloca <4 x i32>, align 16
+  store <4 x i32> %vui, <4 x i32>* %vui.addr, align 16
+  %0 = load <4 x i32>, <4 x i32>* %vui.addr, align 16
+  %vecext = extractelement <4 x i32> %0, i32 2
+  ret i32 %vecext
+; CHECK-LABEL: @getui2
+; CHECK: xxsldwi [[SHL:[0-9]+]], 34, 34, 1
+; CHECK: mfvsrwz 3, [[SHL]]
+; CHECK: clrldi   3, 3, 32
+; CHECK-LABEL-LE: @getui2
+; CHECK-LE: mfvsrwz 3, 34
+; CHECK-LE: clrldi   3, 3, 32
+}
+
+; Function Attrs: nounwind
+define zeroext i32 @getui3(<4 x i32> %vui) {
+entry:
+  %vui.addr = alloca <4 x i32>, align 16
+  store <4 x i32> %vui, <4 x i32>* %vui.addr, align 16
+  %0 = load <4 x i32>, <4 x i32>* %vui.addr, align 16
+  %vecext = extractelement <4 x i32> %0, i32 3
+  ret i32 %vecext
+; CHECK-LABEL: @getui3
+; CHECK: xxsldwi [[SHL:[0-9]+]], 34, 34, 2
+; CHECK: mfvsrwz 3, [[SHL]]
+; CHECK: clrldi   3, 3, 32
+; CHECK-LABEL-LE: @getui3
+; CHECK-LE: xxsldwi [[SHL:[0-9]+]], 34, 34, 3
+; CHECK-LE: mfvsrwz 3, [[SHL]]
+; CHECK-LE: clrldi   3, 3, 32
+}
+
+; Function Attrs: nounwind
+define signext i32 @getvelsi(<4 x i32> %vsi, i32 signext %i) {
+entry:
+  %vsi.addr = alloca <4 x i32>, align 16
+  %i.addr = alloca i32, align 4
+  store <4 x i32> %vsi, <4 x i32>* %vsi.addr, align 16
+  store i32 %i, i32* %i.addr, align 4
+  %0 = load <4 x i32>, <4 x i32>* %vsi.addr, align 16
+  %1 = load i32, i32* %i.addr, align 4
+  %vecext = extractelement <4 x i32> %0, i32 %1
+  ret i32 %vecext
+; CHECK-LABEL: @getvelsi
+; CHECK-LABEL-LE: @getvelsi
+; FIXME: add check patterns when variable element extraction is implemented
+}
+
+; Function Attrs: nounwind
+define zeroext i32 @getvelui(<4 x i32> %vui, i32 signext %i) {
+entry:
+  %vui.addr = alloca <4 x i32>, align 16
+  %i.addr = alloca i32, align 4
+  store <4 x i32> %vui, <4 x i32>* %vui.addr, align 16
+  store i32 %i, i32* %i.addr, align 4
+  %0 = load <4 x i32>, <4 x i32>* %vui.addr, align 16
+  %1 = load i32, i32* %i.addr, align 4
+  %vecext = extractelement <4 x i32> %0, i32 %1
+  ret i32 %vecext
+; CHECK-LABEL: @getvelui
+; CHECK-LABEL-LE: @getvelui
+; FIXME: add check patterns when variable element extraction is implemented
+}
+
+; Function Attrs: nounwind
+define i64 @getsl0(<2 x i64> %vsl) {
+entry:
+  %vsl.addr = alloca <2 x i64>, align 16
+  store <2 x i64> %vsl, <2 x i64>* %vsl.addr, align 16
+  %0 = load <2 x i64>, <2 x i64>* %vsl.addr, align 16
+  %vecext = extractelement <2 x i64> %0, i32 0
+  ret i64 %vecext
+; CHECK-LABEL: @getsl0
+; CHECK: mfvsrd 3, 34
+; CHECK-LABEL-LE: @getsl0
+; CHECK-LE: xxswapd  [[SWP:[0-9]+]], 34
+; CHECK-LE: mfvsrd 3, [[SWP]]
+}
+
+; Function Attrs: nounwind
+define i64 @getsl1(<2 x i64> %vsl) {
+entry:
+  %vsl.addr = alloca <2 x i64>, align 16
+  store <2 x i64> %vsl, <2 x i64>* %vsl.addr, align 16
+  %0 = load <2 x i64>, <2 x i64>* %vsl.addr, align 16
+  %vecext = extractelement <2 x i64> %0, i32 1
+  ret i64 %vecext
+; CHECK-LABEL: @getsl1
+; CHECK: xxswapd  [[SWP:[0-9]+]], 34
+; CHECK: mfvsrd 3, [[SWP]]
+; CHECK-LABEL-LE: @getsl1
+; CHECK-LE: mfvsrd 3, 34
+}
+
+; Function Attrs: nounwind
+define i64 @getul0(<2 x i64> %vul) {
+entry:
+  %vul.addr = alloca <2 x i64>, align 16
+  store <2 x i64> %vul, <2 x i64>* %vul.addr, align 16
+  %0 = load <2 x i64>, <2 x i64>* %vul.addr, align 16
+  %vecext = extractelement <2 x i64> %0, i32 0
+  ret i64 %vecext
+; CHECK-LABEL: @getul0
+; CHECK: mfvsrd 3, 34
+; CHECK-LABEL-LE: @getul0
+; CHECK-LE: xxswapd  [[SWP:[0-9]+]], 34
+; CHECK-LE: mfvsrd 3, [[SWP]]
+}
+
+; Function Attrs: nounwind
+define i64 @getul1(<2 x i64> %vul) {
+entry:
+  %vul.addr = alloca <2 x i64>, align 16
+  store <2 x i64> %vul, <2 x i64>* %vul.addr, align 16
+  %0 = load <2 x i64>, <2 x i64>* %vul.addr, align 16
+  %vecext = extractelement <2 x i64> %0, i32 1
+  ret i64 %vecext
+; CHECK-LABEL: @getul1
+; CHECK: xxswapd  [[SWP:[0-9]+]], 34
+; CHECK: mfvsrd 3, [[SWP]]
+; CHECK-LABEL-LE: @getul1
+; CHECK-LE: mfvsrd 3, 34
+}
+
+; Function Attrs: nounwind
+define i64 @getvelsl(<2 x i64> %vsl, i32 signext %i) {
+entry:
+  %vsl.addr = alloca <2 x i64>, align 16
+  %i.addr = alloca i32, align 4
+  store <2 x i64> %vsl, <2 x i64>* %vsl.addr, align 16
+  store i32 %i, i32* %i.addr, align 4
+  %0 = load <2 x i64>, <2 x i64>* %vsl.addr, align 16
+  %1 = load i32, i32* %i.addr, align 4
+  %vecext = extractelement <2 x i64> %0, i32 %1
+  ret i64 %vecext
+; CHECK-LABEL: @getvelsl
+; CHECK-LABEL-LE: @getvelsl
+; FIXME: add check patterns when variable element extraction is implemented
+}
+
+; Function Attrs: nounwind
+define i64 @getvelul(<2 x i64> %vul, i32 signext %i) {
+entry:
+  %vul.addr = alloca <2 x i64>, align 16
+  %i.addr = alloca i32, align 4
+  store <2 x i64> %vul, <2 x i64>* %vul.addr, align 16
+  store i32 %i, i32* %i.addr, align 4
+  %0 = load <2 x i64>, <2 x i64>* %vul.addr, align 16
+  %1 = load i32, i32* %i.addr, align 4
+  %vecext = extractelement <2 x i64> %0, i32 %1
+  ret i64 %vecext
+; CHECK-LABEL: @getvelul
+; CHECK-LABEL-LE: @getvelul
+; FIXME: add check patterns when variable element extraction is implemented
+}
+
+; Function Attrs: nounwind
+define float @getf0(<4 x float> %vf) {
+entry:
+  %vf.addr = alloca <4 x float>, align 16
+  store <4 x float> %vf, <4 x float>* %vf.addr, align 16
+  %0 = load <4 x float>, <4 x float>* %vf.addr, align 16
+  %vecext = extractelement <4 x float> %0, i32 0
+  ret float %vecext
+; CHECK-LABEL: @getf0
+; CHECK: xscvspdpn 1, 34
+; CHECK-LABEL-LE: @getf0
+; CHECK-LE: xxsldwi [[SHL:[0-9]+]], 34, 34, 3
+; CHECK-LE: xscvspdpn 1, [[SHL]]
+}
+
+; Function Attrs: nounwind
+define float @getf1(<4 x float> %vf) {
+entry:
+  %vf.addr = alloca <4 x float>, align 16
+  store <4 x float> %vf, <4 x float>* %vf.addr, align 16
+  %0 = load <4 x float>, <4 x float>* %vf.addr, align 16
+  %vecext = extractelement <4 x float> %0, i32 1
+  ret float %vecext
+; CHECK-LABEL: @getf1
+; CHECK: xxsldwi [[SHL:[0-9]+]], 34, 34, 1
+; CHECK: xscvspdpn 1, [[SHL]]
+; CHECK-LABEL-LE: @getf1
+; CHECK-LE: xxsldwi [[SHL:[0-9]+]], 34, 34, 2
+; CHECK-LE: xscvspdpn 1, [[SHL]]
+}
+
+; Function Attrs: nounwind
+define float @getf2(<4 x float> %vf) {
+entry:
+  %vf.addr = alloca <4 x float>, align 16
+  store <4 x float> %vf, <4 x float>* %vf.addr, align 16
+  %0 = load <4 x float>, <4 x float>* %vf.addr, align 16
+  %vecext = extractelement <4 x float> %0, i32 2
+  ret float %vecext
+; CHECK-LABEL: @getf2
+; CHECK: xxsldwi [[SHL:[0-9]+]], 34, 34, 2
+; CHECK: xscvspdpn 1, [[SHL]]
+; CHECK-LABEL-LE: @getf2
+; CHECK-LE: xxsldwi [[SHL:[0-9]+]], 34, 34, 1
+; CHECK-LE: xscvspdpn 1, [[SHL]]
+}
+
+; Function Attrs: nounwind
+define float @getf3(<4 x float> %vf) {
+entry:
+  %vf.addr = alloca <4 x float>, align 16
+  store <4 x float> %vf, <4 x float>* %vf.addr, align 16
+  %0 = load <4 x float>, <4 x float>* %vf.addr, align 16
+  %vecext = extractelement <4 x float> %0, i32 3
+  ret float %vecext
+; CHECK-LABEL: @getf3
+; CHECK: xxsldwi [[SHL:[0-9]+]], 34, 34, 3
+; CHECK: xscvspdpn 1, [[SHL]]
+; CHECK-LABEL-LE: @getf3
+; CHECK-LE: xscvspdpn 1, 34
+}
+
+; Function Attrs: nounwind
+define float @getvelf(<4 x float> %vf, i32 signext %i) {
+entry:
+  %vf.addr = alloca <4 x float>, align 16
+  %i.addr = alloca i32, align 4
+  store <4 x float> %vf, <4 x float>* %vf.addr, align 16
+  store i32 %i, i32* %i.addr, align 4
+  %0 = load <4 x float>, <4 x float>* %vf.addr, align 16
+  %1 = load i32, i32* %i.addr, align 4
+  %vecext = extractelement <4 x float> %0, i32 %1
+  ret float %vecext
+; CHECK-LABEL: @getvelf
+; CHECK-LABEL-LE: @getvelf
+; FIXME: add check patterns when variable element extraction is implemented
+}
+
+; Function Attrs: nounwind
+define double @getd0(<2 x double> %vd) {
+entry:
+  %vd.addr = alloca <2 x double>, align 16
+  store <2 x double> %vd, <2 x double>* %vd.addr, align 16
+  %0 = load <2 x double>, <2 x double>* %vd.addr, align 16
+  %vecext = extractelement <2 x double> %0, i32 0
+  ret double %vecext
+; CHECK-LABEL: @getd0
+; CHECK: xxlor 1, 34, 34
+; CHECK-LABEL-LE: @getd0
+; CHECK-LE: xxswapd  1, 34
+}
+
+; Function Attrs: nounwind
+define double @getd1(<2 x double> %vd) {
+entry:
+  %vd.addr = alloca <2 x double>, align 16
+  store <2 x double> %vd, <2 x double>* %vd.addr, align 16
+  %0 = load <2 x double>, <2 x double>* %vd.addr, align 16
+  %vecext = extractelement <2 x double> %0, i32 1
+  ret double %vecext
+; CHECK-LABEL: @getd1
+; CHECK: xxswapd  1, 34
+; CHECK-LABEL-LE: @getd1
+; CHECK-LE: xxlor 1, 34, 34
+}
+
+; Function Attrs: nounwind
+define double @getveld(<2 x double> %vd, i32 signext %i) {
+entry:
+  %vd.addr = alloca <2 x double>, align 16
+  %i.addr = alloca i32, align 4
+  store <2 x double> %vd, <2 x double>* %vd.addr, align 16
+  store i32 %i, i32* %i.addr, align 4
+  %0 = load <2 x double>, <2 x double>* %vd.addr, align 16
+  %1 = load i32, i32* %i.addr, align 4
+  %vecext = extractelement <2 x double> %0, i32 %1
+  ret double %vecext
+; CHECK-LABEL: @getveld
+; CHECK-LABEL-LE: @getveld
+; FIXME: add check patterns when variable element extraction is implemented
+}