[PowerPC] Lower f128 SETCC/SELECT_CC as libcall if p9vector disabled

XSCMPUQP is not available for pre-P9 subtargets. This patch will lower
them into libcall for correct behavior on power7/power8.

Reviewed By: steven.zhang

Differential Revision: https://reviews.llvm.org/D92083

4 files changed, 313 insertions, 318 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp b/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
index 2eea380c49bd..fa95dc2e3fcc 100644
--- a/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp
@@ -3983,7 +3983,7 @@ SDValue PPCDAGToDAGISel::SelectCC(SDValue LHS, SDValue RHS, ISD::CondCode CC,
       Opc = Subtarget->hasVSX() ? PPC::XSCMPUDP : PPC::FCMPUD;
   } else {
     assert(LHS.getValueType() == MVT::f128 && "Unknown vt!");
-    assert(Subtarget->hasVSX() && "__float128 requires VSX");
+    assert(Subtarget->hasP9Vector() && "XSCMPUQP requires Power9 Vector");
     Opc = PPC::XSCMPUQP;
   }
   if (Chain)
diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 65ca0d81fc2a..30927bf88b7c 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -1219,6 +1219,19 @@ PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM,
         setOperationAction(ISD::FP_ROUND, VT, Custom);
         setOperationAction(ISD::STRICT_FP_ROUND, VT, Custom);
       }
+
+      setOperationAction(ISD::SETCC, MVT::f128, Custom);
+      setOperationAction(ISD::STRICT_FSETCC, MVT::f128, Custom);
+      setOperationAction(ISD::STRICT_FSETCCS, MVT::f128, Custom);
+      setOperationAction(ISD::BR_CC, MVT::f128, Expand);
+
+      // Lower following f128 select_cc pattern:
+      // select_cc x, y, tv, fv, cc -> select_cc (setcc x, y, cc), 0, tv, fv, NE
+      setOperationAction(ISD::SELECT_CC, MVT::f128, Custom);
+
+      // We need to handle f128 SELECT_CC with integer result type.
+      setOperationAction(ISD::SELECT_CC, MVT::i32, Custom);
+      setOperationAction(ISD::SELECT_CC, MVT::i64, Custom);
     }
 
     if (Subtarget.hasP9Altivec()) {
@@ -3330,21 +3343,43 @@ SDValue PPCTargetLowering::LowerGlobalAddress(SDValue Op,
 }
 
 SDValue PPCTargetLowering::LowerSETCC(SDValue Op, SelectionDAG &DAG) const {
-  ISD::CondCode CC = cast<CondCodeSDNode>(Op.getOperand(2))->get();
+  bool IsStrict = Op->isStrictFPOpcode();
+  ISD::CondCode CC =
+      cast<CondCodeSDNode>(Op.getOperand(IsStrict ? 3 : 2))->get();
+  SDValue LHS = Op.getOperand(IsStrict ? 1 : 0);
+  SDValue RHS = Op.getOperand(IsStrict ? 2 : 1);
+  SDValue Chain = IsStrict ? Op.getOperand(0) : SDValue();
+  EVT LHSVT = LHS.getValueType();
   SDLoc dl(Op);
 
+  // Soften the setcc with libcall if it is fp128.
+  if (LHSVT == MVT::f128) {
+    assert(!Subtarget.hasP9Vector() &&
+           "SETCC for f128 is already legal under Power9!");
+    softenSetCCOperands(DAG, LHSVT, LHS, RHS, CC, dl, LHS, RHS, Chain,
+                        Op->getOpcode() == ISD::STRICT_FSETCCS);
+    if (RHS.getNode())
+      LHS = DAG.getNode(ISD::SETCC, dl, Op.getValueType(), LHS, RHS,
+                        DAG.getCondCode(CC));
+    if (IsStrict)
+      return DAG.getMergeValues({LHS, Chain}, dl);
+    return LHS;
+  }
+
+  assert(!IsStrict && "Don't know how to handle STRICT_FSETCC!");
+
   if (Op.getValueType() == MVT::v2i64) {
     // When the operands themselves are v2i64 values, we need to do something
     // special because VSX has no underlying comparison operations for these.
-    if (Op.getOperand(0).getValueType() == MVT::v2i64) {
+    if (LHS.getValueType() == MVT::v2i64) {
       // Equality can be handled by casting to the legal type for Altivec
       // comparisons, everything else needs to be expanded.
       if (CC == ISD::SETEQ || CC == ISD::SETNE) {
-        return DAG.getNode(ISD::BITCAST, dl, MVT::v2i64,
-                 DAG.getSetCC(dl, MVT::v4i32,
-                   DAG.getNode(ISD::BITCAST, dl, MVT::v4i32, Op.getOperand(0)),
-                   DAG.getNode(ISD::BITCAST, dl, MVT::v4i32, Op.getOperand(1)),
-                   CC));
+        return DAG.getNode(
+            ISD::BITCAST, dl, MVT::v2i64,
+            DAG.getSetCC(dl, MVT::v4i32,
+                         DAG.getNode(ISD::BITCAST, dl, MVT::v4i32, LHS),
+                         DAG.getNode(ISD::BITCAST, dl, MVT::v4i32, RHS), CC));
       }
 
       return SDValue();
@@ -3360,7 +3395,7 @@ SDValue PPCTargetLowering::LowerSETCC(SDValue Op, SelectionDAG &DAG) const {
   if (SDValue V = lowerCmpEqZeroToCtlzSrl(Op, DAG))
     return V;
 
-  if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(Op.getOperand(1))) {
+  if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(RHS)) {
     // Leave comparisons against 0 and -1 alone for now, since they're usually
     // optimized.  FIXME: revisit this when we can custom lower all setcc
     // optimizations.
@@ -3373,11 +3408,9 @@ SDValue PPCTargetLowering::LowerSETCC(SDValue Op, SelectionDAG &DAG) const {
   // condition register, reading it back out, and masking the correct bit.  The
   // normal approach here uses sub to do this instead of xor.  Using xor exposes
   // the result to other bit-twiddling opportunities.
-  EVT LHSVT = Op.getOperand(0).getValueType();
   if (LHSVT.isInteger() && (CC == ISD::SETEQ || CC == ISD::SETNE)) {
     EVT VT = Op.getValueType();
-    SDValue Sub = DAG.getNode(ISD::XOR, dl, LHSVT, Op.getOperand(0),
-                                Op.getOperand(1));
+    SDValue Sub = DAG.getNode(ISD::XOR, dl, LHSVT, LHS, RHS);
     return DAG.getSetCC(dl, VT, Sub, DAG.getConstant(0, dl, LHSVT), CC);
   }
   return SDValue();
@@ -7607,18 +7640,29 @@ SDValue PPCTargetLowering::LowerTRUNCATEVector(SDValue Op,
 /// LowerSELECT_CC - Lower floating point select_cc's into fsel instruction when
 /// possible.
 SDValue PPCTargetLowering::LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const {
-  // Not FP, or using SPE? Not a fsel.
-  if (!Op.getOperand(0).getValueType().isFloatingPoint() ||
-      !Op.getOperand(2).getValueType().isFloatingPoint() || Subtarget.hasSPE())
-    return Op;
-
   ISD::CondCode CC = cast<CondCodeSDNode>(Op.getOperand(4))->get();
-
   EVT ResVT = Op.getValueType();
   EVT CmpVT = Op.getOperand(0).getValueType();
   SDValue LHS = Op.getOperand(0), RHS = Op.getOperand(1);
   SDValue TV  = Op.getOperand(2), FV  = Op.getOperand(3);
   SDLoc dl(Op);
+
+  // Without power9-vector, we don't have native instruction for f128 comparison.
+  // Following transformation to libcall is needed for setcc:
+  // select_cc lhs, rhs, tv, fv, cc -> select_cc (setcc cc, x, y), 0, tv, fv, NE
+  if (!Subtarget.hasP9Vector() && CmpVT == MVT::f128) {
+    SDValue Z = DAG.getSetCC(
+        dl, getSetCCResultType(DAG.getDataLayout(), *DAG.getContext(), CmpVT),
+        LHS, RHS, CC);
+    SDValue Zero = DAG.getConstant(0, dl, Z.getValueType());
+    return DAG.getSelectCC(dl, Z, Zero, TV, FV, ISD::SETNE);
+  }
+
+  // Not FP, or using SPE? Not a fsel.
+  if (!CmpVT.isFloatingPoint() || !TV.getValueType().isFloatingPoint() ||
+      Subtarget.hasSPE())
+    return Op;
+
   SDNodeFlags Flags = Op.getNode()->getFlags();
 
   // We have xsmaxcdp/xsmincdp which are OK to emit even in the
@@ -10581,6 +10625,8 @@ SDValue PPCTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   case ISD::GlobalAddress:      return LowerGlobalAddress(Op, DAG);
   case ISD::GlobalTLSAddress:   return LowerGlobalTLSAddress(Op, DAG);
   case ISD::JumpTable:          return LowerJumpTable(Op, DAG);
+  case ISD::STRICT_FSETCC:
+  case ISD::STRICT_FSETCCS:
   case ISD::SETCC:              return LowerSETCC(Op, DAG);
   case ISD::INIT_TRAMPOLINE:    return LowerINIT_TRAMPOLINE(Op, DAG);
   case ISD::ADJUST_TRAMPOLINE:  return LowerADJUST_TRAMPOLINE(Op, DAG);
diff --git a/llvm/test/CodeGen/PowerPC/f128-compare.ll b/llvm/test/CodeGen/PowerPC/f128-compare.ll
index 36b0720b5356..869b5182b3a8 100644
--- a/llvm/test/CodeGen/PowerPC/f128-compare.ll
+++ b/llvm/test/CodeGen/PowerPC/f128-compare.ll
@@ -2,7 +2,7 @@
 ; RUN: llc -mcpu=pwr9 -mtriple=powerpc64le-unknown-unknown -verify-machineinstrs \
 ; RUN:   -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | FileCheck %s
 ; RUN: llc -mcpu=pwr8 -mtriple=powerpc64le-unknown-unknown -verify-machineinstrs \
-; RUN:   -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | FileCheck %s \
+; RUN:   -enable-soft-fp128 -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr < %s | FileCheck %s \
 ; RUN:   -check-prefix=CHECK-P8
 
 @a_qp = common dso_local global fp128 0xL00000000000000000000000000000000, align 16
@@ -31,14 +31,12 @@ define dso_local signext i32 @greater_qp() {
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
 ; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r5, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    addi r6, r5, a_qp@toc@l
-; CHECK-P8-NEXT:    addi r7, r4, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r3, a_qp@toc@l(r5)
-; CHECK-P8-NEXT:    ld r5, b_qp@toc@l(r4)
-; CHECK-P8-NEXT:    ld r4, 8(r6)
-; CHECK-P8-NEXT:    ld r6, 8(r7)
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    lvx v2, 0, r3
+; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    bl __gtkf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    extsw r3, r3
@@ -79,14 +77,12 @@ define dso_local signext i32 @less_qp() {
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
 ; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r5, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    addi r6, r5, a_qp@toc@l
-; CHECK-P8-NEXT:    addi r7, r4, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r3, a_qp@toc@l(r5)
-; CHECK-P8-NEXT:    ld r5, b_qp@toc@l(r4)
-; CHECK-P8-NEXT:    ld r4, 8(r6)
-; CHECK-P8-NEXT:    ld r6, 8(r7)
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    lvx v2, 0, r3
+; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    bl __ltkf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    rlwinm r3, r3, 1, 31, 31
@@ -125,14 +121,12 @@ define dso_local signext i32 @greater_eq_qp() {
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
 ; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r5, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    addi r6, r5, a_qp@toc@l
-; CHECK-P8-NEXT:    addi r7, r4, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r3, a_qp@toc@l(r5)
-; CHECK-P8-NEXT:    ld r5, b_qp@toc@l(r4)
-; CHECK-P8-NEXT:    ld r4, 8(r6)
-; CHECK-P8-NEXT:    ld r6, 8(r7)
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    lvx v2, 0, r3
+; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    bl __gekf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    rlwinm r3, r3, 1, 31, 31
@@ -172,14 +166,12 @@ define dso_local signext i32 @less_eq_qp() {
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
 ; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r5, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    addi r6, r5, a_qp@toc@l
-; CHECK-P8-NEXT:    addi r7, r4, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r3, a_qp@toc@l(r5)
-; CHECK-P8-NEXT:    ld r5, b_qp@toc@l(r4)
-; CHECK-P8-NEXT:    ld r4, 8(r6)
-; CHECK-P8-NEXT:    ld r6, 8(r7)
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    lvx v2, 0, r3
+; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    bl __lekf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    extsw r3, r3
@@ -221,14 +213,12 @@ define dso_local signext i32 @equal_qp() {
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
 ; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r5, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    addi r6, r5, a_qp@toc@l
-; CHECK-P8-NEXT:    addi r7, r4, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r3, a_qp@toc@l(r5)
-; CHECK-P8-NEXT:    ld r5, b_qp@toc@l(r4)
-; CHECK-P8-NEXT:    ld r4, 8(r6)
-; CHECK-P8-NEXT:    ld r6, 8(r7)
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    lvx v2, 0, r3
+; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    bl __eqkf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    cntlzw r3, r3
@@ -267,14 +257,12 @@ define dso_local signext i32 @not_greater_qp() {
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
 ; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r5, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    addi r6, r5, a_qp@toc@l
-; CHECK-P8-NEXT:    addi r7, r4, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r3, a_qp@toc@l(r5)
-; CHECK-P8-NEXT:    ld r5, b_qp@toc@l(r4)
-; CHECK-P8-NEXT:    ld r4, 8(r6)
-; CHECK-P8-NEXT:    ld r6, 8(r7)
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    lvx v2, 0, r3
+; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    bl __gtkf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    extsw r3, r3
@@ -316,14 +304,12 @@ define dso_local signext i32 @not_less_qp() {
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
 ; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r5, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    addi r6, r5, a_qp@toc@l
-; CHECK-P8-NEXT:    addi r7, r4, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r3, a_qp@toc@l(r5)
-; CHECK-P8-NEXT:    ld r5, b_qp@toc@l(r4)
-; CHECK-P8-NEXT:    ld r4, 8(r6)
-; CHECK-P8-NEXT:    ld r6, 8(r7)
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    lvx v2, 0, r3
+; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    bl __ltkf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    rlwinm r3, r3, 1, 31, 31
@@ -364,14 +350,12 @@ define dso_local signext i32 @not_greater_eq_qp() {
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
 ; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r5, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    addi r6, r5, a_qp@toc@l
-; CHECK-P8-NEXT:    addi r7, r4, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r3, a_qp@toc@l(r5)
-; CHECK-P8-NEXT:    ld r5, b_qp@toc@l(r4)
-; CHECK-P8-NEXT:    ld r4, 8(r6)
-; CHECK-P8-NEXT:    ld r6, 8(r7)
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    lvx v2, 0, r3
+; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    bl __gekf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    rlwinm r3, r3, 1, 31, 31
@@ -411,14 +395,12 @@ define dso_local signext i32 @not_less_eq_qp() {
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
 ; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r5, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    addi r6, r5, a_qp@toc@l
-; CHECK-P8-NEXT:    addi r7, r4, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r3, a_qp@toc@l(r5)
-; CHECK-P8-NEXT:    ld r5, b_qp@toc@l(r4)
-; CHECK-P8-NEXT:    ld r4, 8(r6)
-; CHECK-P8-NEXT:    ld r6, 8(r7)
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    lvx v2, 0, r3
+; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    bl __lekf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    extsw r3, r3
@@ -459,14 +441,12 @@ define dso_local signext i32 @not_equal_qp() {
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
 ; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r5, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    addi r6, r5, a_qp@toc@l
-; CHECK-P8-NEXT:    addi r7, r4, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r3, a_qp@toc@l(r5)
-; CHECK-P8-NEXT:    ld r5, b_qp@toc@l(r4)
-; CHECK-P8-NEXT:    ld r4, 8(r6)
-; CHECK-P8-NEXT:    ld r6, 8(r7)
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    lvx v2, 0, r3
+; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    bl __nekf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    cntlzw r3, r3
@@ -503,41 +483,38 @@ define fp128 @greater_sel_qp() {
 ; CHECK-P8-LABEL: greater_sel_qp:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
-; CHECK-P8-NEXT:    .cfi_def_cfa_offset 80
-; CHECK-P8-NEXT:    .cfi_offset lr, 16
-; CHECK-P8-NEXT:    .cfi_offset r27, -40
-; CHECK-P8-NEXT:    .cfi_offset r28, -32
-; CHECK-P8-NEXT:    .cfi_offset r29, -24
-; CHECK-P8-NEXT:    .cfi_offset r30, -16
-; CHECK-P8-NEXT:    std r27, -40(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r28, -32(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r29, -24(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -80(r1)
-; CHECK-P8-NEXT:    addis r3, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r4, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    ld r30, a_qp@toc@l(r4)
-; CHECK-P8-NEXT:    addi r4, r4, a_qp@toc@l
-; CHECK-P8-NEXT:    ld r29, b_qp@toc@l(r3)
-; CHECK-P8-NEXT:    addi r3, r3, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r28, 8(r4)
-; CHECK-P8-NEXT:    ld r27, 8(r3)
-; CHECK-P8-NEXT:    mr r3, r30
-; CHECK-P8-NEXT:    mr r5, r29
-; CHECK-P8-NEXT:    mr r4, r28
-; CHECK-P8-NEXT:    mr r6, r27
+; CHECK-P8-NEXT:    .cfi_def_cfa_offset 80
+; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    .cfi_offset v30, -32
+; CHECK-P8-NEXT:    .cfi_offset v31, -16
+; CHECK-P8-NEXT:    li r3, 48
+; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
+; CHECK-P8-NEXT:    stvx v30, r1, r3 # 16-byte Folded Spill
+; CHECK-P8-NEXT:    li r3, 64
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    stvx v31, r1, r3 # 16-byte Folded Spill
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
+; CHECK-P8-NEXT:    lvx v30, 0, r4
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    lvx v31, 0, r3
+; CHECK-P8-NEXT:    vmr v3, v30
+; CHECK-P8-NEXT:    vmr v2, v31
 ; CHECK-P8-NEXT:    bl __gtkf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    cmpwi r3, 0
-; CHECK-P8-NEXT:    iselgt r3, r30, r29
-; CHECK-P8-NEXT:    iselgt r4, r28, r27
+; CHECK-P8-NEXT:    bgt cr0, .LBB10_2
+; CHECK-P8-NEXT:  # %bb.1: # %entry
+; CHECK-P8-NEXT:    vmr v31, v30
+; CHECK-P8-NEXT:  .LBB10_2: # %entry
+; CHECK-P8-NEXT:    li r3, 64
+; CHECK-P8-NEXT:    vmr v2, v31
+; CHECK-P8-NEXT:    lvx v31, r1, r3 # 16-byte Folded Reload
+; CHECK-P8-NEXT:    li r3, 48
+; CHECK-P8-NEXT:    lvx v30, r1, r3 # 16-byte Folded Reload
 ; CHECK-P8-NEXT:    addi r1, r1, 80
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
-; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r28, -32(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r27, -40(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:
@@ -567,41 +544,38 @@ define fp128 @less_sel_qp() {
 ; CHECK-P8-LABEL: less_sel_qp:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
-; CHECK-P8-NEXT:    .cfi_def_cfa_offset 80
-; CHECK-P8-NEXT:    .cfi_offset lr, 16
-; CHECK-P8-NEXT:    .cfi_offset r27, -40
-; CHECK-P8-NEXT:    .cfi_offset r28, -32
-; CHECK-P8-NEXT:    .cfi_offset r29, -24
-; CHECK-P8-NEXT:    .cfi_offset r30, -16
-; CHECK-P8-NEXT:    std r27, -40(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r28, -32(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r29, -24(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -80(r1)
-; CHECK-P8-NEXT:    addis r3, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r4, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    ld r30, a_qp@toc@l(r4)
-; CHECK-P8-NEXT:    addi r4, r4, a_qp@toc@l
-; CHECK-P8-NEXT:    ld r29, b_qp@toc@l(r3)
-; CHECK-P8-NEXT:    addi r3, r3, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r28, 8(r4)
-; CHECK-P8-NEXT:    ld r27, 8(r3)
-; CHECK-P8-NEXT:    mr r3, r30
-; CHECK-P8-NEXT:    mr r5, r29
-; CHECK-P8-NEXT:    mr r4, r28
-; CHECK-P8-NEXT:    mr r6, r27
+; CHECK-P8-NEXT:    .cfi_def_cfa_offset 80
+; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    .cfi_offset v30, -32
+; CHECK-P8-NEXT:    .cfi_offset v31, -16
+; CHECK-P8-NEXT:    li r3, 48
+; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
+; CHECK-P8-NEXT:    stvx v30, r1, r3 # 16-byte Folded Spill
+; CHECK-P8-NEXT:    li r3, 64
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    stvx v31, r1, r3 # 16-byte Folded Spill
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
+; CHECK-P8-NEXT:    lvx v30, 0, r4
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    lvx v31, 0, r3
+; CHECK-P8-NEXT:    vmr v3, v30
+; CHECK-P8-NEXT:    vmr v2, v31
 ; CHECK-P8-NEXT:    bl __ltkf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    cmpwi r3, 0
-; CHECK-P8-NEXT:    isellt r3, r30, r29
-; CHECK-P8-NEXT:    isellt r4, r28, r27
+; CHECK-P8-NEXT:    blt cr0, .LBB11_2
+; CHECK-P8-NEXT:  # %bb.1: # %entry
+; CHECK-P8-NEXT:    vmr v31, v30
+; CHECK-P8-NEXT:  .LBB11_2: # %entry
+; CHECK-P8-NEXT:    li r3, 64
+; CHECK-P8-NEXT:    vmr v2, v31
+; CHECK-P8-NEXT:    lvx v31, r1, r3 # 16-byte Folded Reload
+; CHECK-P8-NEXT:    li r3, 48
+; CHECK-P8-NEXT:    lvx v30, r1, r3 # 16-byte Folded Reload
 ; CHECK-P8-NEXT:    addi r1, r1, 80
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
-; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r28, -32(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r27, -40(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:
@@ -632,41 +606,38 @@ define fp128 @greater_eq_sel_qp() {
 ; CHECK-P8-LABEL: greater_eq_sel_qp:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
-; CHECK-P8-NEXT:    .cfi_def_cfa_offset 80
-; CHECK-P8-NEXT:    .cfi_offset lr, 16
-; CHECK-P8-NEXT:    .cfi_offset r27, -40
-; CHECK-P8-NEXT:    .cfi_offset r28, -32
-; CHECK-P8-NEXT:    .cfi_offset r29, -24
-; CHECK-P8-NEXT:    .cfi_offset r30, -16
-; CHECK-P8-NEXT:    std r27, -40(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r28, -32(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r29, -24(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -80(r1)
-; CHECK-P8-NEXT:    addis r3, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r4, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    ld r30, a_qp@toc@l(r4)
-; CHECK-P8-NEXT:    addi r4, r4, a_qp@toc@l
-; CHECK-P8-NEXT:    ld r29, b_qp@toc@l(r3)
-; CHECK-P8-NEXT:    addi r3, r3, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r28, 8(r4)
-; CHECK-P8-NEXT:    ld r27, 8(r3)
-; CHECK-P8-NEXT:    mr r3, r30
-; CHECK-P8-NEXT:    mr r5, r29
-; CHECK-P8-NEXT:    mr r4, r28
-; CHECK-P8-NEXT:    mr r6, r27
+; CHECK-P8-NEXT:    .cfi_def_cfa_offset 80
+; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    .cfi_offset v30, -32
+; CHECK-P8-NEXT:    .cfi_offset v31, -16
+; CHECK-P8-NEXT:    li r3, 48
+; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
+; CHECK-P8-NEXT:    stvx v30, r1, r3 # 16-byte Folded Spill
+; CHECK-P8-NEXT:    li r3, 64
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    stvx v31, r1, r3 # 16-byte Folded Spill
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
+; CHECK-P8-NEXT:    lvx v30, 0, r4
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    lvx v31, 0, r3
+; CHECK-P8-NEXT:    vmr v3, v30
+; CHECK-P8-NEXT:    vmr v2, v31
 ; CHECK-P8-NEXT:    bl __gekf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    cmpwi r3, -1
-; CHECK-P8-NEXT:    iselgt r3, r30, r29
-; CHECK-P8-NEXT:    iselgt r4, r28, r27
+; CHECK-P8-NEXT:    bgt cr0, .LBB12_2
+; CHECK-P8-NEXT:  # %bb.1: # %entry
+; CHECK-P8-NEXT:    vmr v31, v30
+; CHECK-P8-NEXT:  .LBB12_2: # %entry
+; CHECK-P8-NEXT:    li r3, 64
+; CHECK-P8-NEXT:    vmr v2, v31
+; CHECK-P8-NEXT:    lvx v31, r1, r3 # 16-byte Folded Reload
+; CHECK-P8-NEXT:    li r3, 48
+; CHECK-P8-NEXT:    lvx v30, r1, r3 # 16-byte Folded Reload
 ; CHECK-P8-NEXT:    addi r1, r1, 80
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
-; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r28, -32(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r27, -40(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:
@@ -697,41 +668,38 @@ define fp128 @less_eq_sel_qp() {
 ; CHECK-P8-LABEL: less_eq_sel_qp:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
-; CHECK-P8-NEXT:    .cfi_def_cfa_offset 80
-; CHECK-P8-NEXT:    .cfi_offset lr, 16
-; CHECK-P8-NEXT:    .cfi_offset r27, -40
-; CHECK-P8-NEXT:    .cfi_offset r28, -32
-; CHECK-P8-NEXT:    .cfi_offset r29, -24
-; CHECK-P8-NEXT:    .cfi_offset r30, -16
-; CHECK-P8-NEXT:    std r27, -40(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r28, -32(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r29, -24(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -80(r1)
-; CHECK-P8-NEXT:    addis r3, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r4, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    ld r30, a_qp@toc@l(r4)
-; CHECK-P8-NEXT:    addi r4, r4, a_qp@toc@l
-; CHECK-P8-NEXT:    ld r29, b_qp@toc@l(r3)
-; CHECK-P8-NEXT:    addi r3, r3, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r28, 8(r4)
-; CHECK-P8-NEXT:    ld r27, 8(r3)
-; CHECK-P8-NEXT:    mr r3, r30
-; CHECK-P8-NEXT:    mr r5, r29
-; CHECK-P8-NEXT:    mr r4, r28
-; CHECK-P8-NEXT:    mr r6, r27
+; CHECK-P8-NEXT:    .cfi_def_cfa_offset 80
+; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    .cfi_offset v30, -32
+; CHECK-P8-NEXT:    .cfi_offset v31, -16
+; CHECK-P8-NEXT:    li r3, 48
+; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
+; CHECK-P8-NEXT:    stvx v30, r1, r3 # 16-byte Folded Spill
+; CHECK-P8-NEXT:    li r3, 64
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    stvx v31, r1, r3 # 16-byte Folded Spill
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
+; CHECK-P8-NEXT:    lvx v30, 0, r4
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    lvx v31, 0, r3
+; CHECK-P8-NEXT:    vmr v3, v30
+; CHECK-P8-NEXT:    vmr v2, v31
 ; CHECK-P8-NEXT:    bl __lekf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    cmpwi r3, 1
-; CHECK-P8-NEXT:    isellt r3, r30, r29
-; CHECK-P8-NEXT:    isellt r4, r28, r27
+; CHECK-P8-NEXT:    blt cr0, .LBB13_2
+; CHECK-P8-NEXT:  # %bb.1: # %entry
+; CHECK-P8-NEXT:    vmr v31, v30
+; CHECK-P8-NEXT:  .LBB13_2: # %entry
+; CHECK-P8-NEXT:    li r3, 64
+; CHECK-P8-NEXT:    vmr v2, v31
+; CHECK-P8-NEXT:    lvx v31, r1, r3 # 16-byte Folded Reload
+; CHECK-P8-NEXT:    li r3, 48
+; CHECK-P8-NEXT:    lvx v30, r1, r3 # 16-byte Folded Reload
 ; CHECK-P8-NEXT:    addi r1, r1, 80
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
-; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r28, -32(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r27, -40(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:
@@ -761,41 +729,38 @@ define fp128 @equal_sel_qp() {
 ; CHECK-P8-LABEL: equal_sel_qp:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
-; CHECK-P8-NEXT:    .cfi_def_cfa_offset 80
-; CHECK-P8-NEXT:    .cfi_offset lr, 16
-; CHECK-P8-NEXT:    .cfi_offset r27, -40
-; CHECK-P8-NEXT:    .cfi_offset r28, -32
-; CHECK-P8-NEXT:    .cfi_offset r29, -24
-; CHECK-P8-NEXT:    .cfi_offset r30, -16
-; CHECK-P8-NEXT:    std r27, -40(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r28, -32(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r29, -24(r1) # 8-byte Folded Spill
-; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -80(r1)
-; CHECK-P8-NEXT:    addis r3, r2, b_qp@toc@ha
-; CHECK-P8-NEXT:    addis r4, r2, a_qp@toc@ha
-; CHECK-P8-NEXT:    ld r30, a_qp@toc@l(r4)
-; CHECK-P8-NEXT:    addi r4, r4, a_qp@toc@l
-; CHECK-P8-NEXT:    ld r29, b_qp@toc@l(r3)
-; CHECK-P8-NEXT:    addi r3, r3, b_qp@toc@l
-; CHECK-P8-NEXT:    ld r28, 8(r4)
-; CHECK-P8-NEXT:    ld r27, 8(r3)
-; CHECK-P8-NEXT:    mr r3, r30
-; CHECK-P8-NEXT:    mr r5, r29
-; CHECK-P8-NEXT:    mr r4, r28
-; CHECK-P8-NEXT:    mr r6, r27
+; CHECK-P8-NEXT:    .cfi_def_cfa_offset 80
+; CHECK-P8-NEXT:    .cfi_offset lr, 16
+; CHECK-P8-NEXT:    .cfi_offset v30, -32
+; CHECK-P8-NEXT:    .cfi_offset v31, -16
+; CHECK-P8-NEXT:    li r3, 48
+; CHECK-P8-NEXT:    addis r4, r2, b_qp@toc@ha
+; CHECK-P8-NEXT:    stvx v30, r1, r3 # 16-byte Folded Spill
+; CHECK-P8-NEXT:    li r3, 64
+; CHECK-P8-NEXT:    addi r4, r4, b_qp@toc@l
+; CHECK-P8-NEXT:    stvx v31, r1, r3 # 16-byte Folded Spill
+; CHECK-P8-NEXT:    addis r3, r2, a_qp@toc@ha
+; CHECK-P8-NEXT:    lvx v30, 0, r4
+; CHECK-P8-NEXT:    addi r3, r3, a_qp@toc@l
+; CHECK-P8-NEXT:    lvx v31, 0, r3
+; CHECK-P8-NEXT:    vmr v3, v30
+; CHECK-P8-NEXT:    vmr v2, v31
 ; CHECK-P8-NEXT:    bl __eqkf2
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    cmplwi r3, 0
-; CHECK-P8-NEXT:    iseleq r3, r30, r29
-; CHECK-P8-NEXT:    iseleq r4, r28, r27
+; CHECK-P8-NEXT:    beq cr0, .LBB14_2
+; CHECK-P8-NEXT:  # %bb.1: # %entry
+; CHECK-P8-NEXT:    vmr v31, v30
+; CHECK-P8-NEXT:  .LBB14_2: # %entry
+; CHECK-P8-NEXT:    li r3, 64
+; CHECK-P8-NEXT:    vmr v2, v31
+; CHECK-P8-NEXT:    lvx v31, r1, r3 # 16-byte Folded Reload
+; CHECK-P8-NEXT:    li r3, 48
+; CHECK-P8-NEXT:    lvx v30, r1, r3 # 16-byte Folded Reload
 ; CHECK-P8-NEXT:    addi r1, r1, 80
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
-; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r28, -32(r1) # 8-byte Folded Reload
-; CHECK-P8-NEXT:    ld r27, -40(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:
diff --git a/llvm/test/CodeGen/PowerPC/fp-strict-fcmp.ll b/llvm/test/CodeGen/PowerPC/fp-strict-fcmp.ll
index ea28d84fd47d..ad32202ba905 100644
--- a/llvm/test/CodeGen/PowerPC/fp-strict-fcmp.ll
+++ b/llvm/test/CodeGen/PowerPC/fp-strict-fcmp.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -verify-machineinstrs -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
-; RUN:   < %s -mtriple=powerpc64-unknown-linux -mcpu=pwr8 | FileCheck %s \
+; RUN:   < %s -enable-soft-fp128 -mtriple=powerpc64-unknown-linux -mcpu=pwr8 | FileCheck %s \
 ; RUN:   -check-prefix=P8
 ; RUN: llc -verify-machineinstrs -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
 ; RUN:   < %s -mtriple=powerpc64le-unknown-linux -mcpu=pwr9 \
@@ -1701,36 +1701,32 @@ define i32 @fcmp_one_f128(fp128 %a, fp128 %b) #0 {
 ; P8:       # %bb.0:
 ; P8-NEXT:    mflr r0
 ; P8-NEXT:    std r0, 16(r1)
-; P8-NEXT:    stdu r1, -160(r1)
-; P8-NEXT:    std r26, 112(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r27, 120(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r28, 128(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r29, 136(r1) # 8-byte Folded Spill
-; P8-NEXT:    mr r29, r5
-; P8-NEXT:    mr r28, r4
-; P8-NEXT:    mr r27, r3
-; P8-NEXT:    std r30, 144(r1) # 8-byte Folded Spill
-; P8-NEXT:    mr r30, r6
+; P8-NEXT:    stdu r1, -176(r1)
+; P8-NEXT:    li r3, 128
+; P8-NEXT:    std r30, 160(r1) # 8-byte Folded Spill
+; P8-NEXT:    stxvd2x v30, r1, r3 # 16-byte Folded Spill
+; P8-NEXT:    li r3, 144
+; P8-NEXT:    vmr v30, v2
+; P8-NEXT:    stxvd2x v31, r1, r3 # 16-byte Folded Spill
+; P8-NEXT:    vmr v31, v3
 ; P8-NEXT:    bl __unordkf2
 ; P8-NEXT:    nop
+; P8-NEXT:    vmr v2, v30
 ; P8-NEXT:    cntlzw r3, r3
-; P8-NEXT:    mr r4, r28
-; P8-NEXT:    mr r5, r29
-; P8-NEXT:    mr r6, r30
-; P8-NEXT:    srwi r26, r3, 5
-; P8-NEXT:    mr r3, r27
+; P8-NEXT:    vmr v3, v31
+; P8-NEXT:    srwi r30, r3, 5
 ; P8-NEXT:    bl __eqkf2
 ; P8-NEXT:    nop
 ; P8-NEXT:    cntlzw r3, r3
-; P8-NEXT:    ld r30, 144(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r29, 136(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r28, 128(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r27, 120(r1) # 8-byte Folded Reload
+; P8-NEXT:    li r4, 144
 ; P8-NEXT:    srwi r3, r3, 5
+; P8-NEXT:    lxvd2x v31, r1, r4 # 16-byte Folded Reload
+; P8-NEXT:    li r4, 128
 ; P8-NEXT:    xori r3, r3, 1
-; P8-NEXT:    and r3, r26, r3
-; P8-NEXT:    ld r26, 112(r1) # 8-byte Folded Reload
-; P8-NEXT:    addi r1, r1, 160
+; P8-NEXT:    lxvd2x v30, r1, r4 # 16-byte Folded Reload
+; P8-NEXT:    and r3, r30, r3
+; P8-NEXT:    ld r30, 160(r1) # 8-byte Folded Reload
+; P8-NEXT:    addi r1, r1, 176
 ; P8-NEXT:    ld r0, 16(r1)
 ; P8-NEXT:    mtlr r0
 ; P8-NEXT:    blr
@@ -1959,36 +1955,32 @@ define i32 @fcmp_ueq_f128(fp128 %a, fp128 %b) #0 {
 ; P8:       # %bb.0:
 ; P8-NEXT:    mflr r0
 ; P8-NEXT:    std r0, 16(r1)
-; P8-NEXT:    stdu r1, -160(r1)
-; P8-NEXT:    std r26, 112(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r27, 120(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r28, 128(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r29, 136(r1) # 8-byte Folded Spill
-; P8-NEXT:    mr r29, r5
-; P8-NEXT:    mr r28, r4
-; P8-NEXT:    mr r27, r3
-; P8-NEXT:    std r30, 144(r1) # 8-byte Folded Spill
-; P8-NEXT:    mr r30, r6
+; P8-NEXT:    stdu r1, -176(r1)
+; P8-NEXT:    li r3, 128
+; P8-NEXT:    std r30, 160(r1) # 8-byte Folded Spill
+; P8-NEXT:    stxvd2x v30, r1, r3 # 16-byte Folded Spill
+; P8-NEXT:    li r3, 144
+; P8-NEXT:    vmr v30, v2
+; P8-NEXT:    stxvd2x v31, r1, r3 # 16-byte Folded Spill
+; P8-NEXT:    vmr v31, v3
 ; P8-NEXT:    bl __eqkf2
 ; P8-NEXT:    nop
+; P8-NEXT:    vmr v2, v30
 ; P8-NEXT:    cntlzw r3, r3
-; P8-NEXT:    mr r4, r28
-; P8-NEXT:    mr r5, r29
-; P8-NEXT:    mr r6, r30
-; P8-NEXT:    srwi r26, r3, 5
-; P8-NEXT:    mr r3, r27
+; P8-NEXT:    vmr v3, v31
+; P8-NEXT:    srwi r30, r3, 5
 ; P8-NEXT:    bl __unordkf2
 ; P8-NEXT:    nop
 ; P8-NEXT:    cntlzw r3, r3
-; P8-NEXT:    ld r30, 144(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r29, 136(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r28, 128(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r27, 120(r1) # 8-byte Folded Reload
+; P8-NEXT:    li r4, 144
 ; P8-NEXT:    srwi r3, r3, 5
+; P8-NEXT:    lxvd2x v31, r1, r4 # 16-byte Folded Reload
+; P8-NEXT:    li r4, 128
 ; P8-NEXT:    xori r3, r3, 1
-; P8-NEXT:    or r3, r3, r26
-; P8-NEXT:    ld r26, 112(r1) # 8-byte Folded Reload
-; P8-NEXT:    addi r1, r1, 160
+; P8-NEXT:    lxvd2x v30, r1, r4 # 16-byte Folded Reload
+; P8-NEXT:    or r3, r3, r30
+; P8-NEXT:    ld r30, 160(r1) # 8-byte Folded Reload
+; P8-NEXT:    addi r1, r1, 176
 ; P8-NEXT:    ld r0, 16(r1)
 ; P8-NEXT:    mtlr r0
 ; P8-NEXT:    blr
@@ -2305,36 +2297,32 @@ define i32 @fcmps_one_f128(fp128 %a, fp128 %b) #0 {
 ; P8:       # %bb.0:
 ; P8-NEXT:    mflr r0
 ; P8-NEXT:    std r0, 16(r1)
-; P8-NEXT:    stdu r1, -160(r1)
-; P8-NEXT:    std r26, 112(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r27, 120(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r28, 128(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r29, 136(r1) # 8-byte Folded Spill
-; P8-NEXT:    mr r29, r5
-; P8-NEXT:    mr r28, r4
-; P8-NEXT:    mr r27, r3
-; P8-NEXT:    std r30, 144(r1) # 8-byte Folded Spill
-; P8-NEXT:    mr r30, r6
+; P8-NEXT:    stdu r1, -176(r1)
+; P8-NEXT:    li r3, 128
+; P8-NEXT:    std r30, 160(r1) # 8-byte Folded Spill
+; P8-NEXT:    stxvd2x v30, r1, r3 # 16-byte Folded Spill
+; P8-NEXT:    li r3, 144
+; P8-NEXT:    vmr v30, v2
+; P8-NEXT:    stxvd2x v31, r1, r3 # 16-byte Folded Spill
+; P8-NEXT:    vmr v31, v3
 ; P8-NEXT:    bl __unordkf2
 ; P8-NEXT:    nop
+; P8-NEXT:    vmr v2, v30
 ; P8-NEXT:    cntlzw r3, r3
-; P8-NEXT:    mr r4, r28
-; P8-NEXT:    mr r5, r29
-; P8-NEXT:    mr r6, r30
-; P8-NEXT:    srwi r26, r3, 5
-; P8-NEXT:    mr r3, r27
+; P8-NEXT:    vmr v3, v31
+; P8-NEXT:    srwi r30, r3, 5
 ; P8-NEXT:    bl __eqkf2
 ; P8-NEXT:    nop
 ; P8-NEXT:    cntlzw r3, r3
-; P8-NEXT:    ld r30, 144(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r29, 136(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r28, 128(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r27, 120(r1) # 8-byte Folded Reload
+; P8-NEXT:    li r4, 144
 ; P8-NEXT:    srwi r3, r3, 5
+; P8-NEXT:    lxvd2x v31, r1, r4 # 16-byte Folded Reload
+; P8-NEXT:    li r4, 128
 ; P8-NEXT:    xori r3, r3, 1
-; P8-NEXT:    and r3, r26, r3
-; P8-NEXT:    ld r26, 112(r1) # 8-byte Folded Reload
-; P8-NEXT:    addi r1, r1, 160
+; P8-NEXT:    lxvd2x v30, r1, r4 # 16-byte Folded Reload
+; P8-NEXT:    and r3, r30, r3
+; P8-NEXT:    ld r30, 160(r1) # 8-byte Folded Reload
+; P8-NEXT:    addi r1, r1, 176
 ; P8-NEXT:    ld r0, 16(r1)
 ; P8-NEXT:    mtlr r0
 ; P8-NEXT:    blr
@@ -2563,36 +2551,32 @@ define i32 @fcmps_ueq_f128(fp128 %a, fp128 %b) #0 {
 ; P8:       # %bb.0:
 ; P8-NEXT:    mflr r0
 ; P8-NEXT:    std r0, 16(r1)
-; P8-NEXT:    stdu r1, -160(r1)
-; P8-NEXT:    std r26, 112(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r27, 120(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r28, 128(r1) # 8-byte Folded Spill
-; P8-NEXT:    std r29, 136(r1) # 8-byte Folded Spill
-; P8-NEXT:    mr r29, r5
-; P8-NEXT:    mr r28, r4
-; P8-NEXT:    mr r27, r3
-; P8-NEXT:    std r30, 144(r1) # 8-byte Folded Spill
-; P8-NEXT:    mr r30, r6
+; P8-NEXT:    stdu r1, -176(r1)
+; P8-NEXT:    li r3, 128
+; P8-NEXT:    std r30, 160(r1) # 8-byte Folded Spill
+; P8-NEXT:    stxvd2x v30, r1, r3 # 16-byte Folded Spill
+; P8-NEXT:    li r3, 144
+; P8-NEXT:    vmr v30, v2
+; P8-NEXT:    stxvd2x v31, r1, r3 # 16-byte Folded Spill
+; P8-NEXT:    vmr v31, v3
 ; P8-NEXT:    bl __eqkf2
 ; P8-NEXT:    nop
+; P8-NEXT:    vmr v2, v30
 ; P8-NEXT:    cntlzw r3, r3
-; P8-NEXT:    mr r4, r28
-; P8-NEXT:    mr r5, r29
-; P8-NEXT:    mr r6, r30
-; P8-NEXT:    srwi r26, r3, 5
-; P8-NEXT:    mr r3, r27
+; P8-NEXT:    vmr v3, v31
+; P8-NEXT:    srwi r30, r3, 5
 ; P8-NEXT:    bl __unordkf2
 ; P8-NEXT:    nop
 ; P8-NEXT:    cntlzw r3, r3
-; P8-NEXT:    ld r30, 144(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r29, 136(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r28, 128(r1) # 8-byte Folded Reload
-; P8-NEXT:    ld r27, 120(r1) # 8-byte Folded Reload
+; P8-NEXT:    li r4, 144
 ; P8-NEXT:    srwi r3, r3, 5
+; P8-NEXT:    lxvd2x v31, r1, r4 # 16-byte Folded Reload
+; P8-NEXT:    li r4, 128
 ; P8-NEXT:    xori r3, r3, 1
-; P8-NEXT:    or r3, r3, r26
-; P8-NEXT:    ld r26, 112(r1) # 8-byte Folded Reload
-; P8-NEXT:    addi r1, r1, 160
+; P8-NEXT:    lxvd2x v30, r1, r4 # 16-byte Folded Reload
+; P8-NEXT:    or r3, r3, r30
+; P8-NEXT:    ld r30, 160(r1) # 8-byte Folded Reload
+; P8-NEXT:    addi r1, r1, 176
 ; P8-NEXT:    ld r0, 16(r1)
 ; P8-NEXT:    mtlr r0
 ; P8-NEXT:    blr