[PowerPC] Cust lower fpext v2f32 to v2f64 from extract_subvector v4f32

Add the missing piece of r372029.
Somehow when the patch for review D61961 was committed, only the test case
went in and the code didn't. This of course caused all kinds of build bot
breaks.
This patch just adds the code for that patch.

Author: Lei Huang
Differential revision: https://reviews.llvm.org/D61961

llvm-svn: 372043

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

@@ -1405,7 +1405,7 @@ const char *PPCTargetLowering::getTargetNodeName(unsigned Opcode) const {
   case PPCISD::EXTRACT_SPE:     return "PPCISD::EXTRACT_SPE";
   case PPCISD::EXTSWSLI:        return "PPCISD::EXTSWSLI";
   case PPCISD::LD_VSX_LH:       return "PPCISD::LD_VSX_LH";
-  case PPCISD::FP_EXTEND_LH:    return "PPCISD::FP_EXTEND_LH";
+  case PPCISD::FP_EXTEND_HALF:  return "PPCISD::FP_EXTEND_HALF";
   }
   return nullptr;
 }
@@ -9913,6 +9913,30 @@ SDValue PPCTargetLowering::LowerFP_EXTEND(SDValue Op, SelectionDAG &DAG) const {
   switch (Op0.getOpcode()) {
   default:
     return SDValue();
+  case ISD::EXTRACT_SUBVECTOR: {
+    assert(Op0.getNumOperands() == 2 &&
+           isa<ConstantSDNode>(Op0->getOperand(1)) &&
+           "Node should have 2 operands with second one being a constant!");
+
+    if (Op0.getOperand(0).getValueType() != MVT::v4f32)
+      return SDValue();
+
+    // Custom lower is only done for high or low doubleword.
+    int Idx = cast<ConstantSDNode>(Op0.getOperand(1))->getZExtValue();
+    if (Idx % 2 != 0)
+      return SDValue();
+
+    // Since input is v4f32, at this point Idx is either 0 or 2.
+    // Shift to get the doubleword position we want.
+    int DWord = Idx >> 1;
+
+    // High and low word positions are different on little endian.
+    if (Subtarget.isLittleEndian())
+      DWord ^= 0x1;
+
+    return DAG.getNode(PPCISD::FP_EXTEND_HALF, dl, MVT::v2f64,
+                       Op0.getOperand(0), DAG.getConstant(DWord, dl, MVT::i32));
+  }
   case ISD::FADD:
   case ISD::FMUL:
   case ISD::FSUB: {
@@ -9925,25 +9949,24 @@ SDValue PPCTargetLowering::LowerFP_EXTEND(SDValue Op, SelectionDAG &DAG) const {
       // Generate new load node.
       LoadSDNode *LD = cast<LoadSDNode>(LdOp);
       SDValue LoadOps[] = {LD->getChain(), LD->getBasePtr()};
-      NewLoad[i] =
+      NewLoad[i] = DAG.getMemIntrinsicNode(
-        DAG.getMemIntrinsicNode(PPCISD::LD_VSX_LH, dl,
+          PPCISD::LD_VSX_LH, dl, DAG.getVTList(MVT::v4f32, MVT::Other), LoadOps,
-                                DAG.getVTList(MVT::v4f32, MVT::Other),
+          LD->getMemoryVT(), LD->getMemOperand());
-                                LoadOps, LD->getMemoryVT(),
-                                LD->getMemOperand());
     }
-    SDValue NewOp = DAG.getNode(Op0.getOpcode(), SDLoc(Op0), MVT::v4f32,
+    SDValue NewOp =
-                              NewLoad[0], NewLoad[1],
+        DAG.getNode(Op0.getOpcode(), SDLoc(Op0), MVT::v4f32, NewLoad[0],
-                              Op0.getNode()->getFlags());
+                    NewLoad[1], Op0.getNode()->getFlags());
-    return DAG.getNode(PPCISD::FP_EXTEND_LH, dl, MVT::v2f64, NewOp);
+    return DAG.getNode(PPCISD::FP_EXTEND_HALF, dl, MVT::v2f64, NewOp,
+                       DAG.getConstant(0, dl, MVT::i32));
   }
   case ISD::LOAD: {
     LoadSDNode *LD = cast<LoadSDNode>(Op0);
     SDValue LoadOps[] = {LD->getChain(), LD->getBasePtr()};
-    SDValue NewLd =
+    SDValue NewLd = DAG.getMemIntrinsicNode(
-      DAG.getMemIntrinsicNode(PPCISD::LD_VSX_LH, dl,
+        PPCISD::LD_VSX_LH, dl, DAG.getVTList(MVT::v4f32, MVT::Other), LoadOps,
-                              DAG.getVTList(MVT::v4f32, MVT::Other),
+        LD->getMemoryVT(), LD->getMemOperand());
-                              LoadOps, LD->getMemoryVT(), LD->getMemOperand());
+    return DAG.getNode(PPCISD::FP_EXTEND_HALF, dl, MVT::v2f64, NewLd,
-    return DAG.getNode(PPCISD::FP_EXTEND_LH, dl, MVT::v2f64, NewLd);
+                       DAG.getConstant(0, dl, MVT::i32));
   }
   }
   llvm_unreachable("ERROR:Should return for all cases within swtich.");

llvm/lib/Target/PowerPC/PPCISelLowering.h

@@ -412,8 +412,9 @@ namespace llvm {
       /// representation.
       QBFLT,
 
-      /// Custom extend v4f32 to v2f64.
+      /// FP_EXTEND_HALF(VECTOR, IDX) - Custom extend upper (IDX=0) half or
-      FP_EXTEND_LH,
+      /// lower (IDX=1) half of v4f32 to v2f64.
+      FP_EXTEND_HALF,
 
       /// CHAIN = STBRX CHAIN, GPRC, Ptr, Type - This is a
       /// byte-swapping store instruction.  It byte-swaps the low "Type" bits of

llvm/lib/Target/PowerPC/PPCInstrVSX.td

@@ -58,8 +58,8 @@ def SDT_PPCldvsxlh : SDTypeProfile<1, 1, [
   SDTCisVT<0, v4f32>, SDTCisPtrTy<1>
 ]>;
 
-def SDT_PPCfpextlh : SDTypeProfile<1, 1, [
+def SDT_PPCfpexth : SDTypeProfile<1, 2, [
-  SDTCisVT<0, v2f64>, SDTCisVT<1, v4f32>
+  SDTCisVT<0, v2f64>, SDTCisVT<1, v4f32>, SDTCisPtrTy<2>
 ]>;
 
 // Little-endian-specific nodes.
@@ -102,7 +102,7 @@ def PPCuvec2fp: SDNode<"PPCISD::UINT_VEC_TO_FP", SDTVecConv, []>;
 def PPCswapNoChain : SDNode<"PPCISD::SWAP_NO_CHAIN", SDT_PPCxxswapd>;
 def PPCvabsd : SDNode<"PPCISD::VABSD", SDTVabsd, []>;
 
-def PPCfpextlh : SDNode<"PPCISD::FP_EXTEND_LH", SDT_PPCfpextlh, []>;
+def PPCfpexth : SDNode<"PPCISD::FP_EXTEND_HALF", SDT_PPCfpexth, []>;
 def PPCldvsxlh : SDNode<"PPCISD::LD_VSX_LH", SDT_PPCldvsxlh,
                         [SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
 
@@ -1086,7 +1086,8 @@ def : Pat<(v2f64 (PPCuvec2fp v4i32:$C, 0)),
 def : Pat<(v2f64 (PPCuvec2fp v4i32:$C, 1)),
           (v2f64 (XVCVUXWDP (v2i64 (XXMRGLW $C, $C))))>;
 
-def : Pat<(v2f64 (PPCfpextlh v4f32:$C)), (XVCVSPDP (XXMRGHW $C, $C))>;
+def : Pat<(v2f64 (PPCfpexth v4f32:$C, 0)), (XVCVSPDP (XXMRGHW $C, $C))>;
+def : Pat<(v2f64 (PPCfpexth v4f32:$C, 1)), (XVCVSPDP (XXMRGLW $C, $C))>;
 
 // Loads.
 let Predicates = [HasVSX, HasOnlySwappingMemOps] in {