[PowerPC] - Legalize vector types by widening instead of integer promotion

This patch corresponds to review:
http://reviews.llvm.org/D20443

It changes the legalization strategy for illegal vector types from integer
promotion to widening. This only applies for vectors with elements of width
that is a multiple of a byte since we have hardware support for vectors with
1, 2, 3, 8 and 16 byte elements.
Integer promotion for vectors is quite expensive on PPC due to the sequence
of breaking apart the vector, extending the elements and reconstituting the
vector. Two of these operations are expensive.
This patch causes between minor and major improvements in performance on most
benchmarks. There are very few benchmarks whose performance regresses. These
regressions can be handled in a subsequent patch with a DAG combine (similar
to how this patch handles int -> fp conversions of illegal vector types).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@274535 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/PowerPC/PPCISelLowering.cpp b/lib/Target/PowerPC/PPCISelLowering.cpp
index 2c4e1901ef2d176ad6872eb661d10a0f83df3350..8da29396b7102f521277c0286349b1647cb24bd5 100644 (file)
--- a/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -851,6 +851,7 @@ PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM,
 
   // We have target-specific dag combine patterns for the following nodes:
   setTargetDAGCombine(ISD::SINT_TO_FP);
+  setTargetDAGCombine(ISD::BUILD_VECTOR);
   if (Subtarget.hasFPCVT())
     setTargetDAGCombine(ISD::UINT_TO_FP);
   setTargetDAGCombine(ISD::LOAD);
@@ -1041,6 +1042,8 @@ const char *PPCTargetLowering::getTargetNodeName(unsigned Opcode) const {
   case PPCISD::MFVSR:           return "PPCISD::MFVSR";
   case PPCISD::MTVSRA:          return "PPCISD::MTVSRA";
   case PPCISD::MTVSRZ:          return "PPCISD::MTVSRZ";
+  case PPCISD::SINT_VEC_TO_FP:  return "PPCISD::SINT_VEC_TO_FP";
+  case PPCISD::UINT_VEC_TO_FP:  return "PPCISD::UINT_VEC_TO_FP";
   case PPCISD::ANDIo_1_EQ_BIT:  return "PPCISD::ANDIo_1_EQ_BIT";
   case PPCISD::ANDIo_1_GT_BIT:  return "PPCISD::ANDIo_1_GT_BIT";
   case PPCISD::VCMP:            return "PPCISD::VCMP";
@@ -10188,6 +10191,59 @@ SDValue PPCTargetLowering::DAGCombineExtBoolTrunc(SDNode *N,
       ShiftCst);
 }
 
+SDValue PPCTargetLowering::DAGCombineBuildVector(SDNode *N,
+                                                 DAGCombinerInfo &DCI) const {
+  assert(N->getOpcode() == ISD::BUILD_VECTOR &&
+         "Should be called with a BUILD_VECTOR node");
+
+  SelectionDAG &DAG = DCI.DAG;
+  SDLoc dl(N);
+  if (N->getValueType(0) != MVT::v2f64 || !Subtarget.hasVSX())
+    return SDValue();
+
+  // Looking for:
+  // (build_vector ([su]int_to_fp (extractelt 0)), [su]int_to_fp (extractelt 1))
+  if (N->getOperand(0).getOpcode() != ISD::SINT_TO_FP &&
+      N->getOperand(0).getOpcode() != ISD::UINT_TO_FP)
+    return SDValue();
+  if (N->getOperand(1).getOpcode() != ISD::SINT_TO_FP &&
+      N->getOperand(1).getOpcode() != ISD::UINT_TO_FP)
+    return SDValue();
+  if (N->getOperand(0).getOpcode() != N->getOperand(1).getOpcode())
+    return SDValue();
+
+  SDValue Ext1 = N->getOperand(0).getOperand(0);
+  SDValue Ext2 = N->getOperand(1).getOperand(0);
+  if(Ext1.getOpcode() != ISD::EXTRACT_VECTOR_ELT ||
+     Ext2.getOpcode() != ISD::EXTRACT_VECTOR_ELT)
+    return SDValue();
+
+  ConstantSDNode *Ext1Op = dyn_cast<ConstantSDNode>(Ext1.getOperand(1));
+  ConstantSDNode *Ext2Op = dyn_cast<ConstantSDNode>(Ext2.getOperand(1));
+  if (!Ext1Op || !Ext2Op)
+    return SDValue();
+  if (Ext1.getValueType() != MVT::i32 ||
+      Ext2.getValueType() != MVT::i32)
+  if (Ext1.getOperand(0) != Ext2.getOperand(0))
+    return SDValue();
+
+  int FirstElem = Ext1Op->getZExtValue();
+  int SecondElem = Ext2Op->getZExtValue();
+  int SubvecIdx;
+  if (FirstElem == 0 && SecondElem == 1)
+    SubvecIdx = Subtarget.isLittleEndian() ? 1 : 0;
+  else if (FirstElem == 2 && SecondElem == 3)
+    SubvecIdx = Subtarget.isLittleEndian() ? 0 : 1;
+  else
+    return SDValue();
+
+  SDValue SrcVec = Ext1.getOperand(0);
+  auto NodeType = (N->getOperand(1).getOpcode() == ISD::SINT_TO_FP) ?
+    PPCISD::SINT_VEC_TO_FP : PPCISD::UINT_VEC_TO_FP;
+  return DAG.getNode(NodeType, dl, MVT::v2f64,
+                     SrcVec, DAG.getIntPtrConstant(SubvecIdx, dl));
+}
+
 SDValue PPCTargetLowering::combineFPToIntToFP(SDNode *N,
                                               DAGCombinerInfo &DCI) const {
   assert((N->getOpcode() == ISD::SINT_TO_FP ||
@@ -11024,6 +11080,8 @@ SDValue PPCTargetLowering::PerformDAGCombine(SDNode *N,
     }
     break;
   }
+  case ISD::BUILD_VECTOR:
+    return DAGCombineBuildVector(N, DCI);
   }
 
   return SDValue();

diff --git a/lib/Target/PowerPC/PPCISelLowering.h b/lib/Target/PowerPC/PPCISelLowering.h
index 5f4795b6cebb836d404cafd9a9a307b80c7f1347..14dfc45bcdcaa7fa3480917bf9c2d5fff4db38c9 100644 (file)
--- a/lib/Target/PowerPC/PPCISelLowering.h
+++ b/lib/Target/PowerPC/PPCISelLowering.h
@@ -137,6 +137,16 @@ namespace llvm {
       /// Direct move from a GPR to a VSX register (zero)
       MTVSRZ,
 
+      /// Extract a subvector from signed integer vector and convert to FP.
+      /// It is primarily used to convert a (widened) illegal integer vector
+      /// type to a legal floating point vector type.
+      /// For example v2i32 -> widened to v4i32 -> v2f64
+      SINT_VEC_TO_FP,
+
+      /// Extract a subvector from unsigned integer vector and convert to FP.
+      /// As with SINT_VEC_TO_FP, used for converting illegal types.
+      UINT_VEC_TO_FP,
+
       // FIXME: Remove these once the ANDI glue bug is fixed:
       /// i1 = ANDIo_1_[EQ|GT]_BIT(i32 or i64 x) - Represents the result of the
       /// eq or gt bit of CR0 after executing andi. x, 1. This is used to
@@ -432,6 +442,20 @@ namespace llvm {
     /// DAG node.
     const char *getTargetNodeName(unsigned Opcode) const override;
 
+    /// getPreferredVectorAction - The code we generate when vector types are
+    /// legalized by promoting the integer element type is often much worse
+    /// than code we generate if we widen the type for applicable vector types.
+    /// The issue with promoting is that the vector is scalaraized, individual
+    /// elements promoted and then the vector is rebuilt. So say we load a pair
+    /// of v4i8's and shuffle them. This will turn into a mess of 8 extending
+    /// loads, moves back into VSR's (or memory ops if we don't have moves) and
+    /// then the VPERM for the shuffle. All in all a very slow sequence.
+    TargetLoweringBase::LegalizeTypeAction getPreferredVectorAction(EVT VT)
+      const override {
+      if (VT.getVectorElementType().getSizeInBits() % 8 == 0)
+        return TypeWidenVector;
+      return TargetLoweringBase::getPreferredVectorAction(VT);
+    }
     bool useSoftFloat() const override;
 
     MVT getScalarShiftAmountTy(const DataLayout &, EVT) const override {
@@ -883,6 +907,7 @@ namespace llvm {
     SDValue lowerEH_SJLJ_LONGJMP(SDValue Op, SelectionDAG &DAG) const;
 
     SDValue DAGCombineExtBoolTrunc(SDNode *N, DAGCombinerInfo &DCI) const;
+    SDValue DAGCombineBuildVector(SDNode *N, DAGCombinerInfo &DCI) const;
     SDValue DAGCombineTruncBoolExt(SDNode *N, DAGCombinerInfo &DCI) const;
     SDValue combineFPToIntToFP(SDNode *N, DAGCombinerInfo &DCI) const;
 

diff --git a/lib/Target/PowerPC/PPCInstrVSX.td b/lib/Target/PowerPC/PPCInstrVSX.td
index bc91fb6874bbcb20e9d8e48cf0461c993325e2e8..f461f2bfcf25a8c9eda0681645ac42aca85a8a72 100644 (file)
--- a/lib/Target/PowerPC/PPCInstrVSX.td
+++ b/lib/Target/PowerPC/PPCInstrVSX.td
@@ -57,6 +57,9 @@ def SDT_PPCstxvd2x : SDTypeProfile<0, 2, [
 def SDT_PPCxxswapd : SDTypeProfile<1, 1, [
   SDTCisSameAs<0, 1>
 ]>;
+def SDTVecConv : SDTypeProfile<1, 2, [
+  SDTCisVec<0>, SDTCisVec<1>, SDTCisPtrTy<2>
+]>;
 
 def PPClxvd2x  : SDNode<"PPCISD::LXVD2X", SDT_PPClxvd2x,
                         [SDNPHasChain, SDNPMayLoad]>;
@@ -66,6 +69,8 @@ def PPCxxswapd : SDNode<"PPCISD::XXSWAPD", SDT_PPCxxswapd, [SDNPHasChain]>;
 def PPCmfvsr : SDNode<"PPCISD::MFVSR", SDTUnaryOp, []>;
 def PPCmtvsra : SDNode<"PPCISD::MTVSRA", SDTUnaryOp, []>;
 def PPCmtvsrz : SDNode<"PPCISD::MTVSRZ", SDTUnaryOp, []>;
+def PPCsvec2fp : SDNode<"PPCISD::SINT_VEC_TO_FP", SDTVecConv, []>;
+def PPCuvec2fp: SDNode<"PPCISD::UINT_VEC_TO_FP", SDTVecConv, []>;
 
 multiclass XX3Form_Rcr<bits<6> opcode, bits<7> xo, string asmbase,
                     string asmstr, InstrItinClass itin, Intrinsic Int,
@@ -608,7 +613,8 @@ let Uses = [RM] in {
                       "xvcvsxwdp $XT, $XB", IIC_VecFP, []>;
   def XVCVSXWSP : XX2Form<60, 184,
                       (outs vsrc:$XT), (ins vsrc:$XB),
-                      "xvcvsxwsp $XT, $XB", IIC_VecFP, []>;
+                      "xvcvsxwsp $XT, $XB", IIC_VecFP,
+                      [(set v4f32:$XT, (sint_to_fp v4i32:$XB))]>;
   def XVCVUXDDP : XX2Form<60, 488,
                       (outs vsrc:$XT), (ins vsrc:$XB),
                       "xvcvuxddp $XT, $XB", IIC_VecFP,
@@ -928,6 +934,16 @@ def : Pat<(sext_inreg v2i64:$C, v2i32),
 def : Pat<(v2f64 (sint_to_fp (sext_inreg v2i64:$C, v2i32))),
           (XVCVSXWDP (XXSLDWI $C, $C, 1))>;
 
+def : Pat<(v2f64 (PPCsvec2fp v4i32:$C, 0)),
+          (v2f64 (XVCVSXWDP (v2i64 (XXMRGHW $C, $C))))>;
+def : Pat<(v2f64 (PPCsvec2fp v4i32:$C, 1)),
+          (v2f64 (XVCVSXWDP (v2i64 (XXMRGLW $C, $C))))>;
+
+def : Pat<(v2f64 (PPCuvec2fp v4i32:$C, 0)),
+          (v2f64 (XVCVUXWDP (v2i64 (XXMRGHW $C, $C))))>;
+def : Pat<(v2f64 (PPCuvec2fp v4i32:$C, 1)),
+          (v2f64 (XVCVUXWDP (v2i64 (XXMRGLW $C, $C))))>;
+
 // Loads.
 def : Pat<(v2f64 (load xoaddr:$src)), (LXVD2X xoaddr:$src)>;
 def : Pat<(v2i64 (load xoaddr:$src)), (LXVD2X xoaddr:$src)>;

diff --git a/test/Analysis/CostModel/PowerPC/load_store.ll b/test/Analysis/CostModel/PowerPC/load_store.ll
index 0a568b88e7269c6bfa6040d222544ca6f4f81ebd..d48be5b5f62be52f5e664edfefb3f4d7a5aec44d 100644 (file)
--- a/test/Analysis/CostModel/PowerPC/load_store.ll
+++ b/test/Analysis/CostModel/PowerPC/load_store.ll
@@ -31,7 +31,7 @@ define i32 @loads(i32 %arg) {
 
   ; FIXME: There actually are sub-vector Altivec loads, and so we could handle
   ; this with a small expense, but we don't currently.
-  ; CHECK: cost of 48 {{.*}} load
+  ; CHECK: cost of 42 {{.*}} load
   load <4 x i16>, <4 x i16>* undef, align 2
 
   ; CHECK: cost of 2 {{.*}} load

diff --git a/test/CodeGen/PowerPC/load-v4i8-improved.ll b/test/CodeGen/PowerPC/load-v4i8-improved.ll
new file mode 100644 (file)
index 0000000..d03ff06
--- /dev/null
+++ b/test/CodeGen/PowerPC/load-v4i8-improved.ll
@@ -0,0 +1,23 @@
+; RUN: llc -mcpu=pwr8 -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck \
+; RUN:   -implicit-check-not vmrg -implicit-check-not=vperm %s
+; RUN: llc -mcpu=pwr8 -mtriple=powerpc64-unknown-linux-gnu < %s | FileCheck \
+; RUN:   -implicit-check-not vmrg -implicit-check-not=vperm %s \
+; RUN:   --check-prefix=CHECK-BE
+
+define <16 x i8> @test(i32* %s, i32* %t) {
+entry:
+  %0 = bitcast i32* %s to <4 x i8>*
+  %1 = load <4 x i8>, <4 x i8>* %0, align 4
+  %2 = shufflevector <4 x i8> %1, <4 x i8> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
+  ret <16 x i8> %2
+; CHECK-LABEL: test
+; CHECK: lwz [[GPR:[0-9]+]], 0(3)
+; CHECK: mtvsrd [[VSR:[0-9]+]], [[GPR]]
+; CHECK: xxswapd  [[SWP:[0-9]+]], [[VSR]]
+; CHECK: xxspltw 34, [[SWP]], 3
+; CHECK-BE-LABEL: test
+; CHECK-BE: lwz [[GPR:[0-9]+]], 0(3)
+; CHECK-BE: sldi [[SHL:[0-9]+]], [[GPR]], 32
+; CHECK-BE: mtvsrd [[VSR:[0-9]+]], [[SHL]]
+; CHECK-BE: xxspltw 34, [[VSR]], 0
+}

diff --git a/test/CodeGen/PowerPC/p8altivec-shuffles-pred.ll b/test/CodeGen/PowerPC/p8altivec-shuffles-pred.ll
index 052f55644fe268c12d0530363778376079905d7e..3610c044b943e128e96bfababba750d74317d09b 100644 (file)
--- a/test/CodeGen/PowerPC/p8altivec-shuffles-pred.ll
+++ b/test/CodeGen/PowerPC/p8altivec-shuffles-pred.ll
@@ -9,7 +9,8 @@ entry:
   ret <2 x i32> %strided.vec
 
 ; CHECK-LABEL: @test1
-; CHECK: vsldoi 2, 2, 2, 12
+; CHECK: vsldoi [[TGT:[0-9]+]], 2, 2, 8
+; CHECK: vmrghw 2, 2, [[TGT]]
 ; CHECK: blr
 }
 

diff --git a/test/CodeGen/PowerPC/vec_cmp.ll b/test/CodeGen/PowerPC/vec_cmp.ll
index 516b2dd58b9955dccf7cc43f0028816feef060b9..7b228bffc386c98949fc317d6e2641062722e9cb 100644 (file)
--- a/test/CodeGen/PowerPC/vec_cmp.ll
+++ b/test/CodeGen/PowerPC/vec_cmp.ll
@@ -24,7 +24,7 @@ define <4 x i8> @v4si8_cmp(<4 x i8> %x, <4 x i8> %y) nounwind readnone {
   ret <4 x i8> %sext
 }
 ; CHECK-LABEL: v4si8_cmp:
-; CHECK: vcmpequw {{[0-9]+}}, {{[0-9]+}}, {{[0-9]+}}
+; CHECK: vcmpequb {{[0-9]+}}, {{[0-9]+}}, {{[0-9]+}}
 
 
 define <8 x i8> @v8si8_cmp(<8 x i8> %x, <8 x i8> %y) nounwind readnone {
@@ -33,7 +33,7 @@ define <8 x i8> @v8si8_cmp(<8 x i8> %x, <8 x i8> %y) nounwind readnone {
   ret <8 x i8> %sext
 }
 ; CHECK-LABEL: v8si8_cmp:
-; CHECK: vcmpequh {{[0-9]+}}, {{[0-9]+}}, {{[0-9]+}}
+; CHECK: vcmpequb {{[0-9]+}}, {{[0-9]+}}, {{[0-9]+}}
 
 
 ; Additional tests for v16i8 since it is a altivec native type
@@ -158,7 +158,7 @@ define <4 x i16> @v4si16_cmp(<4 x i16> %x, <4 x i16> %y) nounwind readnone {
   ret <4 x i16> %sext
 }
 ; CHECK-LABEL: v4si16_cmp:
-; CHECK: vcmpequw {{[0-9]+}}, {{[0-9]+}}, {{[0-9]+}}
+; CHECK: vcmpequh {{[0-9]+}}, {{[0-9]+}}, {{[0-9]+}}
 
 
 ; Additional tests for v8i16 since it is an altivec native type

diff --git a/test/CodeGen/PowerPC/vsx.ll b/test/CodeGen/PowerPC/vsx.ll
index b2eefb666760ea2e7e2510476f514a327c957049..9b65649978d3f09bdb6d3c5be57fe0d758ed013f 100644 (file)
--- a/test/CodeGen/PowerPC/vsx.ll
+++ b/test/CodeGen/PowerPC/vsx.ll
@@ -1144,62 +1144,67 @@ define <2 x double> @test68(<2 x i32> %a) {
   ret <2 x double> %w
 
 ; CHECK-LABEL: @test68
-; CHECK: xxsldwi [[V1:[0-9]+]], 34, 34, 1
+; CHECK: xxmrghw [[V1:[0-9]+]]
 ; CHECK: xvcvsxwdp 34, [[V1]]
 ; CHECK: blr
 
 ; CHECK-LE-LABEL: @test68
-; CHECK-LE: xxsldwi [[V1:[0-9]+]], 34, 34, 1
+; CHECK-LE: xxmrglw [[V1:[0-9]+]], 34, 34
 ; CHECK-LE: xvcvsxwdp 34, [[V1]]
 ; CHECK-LE: blr
 }
 
+; This gets scalarized so the code isn't great
 define <2 x double> @test69(<2 x i16> %a) {
   %w = sitofp <2 x i16> %a to <2 x double>
   ret <2 x double> %w
 
 ; CHECK-LABEL: @test69
-; CHECK: vspltisw [[V1:[0-9]+]], 8
-; CHECK: vadduwm [[V2:[0-9]+]], [[V1]], [[V1]]
-; CHECK: vslw [[V3:[0-9]+]], {{[0-9]+}}, [[V2]]
-; CHECK: vsraw {{[0-9]+}}, [[V3]], [[V2]]
-; CHECK: xxsldwi [[V4:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, 1
-; CHECK: xvcvsxwdp 34, [[V4]]
+; CHECK-DAG: lfiwax
+; CHECK-DAG: lfiwax
+; CHECK-DAG: xscvsxddp
+; CHECK-DAG: xscvsxddp
+; CHECK: xxmrghd
 ; CHECK: blr
 
 ; CHECK-LE-LABEL: @test69
-; CHECK-LE: vspltisw [[V1:[0-9]+]], 8
-; CHECK-LE: vadduwm [[V2:[0-9]+]], [[V1]], [[V1]]
-; CHECK-LE: vslw [[V3:[0-9]+]], {{[0-9]+}}, [[V2]]
-; CHECK-LE: vsraw {{[0-9]+}}, [[V3]], [[V2]]
-; CHECK-LE: xxsldwi [[V4:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, 1
-; CHECK-LE: xvcvsxwdp 34, [[V4]]
+; CHECK-LE: mfvsrd
+; CHECK-LE: mtvsrwa
+; CHECK-LE: mtvsrwa
+; CHECK-LE: xscvsxddp
+; CHECK-LE: xscvsxddp
+; CHECK-LE: xxspltd
+; CHECK-LE: xxspltd
+; CHECK-LE: xxmrgld
 ; CHECK-LE: blr
 }
 
+; This gets scalarized so the code isn't great
 define <2 x double> @test70(<2 x i8> %a) {
   %w = sitofp <2 x i8> %a to <2 x double>
   ret <2 x double> %w
 
 ; CHECK-LABEL: @test70
-; CHECK: vspltisw [[V1:[0-9]+]], 12
-; CHECK: vadduwm [[V2:[0-9]+]], [[V1]], [[V1]]
-; CHECK: vslw [[V3:[0-9]+]], {{[0-9]+}}, [[V2]]
-; CHECK: vsraw {{[0-9]+}}, [[V3]], [[V2]]
-; CHECK: xxsldwi [[V4:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, 1
-; CHECK: xvcvsxwdp 34, [[V4]]
+; CHECK-DAG: lfiwax
+; CHECK-DAG: lfiwax
+; CHECK-DAG: xscvsxddp
+; CHECK-DAG: xscvsxddp
+; CHECK: xxmrghd
 ; CHECK: blr
 
 ; CHECK-LE-LABEL: @test70
-; CHECK-LE: vspltisw [[V1:[0-9]+]], 12
-; CHECK-LE: vadduwm [[V2:[0-9]+]], [[V1]], [[V1]]
-; CHECK-LE: vslw [[V3:[0-9]+]], {{[0-9]+}}, [[V2]]
-; CHECK-LE: vsraw {{[0-9]+}}, [[V3]], [[V2]]
-; CHECK-LE: xxsldwi [[V4:[0-9]+]], {{[0-9]+}}, {{[0-9]+}}, 1
-; CHECK-LE: xvcvsxwdp 34, [[V4]]
+; CHECK-LE: mfvsrd
+; CHECK-LE: mtvsrwa
+; CHECK-LE: mtvsrwa
+; CHECK-LE: xscvsxddp
+; CHECK-LE: xscvsxddp
+; CHECK-LE: xxspltd
+; CHECK-LE: xxspltd
+; CHECK-LE: xxmrgld
 ; CHECK-LE: blr
 }
 
+; This gets scalarized so the code isn't great
 define <2 x i32> @test80(i32 %v) {
   %b1 = insertelement <2 x i32> undef, i32 %v, i32 0
   %b2 = shufflevector <2 x i32> %b1, <2 x i32> undef, <2 x i32> zeroinitializer
@@ -1207,31 +1212,38 @@ define <2 x i32> @test80(i32 %v) {
   ret <2 x i32> %i
 
 ; CHECK-REG-LABEL: @test80
-; CHECK-REG-DAG: addi [[R1:[0-9]+]], 3, 3
-; CHECK-REG-DAG: addi [[R2:[0-9]+]], 1, -16
-; CHECK-REG-DAG: addi [[R3:[0-9]+]], 3, 2
-; CHECK-REG: std [[R1]], -8(1)
-; CHECK-REG: std [[R3]], -16(1)
-; CHECK-REG: lxvd2x 34, 0, [[R2]]
-; CHECK-REG-NOT: stxvd2x
+; CHECK-REG: stw 3, -16(1)
+; CHECK-REG: addi [[R1:[0-9]+]], 1, -16
+; CHECK-REG: addis [[R2:[0-9]+]]
+; CHECK-REG: addi [[R2]], [[R2]]
+; CHECK-REG-DAG: lxvw4x [[VS1:[0-9]+]], 0, [[R1]]
+; CHECK-REG-DAG: lxvw4x 35, 0, [[R2]]
+; CHECK-REG: xxspltw 34, [[VS1]], 0
+; CHECK-REG: vadduwm 2, 2, 3
+; CHECK-REG-NOT: stxvw4x
 ; CHECK-REG: blr
 
 ; CHECK-FISL-LABEL: @test80
-; CHECK-FISL-DAG: addi [[R1:[0-9]+]], 3, 3
-; CHECK-FISL-DAG: addi [[R2:[0-9]+]], 1, -16
-; CHECK-FISL-DAG: addi [[R3:[0-9]+]], 3, 2
-; CHECK-FISL-DAG: std [[R1]], -8(1)
-; CHECK-FISL-DAG: std [[R3]], -16(1)
-; CHECK-FISL-DAG: lxvd2x 0, 0, [[R2]]
+; CHECK-FISL: mr 4, 3
+; CHECK-FISL: stw 4, -16(1)
+; CHECK-FISL: addi [[R1:[0-9]+]], 1, -16
+; CHECK-FISL-DAG: lxvw4x [[VS1:[0-9]+]], 0, [[R1]]
+; CHECK-FISL-DAG: xxspltw {{[0-9]+}}, [[VS1]], 0
+; CHECK-FISL: addis [[R2:[0-9]+]]
+; CHECK-FISL: addi [[R2]], [[R2]]
+; CHECK-FISL-DAG: lxvw4x {{[0-9]+}}, 0, [[R2]]
+; CHECK-FISL: vadduwm
+; CHECK-FISL-NOT: stxvw4x
 ; CHECK-FISL: blr
 
 ; CHECK-LE-LABEL: @test80
 ; CHECK-LE-DAG: mtvsrd [[R1:[0-9]+]], 3
+; CHECK-LE-DAG: xxswapd  [[V1:[0-9]+]], [[R1]]
 ; CHECK-LE-DAG: addi [[R2:[0-9]+]], {{[0-9]+}}, .LCPI
 ; CHECK-LE-DAG: lxvd2x [[V2:[0-9]+]], 0, [[R2]]
-; CHECK-LE-DAG: xxspltd 34, [[R1]]
+; CHECK-LE-DAG: xxspltw 34, [[V1]]
 ; CHECK-LE-DAG: xxswapd 35, [[V2]]
-; CHECK-LE: vaddudm 2, 2, 3
+; CHECK-LE: vadduwm 2, 2, 3
 ; CHECK-LE: blr
 }