Add more PPC floating-point conversion instructions

The P7 and A2 have additional floating-point conversion instructions which
allow a direct two-instruction sequence (plus load/store) to convert from all
combinations (signed/unsigned i32/i64) <--> (float/double) (on previous cores,
only some combinations were directly available).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178480 91177308-0d34-0410-b5e6-96231b3b80d8

12 files changed, 325 insertions, 40 deletions

diff --git a/lib/Target/PowerPC/PPC.td b/lib/Target/PowerPC/PPC.td
index 602e33cd290..a1ea2297bf5 100644
--- a/lib/Target/PowerPC/PPC.td
+++ b/lib/Target/PowerPC/PPC.td
@@ -63,6 +63,8 @@ def FeatureLFIWAX    : SubtargetFeature<"lfiwax","HasLFIWAX", "true",
                                         "Enable the lfiwax instruction">;
 def FeatureFPRND     : SubtargetFeature<"fprnd", "HasFPRND", "true",
                                         "Enable the fri[mnpz] instructions">;
+def FeatureFPCVT     : SubtargetFeature<"fpcvt", "HasFPCVT", "true",
+  "Enable fc[ft]* (unsigned and single-precision) and lfiwzx instructions">;
 def FeatureISEL      : SubtargetFeature<"isel","HasISEL", "true",
                                         "Enable the isel instruction">;
 def FeaturePOPCNTD   : SubtargetFeature<"popcntd","HasPOPCNTD", "true",
@@ -79,10 +81,8 @@ def FeatureQPX       : SubtargetFeature<"qpx","HasQPX", "true",
 //
 // CMPB         p6, p6x, p7        cmpb
 // DFP          p6, p6x, p7        decimal floating-point instructions
-// FLT_CVT      p7                 fcfids, fcfidu, fcfidus, fcfiduz, fctiwuz
 // FRE          p5 through p7      fre (vs. fres, available since p3)
 // FRSQRTES     p5 through p7      frsqrtes (vs. frsqrte, available since p3)
-// LFIWZX       p7                 lfiwzx
 // POPCNTB      p5 through p7      popcntb and related instructions
 // RECIP_PREC   p6, p6x, p7        higher precision reciprocal estimates
 // VSX          p7                 vector-scalar instruction set
@@ -135,14 +135,15 @@ def : ProcessorModel<"e5500", PPCE5500Model,
 def : Processor<"a2", PPCA2Itineraries,
                   [DirectiveA2, FeatureBookE, FeatureMFOCRF,
                    FeatureFSqrt, FeatureSTFIWX, FeatureLFIWAX,
-                   FeatureFPRND, FeatureISEL, FeaturePOPCNTD,
-                   FeatureLDBRX, Feature64Bit /*, Feature64BitRegs */]>;
+                   FeatureFPRND, FeatureFPCVT, FeatureISEL,
+                   FeaturePOPCNTD, FeatureLDBRX, Feature64Bit
+               /*, Feature64BitRegs */]>;
 def : Processor<"a2q", PPCA2Itineraries,
                   [DirectiveA2, FeatureBookE, FeatureMFOCRF,
                    FeatureFSqrt, FeatureSTFIWX, FeatureLFIWAX,
-                   FeatureFPRND, FeatureISEL, FeaturePOPCNTD,
-                   FeatureLDBRX, Feature64Bit /*, Feature64BitRegs */,
-                   FeatureQPX]>;
+                   FeatureFPRND, FeatureFPCVT, FeatureISEL,
+                   FeaturePOPCNTD, FeatureLDBRX, Feature64Bit
+               /*, Feature64BitRegs */, FeatureQPX]>;
 def : Processor<"pwr3", G5Itineraries,
                   [DirectivePwr3, FeatureAltivec, FeatureMFOCRF,
                    FeatureSTFIWX, Feature64Bit]>;
@@ -168,9 +169,9 @@ def : Processor<"pwr6x", G5Itineraries,
 def : Processor<"pwr7", G5Itineraries,
                   [DirectivePwr7, FeatureAltivec,
                    FeatureMFOCRF, FeatureFSqrt, FeatureSTFIWX,
-                   FeatureLFIWAX, FeatureFPRND, FeatureISEL,
-                   FeaturePOPCNTD, FeatureLDBRX, Feature64Bit
-               /*, Feature64BitRegs */]>;
+                   FeatureLFIWAX, FeatureFPRND, FeatureFPCVT,
+                   FeatureISEL, FeaturePOPCNTD, FeatureLDBRX,
+                   Feature64Bit /*, Feature64BitRegs */]>;
 def : Processor<"ppc", G3Itineraries, [Directive32]>;
 def : Processor<"ppc64", G5Itineraries,
                   [Directive64, FeatureAltivec,
diff --git a/lib/Target/PowerPC/PPCISelLowering.cpp b/lib/Target/PowerPC/PPCISelLowering.cpp
index 89b42af72e9..9c686cb9467 100644
--- a/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -326,13 +326,28 @@ PPCTargetLowering::PPCTargetLowering(PPCTargetMachine &TM)
     // We cannot do this with Promote because i64 is not a legal type.
     setOperationAction(ISD::FP_TO_UINT, MVT::i32, Custom);
 
-    if (Subtarget->isPPC64())
+    if (PPCSubTarget.hasLFIWAX() || Subtarget->isPPC64())
       setOperationAction(ISD::SINT_TO_FP, MVT::i32, Custom);
   } else {
     // PowerPC does not have FP_TO_UINT on 32-bit implementations.
     setOperationAction(ISD::FP_TO_UINT, MVT::i32, Expand);
   }
 
+  // With the instructions enabled under FPCVT, we can do everything.
+  if (PPCSubTarget.hasFPCVT()) {
+    if (Subtarget->has64BitSupport()) {
+      setOperationAction(ISD::FP_TO_SINT, MVT::i64, Custom);
+      setOperationAction(ISD::FP_TO_UINT, MVT::i64, Custom);
+      setOperationAction(ISD::SINT_TO_FP, MVT::i64, Custom);
+      setOperationAction(ISD::UINT_TO_FP, MVT::i64, Custom);
+    }
+
+    setOperationAction(ISD::FP_TO_SINT, MVT::i32, Custom);
+    setOperationAction(ISD::FP_TO_UINT, MVT::i32, Custom);
+    setOperationAction(ISD::SINT_TO_FP, MVT::i32, Custom);
+    setOperationAction(ISD::UINT_TO_FP, MVT::i32, Custom);
+  }
+
   if (Subtarget->use64BitRegs()) {
     // 64-bit PowerPC implementations can support i64 types directly
     addRegisterClass(MVT::i64, &PPC::G8RCRegClass);
@@ -4716,37 +4731,72 @@ SDValue PPCTargetLowering::LowerFP_TO_INT(SDValue Op, SelectionDAG &DAG,
   default: llvm_unreachable("Unhandled FP_TO_INT type in custom expander!");
   case MVT::i32:
     Tmp = DAG.getNode(Op.getOpcode()==ISD::FP_TO_SINT ? PPCISD::FCTIWZ :
-                                                         PPCISD::FCTIDZ,
+                        (PPCSubTarget.hasFPCVT() ? PPCISD::FCTIWUZ :
+                                                   PPCISD::FCTIDZ),
                       dl, MVT::f64, Src);
     break;
   case MVT::i64:
-    Tmp = DAG.getNode(PPCISD::FCTIDZ, dl, MVT::f64, Src);
+    assert((Op.getOpcode() == ISD::SINT_TO_FP || PPCSubTarget.hasFPCVT()) &&
+           "i64 UINT_TO_FP is supported only with FPCVT");
+    Tmp = DAG.getNode(Op.getOpcode()==ISD::FP_TO_SINT ? PPCISD::FCTIDZ :
+                                                        PPCISD::FCTIDUZ,
+                      dl, MVT::f64, Src);
     break;
   }
 
   // Convert the FP value to an int value through memory.
-  SDValue FIPtr = DAG.CreateStackTemporary(MVT::f64);
+  bool i32Stack = Op.getValueType() == MVT::i32 && PPCSubTarget.hasSTFIWX() &&
+    (Op.getOpcode() == ISD::FP_TO_SINT || PPCSubTarget.hasFPCVT());
+  SDValue FIPtr = DAG.CreateStackTemporary(i32Stack ? MVT::i32 : MVT::f64);
+  int FI = cast<FrameIndexSDNode>(FIPtr)->getIndex();
+  MachinePointerInfo MPI = MachinePointerInfo::getFixedStack(FI);
 
   // Emit a store to the stack slot.
-  SDValue Chain = DAG.getStore(DAG.getEntryNode(), dl, Tmp, FIPtr,
-                               MachinePointerInfo(), false, false, 0);
+  SDValue Chain;
+  if (i32Stack) {
+    MachineFunction &MF = DAG.getMachineFunction();
+    MachineMemOperand *MMO =
+      MF.getMachineMemOperand(MPI, MachineMemOperand::MOStore, 4, 4);
+    SDValue Ops[] = { DAG.getEntryNode(), Tmp, FIPtr };
+    Chain = DAG.getMemIntrinsicNode(PPCISD::STFIWX, dl,
+              DAG.getVTList(MVT::Other), Ops, array_lengthof(Ops),
+              MVT::i32, MMO);
+  } else
+    Chain = DAG.getStore(DAG.getEntryNode(), dl, Tmp, FIPtr,
+                         MPI, false, false, 0);
 
   // Result is a load from the stack slot.  If loading 4 bytes, make sure to
   // add in a bias.
-  if (Op.getValueType() == MVT::i32)
+  if (Op.getValueType() == MVT::i32 && !i32Stack) {
     FIPtr = DAG.getNode(ISD::ADD, dl, FIPtr.getValueType(), FIPtr,
                         DAG.getConstant(4, FIPtr.getValueType()));
-  return DAG.getLoad(Op.getValueType(), dl, Chain, FIPtr, MachinePointerInfo(),
+    MPI = MachinePointerInfo();
+  }
+
+  return DAG.getLoad(Op.getValueType(), dl, Chain, FIPtr, MPI,
                      false, false, false, 0);
 }
 
-SDValue PPCTargetLowering::LowerSINT_TO_FP(SDValue Op,
+SDValue PPCTargetLowering::LowerINT_TO_FP(SDValue Op,
                                            SelectionDAG &DAG) const {
   DebugLoc dl = Op.getDebugLoc();
   // Don't handle ppc_fp128 here; let it be lowered to a libcall.
   if (Op.getValueType() != MVT::f32 && Op.getValueType() != MVT::f64)
     return SDValue();
 
+  assert((Op.getOpcode() == ISD::SINT_TO_FP || PPCSubTarget.hasFPCVT()) &&
+         "UINT_TO_FP is supported only with FPCVT");
+
+  // If we have FCFIDS, then use it when converting to single-precision.
+  // Otherwise, convert to double-prcision and then round.
+  unsigned FCFOp = (PPCSubTarget.hasFPCVT() && Op.getValueType() == MVT::f32) ?
+                   (Op.getOpcode() == ISD::UINT_TO_FP ?
+                    PPCISD::FCFIDUS : PPCISD::FCFIDS) :
+                   (Op.getOpcode() == ISD::UINT_TO_FP ?
+                    PPCISD::FCFIDU : PPCISD::FCFID);
+  MVT      FCFTy = (PPCSubTarget.hasFPCVT() && Op.getValueType() == MVT::f32) ?
+                   MVT::f32 : MVT::f64;
+
   if (Op.getOperand(0).getValueType() == MVT::i64) {
     SDValue SINT = Op.getOperand(0);
     // When converting to single-precision, we actually need to convert
@@ -4760,6 +4810,7 @@ SDValue PPCTargetLowering::LowerSINT_TO_FP(SDValue Op,
     // However, if -enable-unsafe-fp-math is in effect, accept double
     // rounding to avoid the extra overhead.
     if (Op.getValueType() == MVT::f32 &&
+        !PPCSubTarget.hasFPCVT() &&
         !DAG.getTarget().Options.UnsafeFPMath) {
 
       // Twiddle input to make sure the low 11 bits are zero.  (If this
@@ -4793,16 +4844,18 @@ SDValue PPCTargetLowering::LowerSINT_TO_FP(SDValue Op,
 
       SINT = DAG.getNode(ISD::SELECT, dl, MVT::i64, Cond, Round, SINT);
     }
+
     SDValue Bits = DAG.getNode(ISD::BITCAST, dl, MVT::f64, SINT);
-    SDValue FP = DAG.getNode(PPCISD::FCFID, dl, MVT::f64, Bits);
-    if (Op.getValueType() == MVT::f32)
+    SDValue FP = DAG.getNode(FCFOp, dl, FCFTy, Bits);
+
+    if (Op.getValueType() == MVT::f32 && !PPCSubTarget.hasFPCVT())
       FP = DAG.getNode(ISD::FP_ROUND, dl,
                        MVT::f32, FP, DAG.getIntPtrConstant(0));
     return FP;
   }
 
   assert(Op.getOperand(0).getValueType() == MVT::i32 &&
-         "Unhandled SINT_TO_FP type in custom expander!");
+         "Unhandled INT_TO_FP type in custom expander!");
   // Since we only generate this in 64-bit mode, we can take advantage of
   // 64-bit registers.  In particular, sign extend the input value into the
   // 64-bit register with extsw, store the WHOLE 64-bit value into the stack
@@ -4812,7 +4865,7 @@ SDValue PPCTargetLowering::LowerSINT_TO_FP(SDValue Op,
   EVT PtrVT = DAG.getTargetLoweringInfo().getPointerTy();
 
   SDValue Ld;
-  if (PPCSubTarget.hasLFIWAX()) {
+  if (PPCSubTarget.hasLFIWAX() || PPCSubTarget.hasFPCVT()) {
     int FrameIdx = FrameInfo->CreateStackObject(4, 4, false);
     SDValue FIdx = DAG.getFrameIndex(FrameIdx, PtrVT);
 
@@ -4826,10 +4879,14 @@ SDValue PPCTargetLowering::LowerSINT_TO_FP(SDValue Op,
       MF.getMachineMemOperand(MachinePointerInfo::getFixedStack(FrameIdx),
                               MachineMemOperand::MOLoad, 4, 4);
     SDValue Ops[] = { Store, FIdx };
-    Ld = DAG.getMemIntrinsicNode(PPCISD::LFIWAX, dl,
-                                 DAG.getVTList(MVT::f64, MVT::Other), Ops, 2,
-                                 MVT::i32, MMO);
+    Ld = DAG.getMemIntrinsicNode(Op.getOpcode() == ISD::UINT_TO_FP ?
+                                   PPCISD::LFIWZX : PPCISD::LFIWAX,
+                                 dl, DAG.getVTList(MVT::f64, MVT::Other),
+                                 Ops, 2, MVT::i32, MMO);
   } else {
+    assert(PPCSubTarget.isPPC64() &&
+           "i32->FP without LFIWAX supported only on PPC64");
+
     int FrameIdx = FrameInfo->CreateStackObject(8, 8, false);
     SDValue FIdx = DAG.getFrameIndex(FrameIdx, PtrVT);
 
@@ -4848,8 +4905,8 @@ SDValue PPCTargetLowering::LowerSINT_TO_FP(SDValue Op,
   }
 
   // FCFID it and return it.
-  SDValue FP = DAG.getNode(PPCISD::FCFID, dl, MVT::f64, Ld);
-  if (Op.getValueType() == MVT::f32)
+  SDValue FP = DAG.getNode(FCFOp, dl, FCFTy, Ld);
+  if (Op.getValueType() == MVT::f32 && !PPCSubTarget.hasFPCVT())
     FP = DAG.getNode(ISD::FP_ROUND, dl, MVT::f32, FP, DAG.getIntPtrConstant(0));
   return FP;
 }
@@ -5651,7 +5708,8 @@ SDValue PPCTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   case ISD::FP_TO_UINT:
   case ISD::FP_TO_SINT:         return LowerFP_TO_INT(Op, DAG,
                                                        Op.getDebugLoc());
-  case ISD::SINT_TO_FP:         return LowerSINT_TO_FP(Op, DAG);
+  case ISD::UINT_TO_FP:
+  case ISD::SINT_TO_FP:         return LowerINT_TO_FP(Op, DAG);
   case ISD::FLT_ROUNDS_:        return LowerFLT_ROUNDS_(Op, DAG);
 
   // Lower 64-bit shifts.
diff --git a/lib/Target/PowerPC/PPCISelLowering.h b/lib/Target/PowerPC/PPCISelLowering.h
index e93a183a6ad..6690899e5d2 100644
--- a/lib/Target/PowerPC/PPCISelLowering.h
+++ b/lib/Target/PowerPC/PPCISelLowering.h
@@ -36,11 +36,19 @@ namespace llvm {
       /// was temporarily in the f64 operand.
       FCFID,
 
+      /// Newer FCFID[US] integer-to-floating-point conversion instructions for
+      /// unsigned integers and single-precision outputs.
+      FCFIDU, FCFIDS, FCFIDUS,
+
       /// FCTI[D,W]Z - The FCTIDZ and FCTIWZ instructions, taking an f32 or f64
       /// operand, producing an f64 value containing the integer representation
       /// of that FP value.
       FCTIDZ, FCTIWZ,
 
+      /// Newer FCTI[D,W]UZ floating-point-to-integer conversion instructions for
+      /// unsigned integers.
+      FCTIDUZ, FCTIWUZ,
+
       // VMADDFP, VNMSUBFP - The VMADDFP and VNMSUBFP instructions, taking
       // three v4f32 operands and producing a v4f32 result.
       VMADDFP, VNMSUBFP,
@@ -247,6 +255,11 @@ namespace llvm {
       /// destination 64-bit register.
       LFIWAX,
 
+      /// GPRC, CHAIN = LFIWZX CHAIN, Ptr - This is a floating-point
+      /// load which zero-extends from a 32-bit integer value into the
+      /// destination 64-bit register.
+      LFIWZX,
+
       /// G8RC = ADDIS_TOC_HA %X2, Symbol - For medium and large code model,
       /// produces an ADDIS8 instruction that adds the TOC base register to
       /// sym@toc@ha.
@@ -494,7 +507,7 @@ namespace llvm {
                                       const PPCSubtarget &Subtarget) const;
     SDValue LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerFP_TO_INT(SDValue Op, SelectionDAG &DAG, DebugLoc dl) const;
-    SDValue LowerSINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
+    SDValue LowerINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerFLT_ROUNDS_(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerSHL_PARTS(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerSRL_PARTS(SDValue Op, SelectionDAG &DAG) const;
diff --git a/lib/Target/PowerPC/PPCInstr64Bit.td b/lib/Target/PowerPC/PPCInstr64Bit.td
index 61702cf916a..fa5b65f0ba2 100644
--- a/lib/Target/PowerPC/PPCInstr64Bit.td
+++ b/lib/Target/PowerPC/PPCInstr64Bit.td
@@ -859,6 +859,22 @@ def FCFID  : XForm_26<63, 846, (outs F8RC:$frD), (ins F8RC:$frB),
 def FCTIDZ : XForm_26<63, 815, (outs F8RC:$frD), (ins F8RC:$frB),
                       "fctidz $frD, $frB", FPGeneral,
                       [(set f64:$frD, (PPCfctidz f64:$frB))]>, isPPC64;
+
+def FCFIDU  : XForm_26<63, 974, (outs F8RC:$frD), (ins F8RC:$frB),
+                      "fcfidu $frD, $frB", FPGeneral,
+                      [(set f64:$frD, (PPCfcfidu f64:$frB))]>, isPPC64;
+def FCFIDS  : XForm_26<59, 846, (outs F4RC:$frD), (ins F8RC:$frB),
+                      "fcfids $frD, $frB", FPGeneral,
+                      [(set f32:$frD, (PPCfcfids f64:$frB))]>, isPPC64;
+def FCFIDUS : XForm_26<59, 974, (outs F4RC:$frD), (ins F8RC:$frB),
+                      "fcfidus $frD, $frB", FPGeneral,
+                      [(set f32:$frD, (PPCfcfidus f64:$frB))]>, isPPC64;
+def FCTIDUZ : XForm_26<63, 943, (outs F8RC:$frD), (ins F8RC:$frB),
+                      "fctiduz $frD, $frB", FPGeneral,
+                      [(set f64:$frD, (PPCfctiduz f64:$frB))]>, isPPC64;
+def FCTIWUZ : XForm_26<63, 143, (outs F8RC:$frD), (ins F8RC:$frB),
+                      "fctiwuz $frD, $frB", FPGeneral,
+                      [(set f64:$frD, (PPCfctiwuz f64:$frB))]>, isPPC64;
 }
 
 
diff --git a/lib/Target/PowerPC/PPCInstrInfo.td b/lib/Target/PowerPC/PPCInstrInfo.td
index 478e6127ab0..067f5aacfaa 100644
--- a/lib/Target/PowerPC/PPCInstrInfo.td
+++ b/lib/Target/PowerPC/PPCInstrInfo.td
@@ -20,7 +20,7 @@ include "PPCInstrFormats.td"
 def SDT_PPCstfiwx : SDTypeProfile<0, 2, [ // stfiwx
   SDTCisVT<0, f64>, SDTCisPtrTy<1>
 ]>;
-def SDT_PPClfiwax : SDTypeProfile<1, 1, [ // lfiwax
+def SDT_PPClfiwx : SDTypeProfile<1, 1, [ // lfiw[az]x
   SDTCisVT<0, f64>, SDTCisPtrTy<1>
 ]>;
 
@@ -62,12 +62,19 @@ def SDT_PPCTC_ret : SDTypeProfile<0, 2, [
 // PowerPC specific DAG Nodes.
 //
 
-def PPCfcfid  : SDNode<"PPCISD::FCFID" , SDTFPUnaryOp, []>;
+def PPCfcfid  : SDNode<"PPCISD::FCFID",   SDTFPUnaryOp, []>;
+def PPCfcfidu : SDNode<"PPCISD::FCFIDU",  SDTFPUnaryOp, []>;
+def PPCfcfids : SDNode<"PPCISD::FCFIDS",  SDTFPRoundOp, []>;
+def PPCfcfidus: SDNode<"PPCISD::FCFIDUS", SDTFPRoundOp, []>;
 def PPCfctidz : SDNode<"PPCISD::FCTIDZ", SDTFPUnaryOp, []>;
 def PPCfctiwz : SDNode<"PPCISD::FCTIWZ", SDTFPUnaryOp, []>;
+def PPCfctiduz: SDNode<"PPCISD::FCTIDUZ",SDTFPUnaryOp, []>;
+def PPCfctiwuz: SDNode<"PPCISD::FCTIWUZ",SDTFPUnaryOp, []>;
 def PPCstfiwx : SDNode<"PPCISD::STFIWX", SDT_PPCstfiwx,
                        [SDNPHasChain, SDNPMayStore]>;
-def PPClfiwax : SDNode<"PPCISD::LFIWAX", SDT_PPClfiwax,
+def PPClfiwax : SDNode<"PPCISD::LFIWAX", SDT_PPClfiwx,
+                       [SDNPHasChain, SDNPMayLoad]>;
+def PPClfiwzx : SDNode<"PPCISD::LFIWZX", SDT_PPClfiwx,
                        [SDNPHasChain, SDNPMayLoad]>;
 
 // Extract FPSCR (not modeled at the DAG level).
@@ -853,6 +860,9 @@ def LFDX   : XForm_25<31, 599, (outs F8RC:$frD), (ins memrr:$src),
 def LFIWAX : XForm_25<31, 855, (outs F8RC:$frD), (ins memrr:$src),
                       "lfiwax $frD, $src", LdStLFD,
                       [(set f64:$frD, (PPClfiwax xoaddr:$src))]>;
+def LFIWZX : XForm_25<31, 887, (outs F8RC:$frD), (ins memrr:$src),
+                      "lfiwzx $frD, $src", LdStLFD,
+                      [(set f64:$frD, (PPClfiwzx xoaddr:$src))]>;
 }
 
 //===----------------------------------------------------------------------===//
diff --git a/lib/Target/PowerPC/PPCSubtarget.cpp b/lib/Target/PowerPC/PPCSubtarget.cpp
index 57e18ed07ea..1b7150fd37d 100644
--- a/lib/Target/PowerPC/PPCSubtarget.cpp
+++ b/lib/Target/PowerPC/PPCSubtarget.cpp
@@ -41,6 +41,7 @@ PPCSubtarget::PPCSubtarget(const std::string &TT, const std::string &CPU,
   , HasSTFIWX(false)
   , HasLFIWAX(false)
   , HasFPRND(false)
+  , HasFPCVT(false)
   , HasISEL(false)
   , HasPOPCNTD(false)
   , HasLDBRX(false)
diff --git a/lib/Target/PowerPC/PPCSubtarget.h b/lib/Target/PowerPC/PPCSubtarget.h
index 3958bc9c006..d5dfa1e8e14 100644
--- a/lib/Target/PowerPC/PPCSubtarget.h
+++ b/lib/Target/PowerPC/PPCSubtarget.h
@@ -80,6 +80,7 @@ protected:
   bool HasSTFIWX;
   bool HasLFIWAX;
   bool HasFPRND;
+  bool HasFPCVT;
   bool HasISEL;
   bool HasPOPCNTD;
   bool HasLDBRX;
@@ -161,6 +162,7 @@ public:
   bool hasSTFIWX() const { return HasSTFIWX; }
   bool hasLFIWAX() const { return HasLFIWAX; }
   bool hasFPRND() const { return HasFPRND; }
+  bool hasFPCVT() const { return HasFPCVT; }
   bool hasAltivec() const { return HasAltivec; }
   bool hasQPX() const { return HasQPX; }
   bool hasMFOCRF() const { return HasMFOCRF; }
diff --git a/test/CodeGen/PowerPC/float-to-int.ll b/test/CodeGen/PowerPC/float-to-int.ll
new file mode 100644
index 00000000000..ebd0903358d
--- /dev/null
+++ b/test/CodeGen/PowerPC/float-to-int.ll
@@ -0,0 +1,92 @@
+; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 | FileCheck %s
+target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+define i64 @foo(float %a) nounwind {
+  %x = fptosi float %a to i64
+  ret i64 %x
+
+; CHECK: @foo
+; CHECK: fctidz [[REG:[0-9]+]], 1
+; CHECK: stfd [[REG]],
+; CHECK: ld 3,
+; CHECK: blr
+}
+
+define i64 @foo2(double %a) nounwind {
+  %x = fptosi double %a to i64
+  ret i64 %x
+
+; CHECK: @foo2
+; CHECK: fctidz [[REG:[0-9]+]], 1
+; CHECK: stfd [[REG]],
+; CHECK: ld 3,
+; CHECK: blr
+}
+
+define i64 @foo3(float %a) nounwind {
+  %x = fptoui float %a to i64
+  ret i64 %x
+
+; CHECK: @foo3
+; CHECK: fctiduz [[REG:[0-9]+]], 1
+; CHECK: stfd [[REG]],
+; CHECK: ld 3,
+; CHECK: blr
+}
+
+define i64 @foo4(double %a) nounwind {
+  %x = fptoui double %a to i64
+  ret i64 %x
+
+; CHECK: @foo4
+; CHECK: fctiduz [[REG:[0-9]+]], 1
+; CHECK: stfd [[REG]],
+; CHECK: ld 3,
+; CHECK: blr
+}
+
+define i32 @goo(float %a) nounwind {
+  %x = fptosi float %a to i32
+  ret i32 %x
+
+; CHECK: @goo
+; CHECK: fctiwz [[REG:[0-9]+]], 1
+; CHECK: stfiwx [[REG]],
+; CHECK: lwz 3,
+; CHECK: blr
+}
+
+define i32 @goo2(double %a) nounwind {
+  %x = fptosi double %a to i32
+  ret i32 %x
+
+; CHECK: @goo2
+; CHECK: fctiwz [[REG:[0-9]+]], 1
+; CHECK: stfiwx [[REG]],
+; CHECK: lwz 3,
+; CHECK: blr
+}
+
+define i32 @goo3(float %a) nounwind {
+  %x = fptoui float %a to i32
+  ret i32 %x
+
+; CHECK: @goo3
+; CHECK: fctiwuz [[REG:[0-9]+]], 1
+; CHECK: stfiwx [[REG]],
+; CHECK: lwz 3,
+; CHECK: blr
+}
+
+define i32 @goo4(double %a) nounwind {
+  %x = fptoui double %a to i32
+  ret i32 %x
+
+; CHECK: @goo4
+; CHECK: fctiwuz [[REG:[0-9]+]], 1
+; CHECK: stfiwx [[REG]],
+; CHECK: lwz 3,
+; CHECK: blr
+}
+
diff --git a/test/CodeGen/PowerPC/i32-to-float.ll b/test/CodeGen/PowerPC/i32-to-float.ll
index bed940c5de0..2707d0352de 100644
--- a/test/CodeGen/PowerPC/i32-to-float.ll
+++ b/test/CodeGen/PowerPC/i32-to-float.ll
@@ -1,4 +1,5 @@
 ; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=g5 | FileCheck %s
+; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr6 | FileCheck -check-prefix=CHECK-PWR6 %s
 ; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 | FileCheck -check-prefix=CHECK-A2 %s
 target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
 target triple = "powerpc64-unknown-linux-gnu"
@@ -16,11 +17,17 @@ entry:
 ; CHECK: frsp 1, [[REG3]]
 ; CHECK: blr
 
+; CHECK-PWR6: @foo
+; CHECK-PWR6: stw 3,
+; CHECK-PWR6: lfiwax [[REG:[0-9]+]],
+; CHECK-PWR6: fcfid [[REG2:[0-9]+]], [[REG]]
+; CHECK-PWR6: frsp 1, [[REG2]]
+; CHECK-PWR6: blr
+
 ; CHECK-A2: @foo
 ; CHECK-A2: stw 3,
 ; CHECK-A2: lfiwax [[REG:[0-9]+]],
-; CHECK-A2: fcfid [[REG2:[0-9]+]], [[REG]]
-; CHECK-A2: frsp 1, [[REG2]]
+; CHECK-A2: fcfids 1, [[REG]]
 ; CHECK-A2: blr
 }
 
@@ -36,6 +43,12 @@ entry:
 ; CHECK: fcfid 1, [[REG2]]
 ; CHECK: blr
 
+; CHECK-PWR6: @goo
+; CHECK-PWR6: stw 3,
+; CHECK-PWR6: lfiwax [[REG:[0-9]+]],
+; CHECK-PWR6: fcfid 1, [[REG]]
+; CHECK-PWR6: blr
+
 ; CHECK-A2: @goo
 ; CHECK-A2: stw 3,
 ; CHECK-A2: lfiwax [[REG:[0-9]+]],
@@ -43,3 +56,27 @@ entry:
 ; CHECK-A2: blr
 }
 
+define float @foou(i32 %a) nounwind {
+entry:
+  %x = uitofp i32 %a to float
+  ret float %x
+
+; CHECK-A2: @foou
+; CHECK-A2: stw 3,
+; CHECK-A2: lfiwzx [[REG:[0-9]+]],
+; CHECK-A2: fcfidus 1, [[REG]]
+; CHECK-A2: blr
+}
+
+define double @goou(i32 %a) nounwind {
+entry:
+  %x = uitofp i32 %a to double
+  ret double %x
+
+; CHECK-A2: @goou
+; CHECK-A2: stw 3,
+; CHECK-A2: lfiwzx [[REG:[0-9]+]],
+; CHECK-A2: fcfidu 1, [[REG]]
+; CHECK-A2: blr
+}
+
diff --git a/test/CodeGen/PowerPC/i64-to-float.ll b/test/CodeGen/PowerPC/i64-to-float.ll
new file mode 100644
index 00000000000..b81d109e7f4
--- /dev/null
+++ b/test/CodeGen/PowerPC/i64-to-float.ll
@@ -0,0 +1,52 @@
+; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=a2 | FileCheck %s
+target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+define float @foo(i64 %a) nounwind {
+entry:
+  %x = sitofp i64 %a to float
+  ret float %x
+
+; CHECK: @foo
+; CHECK: std 3,
+; CHECK: lfd [[REG:[0-9]+]],
+; CHECK: fcfids 1, [[REG]]
+; CHECK: blr
+}
+
+define double @goo(i64 %a) nounwind {
+entry:
+  %x = sitofp i64 %a to double
+  ret double %x
+
+; CHECK: @goo
+; CHECK: std 3,
+; CHECK: lfd [[REG:[0-9]+]],
+; CHECK: fcfid 1, [[REG]]
+; CHECK: blr
+}
+
+define float @foou(i64 %a) nounwind {
+entry:
+  %x = uitofp i64 %a to float
+  ret float %x
+
+; CHECK: @foou
+; CHECK: std 3,
+; CHECK: lfd [[REG:[0-9]+]],
+; CHECK: fcfidus 1, [[REG]]
+; CHECK: blr
+}
+
+define double @goou(i64 %a) nounwind {
+entry:
+  %x = uitofp i64 %a to double
+  ret double %x
+
+; CHECK: @goou
+; CHECK: std 3,
+; CHECK: lfd [[REG:[0-9]+]],
+; CHECK: fcfidu 1, [[REG]]
+; CHECK: blr
+}
+
diff --git a/test/CodeGen/PowerPC/i64_fp_round.ll b/test/CodeGen/PowerPC/i64_fp_round.ll
index 5ae1be8953c..d2a3239ab86 100644
--- a/test/CodeGen/PowerPC/i64_fp_round.ll
+++ b/test/CodeGen/PowerPC/i64_fp_round.ll
@@ -1,4 +1,4 @@
-; RUN: llc -mcpu=pwr7 < %s | FileCheck %s
+; RUN: llc -mcpu=pwr7 -mattr=-fpcvt < %s | FileCheck %s
 target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32:64"
 target triple = "powerpc64-unknown-linux-gnu"
 
@@ -22,6 +22,6 @@ entry:
 ; Also check that with -enable-unsafe-fp-math we do not get that extra
 ; code sequence.  Simply verify that there is no "isel" present.
 
-; RUN: llc -mcpu=pwr7 -enable-unsafe-fp-math < %s | FileCheck %s -check-prefix=UNSAFE
+; RUN: llc -mcpu=pwr7 -mattr=-fpcvt -enable-unsafe-fp-math < %s | FileCheck %s -check-prefix=UNSAFE
 ; CHECK-UNSAFE-NOT: isel
 
diff --git a/test/CodeGen/PowerPC/stfiwx-2.ll b/test/CodeGen/PowerPC/stfiwx-2.ll
index c49b25cc230..345f1c93e8d 100644
--- a/test/CodeGen/PowerPC/stfiwx-2.ll
+++ b/test/CodeGen/PowerPC/stfiwx-2.ll
@@ -1,11 +1,14 @@
-; This cannot be a stfiwx
-; RUN: llc < %s -march=ppc32 -mcpu=g5 | grep stb
-; RUN: llc < %s -march=ppc32 -mcpu=g5 | not grep stfiwx
+; RUN: llc < %s -march=ppc32 -mcpu=g5 | FileCheck %s
 
 define void @test(float %F, i8* %P) {
 	%I = fptosi float %F to i32
 	%X = trunc i32 %I to i8
 	store i8 %X, i8* %P
 	ret void
+; CHECK: fctiwz 0, 1
+; CHECK: stfiwx 0, 0, 4
+; CHECK: lwz 4, 12(1)
+; CHECK: stb 4, 0(3)
+; CHECK: blr
 }