diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -1252,7 +1252,6 @@
         setOperationAction(ISD::INSERT_VECTOR_ELT, MVT::v8i16, Legal);
         setOperationAction(ISD::INSERT_VECTOR_ELT, MVT::v16i8, Legal);
         setOperationAction(ISD::INSERT_VECTOR_ELT, MVT::v4i32, Legal);
-        setOperationAction(ISD::INSERT_VECTOR_ELT, MVT::v4f32, Legal);
       } else {
         setOperationAction(ISD::INSERT_VECTOR_ELT, MVT::v8i16, Custom);
         setOperationAction(ISD::INSERT_VECTOR_ELT, MVT::v16i8, Custom);
@@ -10754,6 +10753,24 @@
   if (VT == MVT::v2f64 && C)
     return Op;
 
+  if (Subtarget.hasP9Vector()) {
+    // A f32 load feeding into a v4f32 insert_vector_elt is handled in this way
+    // because on P10, it allows this specific insert_vector_elt load pattern to
+    // utilize the refactored load and store infrastructure in order to exploit
+    // prefixed loads.
+    // Additionally, on Power9, this enables utilizing direct moves (which are
+    // cheaper than the alternative sequence).
+    if ((VT == MVT::v4f32) && (V2.getValueType() == MVT::f32) &&
+        (isa<LoadSDNode>(V2))) {
+      SDValue BitcastVector = DAG.getBitcast(MVT::v4i32, V1);
+      SDValue BitcastLoad = DAG.getBitcast(MVT::i32, V2);
+      SDValue InsVecElt =
+        DAG.getNode(ISD::INSERT_VECTOR_ELT, dl, MVT::v4i32, BitcastVector,
+                    BitcastLoad, Op.getOperand(2));
+      return DAG.getBitcast(MVT::v4f32, InsVecElt);
+    }
+  }
+
   if (Subtarget.isISA3_1()) {
     if ((VT == MVT::v2i64 || VT == MVT::v2f64) && !Subtarget.isPPC64())
       return SDValue();
diff --git a/llvm/lib/Target/PowerPC/PPCInstrPrefix.td b/llvm/lib/Target/PowerPC/PPCInstrPrefix.td
--- a/llvm/lib/Target/PowerPC/PPCInstrPrefix.td
+++ b/llvm/lib/Target/PowerPC/PPCInstrPrefix.td
@@ -2814,31 +2814,27 @@
 
   def : Pat<(v4f32 (insertelt v4f32:$vDi, f32:$rA, i64:$rB)),
             (VINSWVRX $vDi, InsertEltShift.Sub32Left2, (XSCVDPSPN $rA))>;
-  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load iaddr:$rA)), i64:$rB)),
-            (VINSWRX $vDi, InsertEltShift.Sub32Left2, (LWZ memri:$rA))>;
-  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load iaddrX34:$rA)), i64:$rB)),
+  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load PDForm:$rA)), i64:$rB)),
             (VINSWRX $vDi, InsertEltShift.Sub32Left2, (PLWZ memri34:$rA))>;
-  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load xaddr:$rA)), i64:$rB)),
+  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load XForm:$rA)), i64:$rB)),
             (VINSWRX $vDi, InsertEltShift.Sub32Left2, (LWZX memrr:$rA))>;
 
   def : Pat<(v2f64 (insertelt v2f64:$vDi,  f64:$A, i64:$rB)),
             (VINSDRX $vDi, InsertEltShift.Left3, Bitcast.DblToLong)>;
-  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load iaddrX4:$rA)), i64:$rB)),
+  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load DSForm:$rA)), i64:$rB)),
             (VINSDRX $vDi, InsertEltShift.Left3, (LD memrix:$rA))>;
-  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load iaddrX34:$rA)), i64:$rB)),
+  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load PDForm:$rA)), i64:$rB)),
             (VINSDRX $vDi, InsertEltShift.Left3, (PLD memri34:$rA))>;
-  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load xaddrX4:$rA)), i64:$rB)),
+  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load XForm:$rA)), i64:$rB)),
             (VINSDRX $vDi, InsertEltShift.Left3, (LDX memrr:$rA))>;
   let AddedComplexity = 400 in {
     // Immediate vector insert element
     foreach Idx = [0, 1, 2, 3] in {
       def : Pat<(v4i32 (insertelt v4i32:$vDi, i32:$rA, Idx)),
                 (VINSW $vDi, !mul(!sub(3, Idx), 4), $rA)>;
-      def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load iaddr:$rA)), Idx)),
-                (VINSW $vDi, !mul(!sub(3, Idx), 4), (LWZ memri:$rA))>;
-      def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load iaddrX34:$rA)), Idx)),
+      def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load PDForm:$rA)), Idx)),
                 (VINSW $vDi, !mul(!sub(3, Idx), 4), (PLWZ memri34:$rA))>;
-      def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load xaddr:$rA)), Idx)),
+      def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load XForm:$rA)), Idx)),
                 (VINSW $vDi, !mul(!sub(3, Idx), 4), (LWZX memrr:$rA))>;
     }
     foreach i = [0, 1] in
@@ -2858,11 +2854,9 @@
 
   def : Pat<(v4f32 (insertelt v4f32:$vDi,  f32:$rA, i32:$rB)),
             (VINSWVLX $vDi, InsertEltShift.Left2, (XSCVDPSPN $rA))>;
-  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load iaddr:$rA)), i32:$rB)),
-            (VINSWLX v4f32:$vDi, InsertEltShift.Left2, (LWZ memri:$rA))>;
-  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load iaddrX34:$rA)), i32:$rB)),
+  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load PDForm:$rA)), i32:$rB)),
             (VINSWLX v4f32:$vDi, InsertEltShift.Left2, (PLWZ memri34:$rA))>;
-  def: Pat<(v4f32(insertelt v4f32 : $vDi, (f32(load xaddr : $rA)), i32 : $rB)),
+  def: Pat<(v4f32(insertelt v4f32 : $vDi, (f32(load XForm : $rA)), i32 : $rB)),
            (VINSWLX v4f32 : $vDi, InsertEltShift.Left2, (LWZX memrr : $rA))>;
 }
 
@@ -2879,20 +2873,18 @@
 
   def : Pat<(v4f32 (insertelt v4f32:$vDi,  f32:$rA, i64:$rB)),
             (VINSWVLX $vDi, InsertEltShift.Sub32Left2, (XSCVDPSPN $rA))>;
-  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load iaddr:$rA)), i64:$rB)),
-            (VINSWLX $vDi, InsertEltShift.Sub32Left2, (LWZ memri:$rA))>;
-  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load iaddrX34:$rA)), i64:$rB)),
+  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load PDForm:$rA)), i64:$rB)),
             (VINSWLX $vDi, InsertEltShift.Sub32Left2, (PLWZ memri34:$rA))>;
-  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load xaddr:$rA)), i64:$rB)),
+  def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load XForm:$rA)), i64:$rB)),
             (VINSWLX $vDi, InsertEltShift.Sub32Left2, (LWZX memrr:$rA))>;
 
   def : Pat<(v2f64 (insertelt v2f64:$vDi,  f64:$A, i64:$rB)),
             (VINSDLX $vDi, InsertEltShift.Left3, Bitcast.DblToLong)>;
-  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load iaddrX4:$rA)), i64:$rB)),
+  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load DSForm:$rA)), i64:$rB)),
             (VINSDLX $vDi, InsertEltShift.Left3, (LD memrix:$rA))>;
-  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load iaddrX34:$rA)), i64:$rB)),
+  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load PDForm:$rA)), i64:$rB)),
             (VINSDLX $vDi, InsertEltShift.Left3, (PLD memri34:$rA))>;
-  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load xaddrX4:$rA)), i64:$rB)),
+  def : Pat<(v2f64 (insertelt v2f64:$vDi, (f64 (load XForm:$rA)), i64:$rB)),
             (VINSDLX $vDi, InsertEltShift.Left3, (LDX memrr:$rA))>;
 }
 
@@ -2902,13 +2894,10 @@
     foreach Idx = [0, 1, 2, 3] in {
       def : Pat<(v4i32 (insertelt v4i32:$vDi, i32:$rA, (Ty Idx))),
                (VINSW $vDi, !mul(Idx, 4), $rA)>;
-      def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load iaddr:$rA)),
-                                  (Ty Idx))),
-               (VINSW $vDi, !mul(Idx, 4), (LWZ memri:$rA))>;
-      def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load iaddrX34:$rA)),
+      def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load PDForm:$rA)),
                                   (Ty Idx))),
                (VINSW $vDi, !mul(Idx, 4), (PLWZ memri34:$rA))>;
-      def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load xaddr:$rA)),
+      def : Pat<(v4f32 (insertelt v4f32:$vDi, (f32 (load XForm:$rA)),
                                   (Ty Idx))),
                (VINSW $vDi, !mul(Idx, 4), (LWZX memrr:$rA))>;
     }
diff --git a/llvm/test/CodeGen/PowerPC/aix-vec_insert_elt.ll b/llvm/test/CodeGen/PowerPC/aix-vec_insert_elt.ll
--- a/llvm/test/CodeGen/PowerPC/aix-vec_insert_elt.ll
+++ b/llvm/test/CodeGen/PowerPC/aix-vec_insert_elt.ll
@@ -306,32 +306,32 @@
 ; CHECK-64:       # %bb.0: # %entry
 ; CHECK-64-NEXT:    lwz 6, 0(3)
 ; CHECK-64-DAG:     rlwinm 4, 4, 2, 28, 29
-; CHECK-64-DAG:     addi 7, 1, -32
-; CHECK-64-NEXT:    stxv 34, -32(1)
+; CHECK-64-DAG:     addi 7, 1, -16
+; CHECK-64-NEXT:    stxv 34, -16(1)
 ; CHECK-64-NEXT:    stwx 6, 7, 4
 ; CHECK-64-NEXT:    rlwinm 4, 5, 2, 28, 29
-; CHECK-64-NEXT:    addi 5, 1, -16
-; CHECK-64-NEXT:    lxv 0, -32(1)
+; CHECK-64-NEXT:    addi 5, 1, -32
+; CHECK-64-NEXT:    lxv 0, -16(1)
 ; CHECK-64-NEXT:    lwz 3, 1(3)
-; CHECK-64-NEXT:    stxv 0, -16(1)
+; CHECK-64-NEXT:    stxv 0, -32(1)
 ; CHECK-64-NEXT:    stwx 3, 5, 4
-; CHECK-64-NEXT:    lxv 34, -16(1)
+; CHECK-64-NEXT:    lxv 34, -32(1)
 ; CHECK-64-NEXT:    blr
 ;
 ; CHECK-32-LABEL: testFloat2:
 ; CHECK-32:       # %bb.0: # %entry
 ; CHECK-32-NEXT:    lwz 6, 0(3)
-; CHECK-32-NEXT:    addi 7, 1, -32
+; CHECK-32-NEXT:    addi 7, 1, -16
 ; CHECK-32-NEXT:    rlwinm 4, 4, 2, 28, 29
-; CHECK-32-NEXT:    stxv 34, -32(1)
+; CHECK-32-NEXT:    stxv 34, -16(1)
 ; CHECK-32-NEXT:    rlwinm 5, 5, 2, 28, 29
 ; CHECK-32-NEXT:    stwx 6, 7, 4
-; CHECK-32-NEXT:    addi 4, 1, -16
-; CHECK-32-NEXT:    lxv 0, -32(1)
+; CHECK-32-NEXT:    addi 4, 1, -48
+; CHECK-32-NEXT:    lxv 0, -16(1)
 ; CHECK-32-NEXT:    lwz 3, 1(3)
-; CHECK-32-NEXT:    stxv 0, -16(1)
+; CHECK-32-NEXT:    stxv 0, -48(1)
 ; CHECK-32-NEXT:    stwx 3, 4, 5
-; CHECK-32-NEXT:    lxv 34, -16(1)
+; CHECK-32-NEXT:    lxv 34, -48(1)
 ; CHECK-32-NEXT:    blr
 ;
 ; CHECK-64-P10-LABEL: testFloat2:
@@ -371,36 +371,36 @@
 ; CHECK-64:       # %bb.0: # %entry
 ; CHECK-64-NEXT:    lis 6, 1
 ; CHECK-64-DAG:         rlwinm 4, 4, 2, 28, 29
-; CHECK-64-DAG:    addi 7, 1, -32
+; CHECK-64-DAG:    addi 7, 1, -16
 ; CHECK-64-NEXT:    lwzx 6, 3, 6
-; CHECK-64-NEXT:    stxv 34, -32(1)
+; CHECK-64-NEXT:    stxv 34, -16(1)
 ; CHECK-64-NEXT:    stwx 6, 7, 4
 ; CHECK-64-NEXT:    li 4, 1
-; CHECK-64-NEXT:    lxv 0, -32(1)
+; CHECK-64-NEXT:    lxv 0, -16(1)
 ; CHECK-64-NEXT:    rldic 4, 4, 36, 27
 ; CHECK-64-NEXT:    lwzx 3, 3, 4
 ; CHECK-64-NEXT:    rlwinm 4, 5, 2, 28, 29
-; CHECK-64-NEXT:    addi 5, 1, -16
-; CHECK-64-NEXT:    stxv 0, -16(1)
+; CHECK-64-NEXT:    addi 5, 1, -32
+; CHECK-64-NEXT:    stxv 0, -32(1)
 ; CHECK-64-NEXT:    stwx 3, 5, 4
-; CHECK-64-NEXT:    lxv 34, -16(1)
+; CHECK-64-NEXT:    lxv 34, -32(1)
 ; CHECK-64-NEXT:    blr
 ;
 ; CHECK-32-LABEL: testFloat3:
 ; CHECK-32:       # %bb.0: # %entry
 ; CHECK-32-NEXT:    lis 6, 1
-; CHECK-32-NEXT:    addi 7, 1, -32
+; CHECK-32-NEXT:    addi 7, 1, -16
 ; CHECK-32-NEXT:    rlwinm 4, 4, 2, 28, 29
 ; CHECK-32-NEXT:    rlwinm 5, 5, 2, 28, 29
 ; CHECK-32-NEXT:    lwzx 6, 3, 6
-; CHECK-32-NEXT:    stxv 34, -32(1)
+; CHECK-32-NEXT:    stxv 34, -16(1)
 ; CHECK-32-NEXT:    stwx 6, 7, 4
-; CHECK-32-NEXT:    addi 4, 1, -16
-; CHECK-32-NEXT:    lxv 0, -32(1)
+; CHECK-32-NEXT:    addi 4, 1, -48
+; CHECK-32-NEXT:    lxv 0, -16(1)
 ; CHECK-32-NEXT:    lwz 3, 0(3)
-; CHECK-32-NEXT:    stxv 0, -16(1)
+; CHECK-32-NEXT:    stxv 0, -48(1)
 ; CHECK-32-NEXT:    stwx 3, 4, 5
-; CHECK-32-NEXT:    lxv 34, -16(1)
+; CHECK-32-NEXT:    lxv 34, -48(1)
 ; CHECK-32-NEXT:    blr
 ;
 ; CHECK-64-P10-LABEL: testFloat3:
@@ -419,10 +419,9 @@
 ;
 ; CHECK-32-P10-LABEL: testFloat3:
 ; CHECK-32-P10:       # %bb.0: # %entry
-; CHECK-32-P10-NEXT:    lis 6, 1
-; CHECK-32-P10-NEXT:    slwi 4, 4, 2
-; CHECK-32-P10-NEXT:    lwzx 6, 3, 6
+; CHECK-32-P10-NEXT:    plwz 6, 65536(3), 0
 ; CHECK-32-P10-NEXT:    lwz 3, 0(3)
+; CHECK-32-P10-NEXT:    slwi 4, 4, 2
 ; CHECK-32-P10-NEXT:    vinswlx 2, 4, 6
 ; CHECK-32-P10-NEXT:    slwi 4, 5, 2
 ; CHECK-32-P10-NEXT:    vinswlx 2, 4, 3
@@ -478,21 +477,21 @@
 define <4 x float> @testFloatImm2(<4 x float> %a, i32* %b) {
 ; CHECK-64-LABEL: testFloatImm2:
 ; CHECK-64:       # %bb.0: # %entry
-; CHECK-64-NEXT:    lfs 0, 0(3)
-; CHECK-64-NEXT:    xscvdpspn 0, 0
+; CHECK-64-NEXT:    lwz 4, 0(3)
+; CHECK-64-NEXT:    lwz 3, 4(3)
+; CHECK-64-NEXT:    mtfprwz 0, 4
 ; CHECK-64-NEXT:    xxinsertw 34, 0, 0
-; CHECK-64-NEXT:    lfs 0, 4(3)
-; CHECK-64-NEXT:    xscvdpspn 0, 0
+; CHECK-64-NEXT:    mtfprwz 0, 3
 ; CHECK-64-NEXT:    xxinsertw 34, 0, 8
 ; CHECK-64-NEXT:    blr
 ;
 ; CHECK-32-LABEL: testFloatImm2:
 ; CHECK-32:       # %bb.0: # %entry
-; CHECK-32-NEXT:    lfs 0, 0(3)
-; CHECK-32-NEXT:    xscvdpspn 0, 0
+; CHECK-32-NEXT:    lwz 4, 0(3)
+; CHECK-32-NEXT:    lwz 3, 4(3)
+; CHECK-32-NEXT:    mtfprwz 0, 4
 ; CHECK-32-NEXT:    xxinsertw 34, 0, 0
-; CHECK-32-NEXT:    lfs 0, 4(3)
-; CHECK-32-NEXT:    xscvdpspn 0, 0
+; CHECK-32-NEXT:    mtfprwz 0, 3
 ; CHECK-32-NEXT:    xxinsertw 34, 0, 8
 ; CHECK-32-NEXT:    blr
 ;
@@ -526,24 +525,24 @@
 ; CHECK-64-LABEL: testFloatImm3:
 ; CHECK-64:       # %bb.0: # %entry
 ; CHECK-64-NEXT:    lis 4, 4
-; CHECK-64-NEXT:    lfsx 0, 3, 4
+; CHECK-64-NEXT:    lwzx 4, 3, 4
+; CHECK-64-NEXT:    mtfprwz 0, 4
 ; CHECK-64-NEXT:    li 4, 1
 ; CHECK-64-NEXT:    rldic 4, 4, 38, 25
-; CHECK-64-NEXT:    xscvdpspn 0, 0
 ; CHECK-64-NEXT:    xxinsertw 34, 0, 0
-; CHECK-64-NEXT:    lfsx 0, 3, 4
-; CHECK-64-NEXT:    xscvdpspn 0, 0
+; CHECK-64-NEXT:    lwzx 3, 3, 4
+; CHECK-64-NEXT:    mtfprwz 0, 3
 ; CHECK-64-NEXT:    xxinsertw 34, 0, 8
 ; CHECK-64-NEXT:    blr
 ;
 ; CHECK-32-LABEL: testFloatImm3:
 ; CHECK-32:       # %bb.0: # %entry
 ; CHECK-32-NEXT:    lis 4, 4
-; CHECK-32-NEXT:    lfsx 0, 3, 4
-; CHECK-32-NEXT:    xscvdpspn 0, 0
+; CHECK-32-NEXT:    lwzx 4, 3, 4
+; CHECK-32-NEXT:    lwz 3, 0(3)
+; CHECK-32-NEXT:    mtfprwz 0, 4
 ; CHECK-32-NEXT:    xxinsertw 34, 0, 0
-; CHECK-32-NEXT:    lfs 0, 0(3)
-; CHECK-32-NEXT:    xscvdpspn 0, 0
+; CHECK-32-NEXT:    mtfprwz 0, 3
 ; CHECK-32-NEXT:    xxinsertw 34, 0, 8
 ; CHECK-32-NEXT:    blr
 ;
@@ -559,8 +558,7 @@
 ;
 ; CHECK-32-P10-LABEL: testFloatImm3:
 ; CHECK-32-P10:       # %bb.0: # %entry
-; CHECK-32-P10-NEXT:    lis 4, 4
-; CHECK-32-P10-NEXT:    lwzx 4, 3, 4
+; CHECK-32-P10-NEXT:    plwz 4, 262144(3), 0
 ; CHECK-32-P10-NEXT:    lwz 3, 0(3)
 ; CHECK-32-P10-NEXT:    vinsw 2, 4, 0
 ; CHECK-32-P10-NEXT:    vinsw 2, 3, 8
diff --git a/llvm/test/CodeGen/PowerPC/scalar_vector_test_4.ll b/llvm/test/CodeGen/PowerPC/scalar_vector_test_4.ll
--- a/llvm/test/CodeGen/PowerPC/scalar_vector_test_4.ll
+++ b/llvm/test/CodeGen/PowerPC/scalar_vector_test_4.ll
@@ -214,15 +214,15 @@
 define <4 x float> @s2v_test_f1(float* nocapture readonly %f64, <4 x float> %vec)  {
 ; P9LE-LABEL: s2v_test_f1:
 ; P9LE:       # %bb.0: # %entry
-; P9LE-NEXT:    lfs f0, 0(r3)
-; P9LE-NEXT:    xscvdpspn vs0, f0
+; P9LE-NEXT:    lwz r3, 0(r3)
+; P9LE-NEXT:    mtfprwz f0, r3
 ; P9LE-NEXT:    xxinsertw v2, vs0, 12
 ; P9LE-NEXT:    blr
 ;
 ; P9BE-LABEL: s2v_test_f1:
 ; P9BE:       # %bb.0: # %entry
-; P9BE-NEXT:    lfs f0, 0(r3)
-; P9BE-NEXT:    xscvdpspn vs0, f0
+; P9BE-NEXT:    lwz r3, 0(r3)
+; P9BE-NEXT:    mtfprwz f0, r3
 ; P9BE-NEXT:    xxinsertw v2, vs0, 0
 ; P9BE-NEXT:    blr
 ;
diff --git a/llvm/test/CodeGen/PowerPC/vec_insert_elt.ll b/llvm/test/CodeGen/PowerPC/vec_insert_elt.ll
--- a/llvm/test/CodeGen/PowerPC/vec_insert_elt.ll
+++ b/llvm/test/CodeGen/PowerPC/vec_insert_elt.ll
@@ -255,16 +255,16 @@
 ; CHECK-P9:       # %bb.0: # %entry
 ; CHECK-P9-NEXT:    lwz r3, 0(r5)
 ; CHECK-P9-NEXT:    rlwinm r4, r6, 2, 28, 29
-; CHECK-P9-NEXT:    addi r6, r1, -32
-; CHECK-P9-NEXT:    stxv v2, -32(r1)
+; CHECK-P9-NEXT:    addi r6, r1, -16
+; CHECK-P9-NEXT:    stxv v2, -16(r1)
 ; CHECK-P9-NEXT:    stwx r3, r6, r4
 ; CHECK-P9-NEXT:    rlwinm r4, r7, 2, 28, 29
-; CHECK-P9-NEXT:    lxv vs0, -32(r1)
+; CHECK-P9-NEXT:    lxv vs0, -16(r1)
 ; CHECK-P9-NEXT:    lwz r3, 1(r5)
-; CHECK-P9-NEXT:    addi r5, r1, -16
-; CHECK-P9-NEXT:    stxv vs0, -16(r1)
+; CHECK-P9-NEXT:    addi r5, r1, -32
+; CHECK-P9-NEXT:    stxv vs0, -32(r1)
 ; CHECK-P9-NEXT:    stwx r3, r5, r4
-; CHECK-P9-NEXT:    lxv v2, -16(r1)
+; CHECK-P9-NEXT:    lxv v2, -32(r1)
 ; CHECK-P9-NEXT:    blr
 entry:
   %0 = bitcast i8* %b to float*
@@ -310,19 +310,19 @@
 ; CHECK-P9:       # %bb.0: # %entry
 ; CHECK-P9-NEXT:    lis r3, 1
 ; CHECK-P9-NEXT:    rlwinm r4, r6, 2, 28, 29
-; CHECK-P9-NEXT:    addi r6, r1, -32
+; CHECK-P9-NEXT:    addi r6, r1, -16
 ; CHECK-P9-NEXT:    lwzx r3, r5, r3
-; CHECK-P9-NEXT:    stxv v2, -32(r1)
+; CHECK-P9-NEXT:    stxv v2, -16(r1)
 ; CHECK-P9-NEXT:    stwx r3, r6, r4
 ; CHECK-P9-NEXT:    li r3, 1
 ; CHECK-P9-NEXT:    rlwinm r4, r7, 2, 28, 29
-; CHECK-P9-NEXT:    lxv vs0, -32(r1)
+; CHECK-P9-NEXT:    lxv vs0, -16(r1)
 ; CHECK-P9-NEXT:    rldic r3, r3, 36, 27
 ; CHECK-P9-NEXT:    lwzx r3, r5, r3
-; CHECK-P9-NEXT:    addi r5, r1, -16
-; CHECK-P9-NEXT:    stxv vs0, -16(r1)
+; CHECK-P9-NEXT:    addi r5, r1, -32
+; CHECK-P9-NEXT:    stxv vs0, -32(r1)
 ; CHECK-P9-NEXT:    stwx r3, r5, r4
-; CHECK-P9-NEXT:    lxv v2, -16(r1)
+; CHECK-P9-NEXT:    lxv v2, -32(r1)
 ; CHECK-P9-NEXT:    blr
 entry:
   %add.ptr = getelementptr inbounds i8, i8* %b, i64 65536
@@ -384,11 +384,11 @@
 ;
 ; CHECK-P9-LABEL: testFloatImm2:
 ; CHECK-P9:       # %bb.0: # %entry
-; CHECK-P9-NEXT:    lfs f0, 0(r5)
-; CHECK-P9-NEXT:    xscvdpspn vs0, f0
+; CHECK-P9-NEXT:    lwz r3, 0(r5)
+; CHECK-P9-NEXT:    mtfprwz f0, r3
+; CHECK-P9-NEXT:    lwz r3, 4(r5)
 ; CHECK-P9-NEXT:    xxinsertw v2, vs0, 0
-; CHECK-P9-NEXT:    lfs f0, 4(r5)
-; CHECK-P9-NEXT:    xscvdpspn vs0, f0
+; CHECK-P9-NEXT:    mtfprwz f0, r3
 ; CHECK-P9-NEXT:    xxinsertw v2, vs0, 8
 ; CHECK-P9-NEXT:    blr
 entry:
@@ -426,13 +426,13 @@
 ; CHECK-P9-LABEL: testFloatImm3:
 ; CHECK-P9:       # %bb.0: # %entry
 ; CHECK-P9-NEXT:    lis r3, 4
-; CHECK-P9-NEXT:    lfsx f0, r5, r3
+; CHECK-P9-NEXT:    lwzx r3, r5, r3
+; CHECK-P9-NEXT:    mtfprwz f0, r3
 ; CHECK-P9-NEXT:    li r3, 1
 ; CHECK-P9-NEXT:    rldic r3, r3, 38, 25
-; CHECK-P9-NEXT:    xscvdpspn vs0, f0
 ; CHECK-P9-NEXT:    xxinsertw v2, vs0, 0
-; CHECK-P9-NEXT:    lfsx f0, r5, r3
-; CHECK-P9-NEXT:    xscvdpspn vs0, f0
+; CHECK-P9-NEXT:    lwzx r3, r5, r3
+; CHECK-P9-NEXT:    mtfprwz f0, r3
 ; CHECK-P9-NEXT:    xxinsertw v2, vs0, 8
 ; CHECK-P9-NEXT:    blr
 entry: