[Power9]Legalize and emit code for quad-precision convert from double-precision

[lei]

Summary

Legalize and emit code for quad-precision floating point operation xscvdpqp and add option to guard the quad precision operation support.

[lei]

fix checks in testcase.

[nemanjai]

LGTM.

llvm/trunk/lib/Target/PowerPC/PPCISelLowering.cpp

 cl::desc("disable setting the node scheduling preference to ILP on PPC"), cl::Hidden);
 
 static cl::opt<bool> DisablePPCUnaligned("disable-ppc-unaligned",
 cl::desc("disable unaligned load/store generation on PPC"), cl::Hidden);
 
 static cl::opt<bool> DisableSCO("disable-ppc-sco",
 cl::desc("disable sibling call optimization on ppc"), cl::Hidden);
 
+static cl::opt<bool> EnableQuadPrecision("enable-ppc-quad-precision",
+cl::desc("enable quad precision float support on ppc"), cl::Hidden);
+
 STATISTIC(NumTailCalls, "Number of tail calls");
 STATISTIC(NumSiblingCalls, "Number of sibling calls");
 
 static bool isNByteElemShuffleMask(ShuffleVectorSDNode *, unsigned, int);
 
 // FIXME: Remove this once the bug has been fixed!
 extern cl::opt<bool> ANDIGlueBug;
 
if (Subtarget.hasP9Vector()) {
 
       // 128 bit shifts can be accomplished via 3 instructions for SHL and
       // SRL, but not for SRA because of the instructions available:
       // VS{RL} and VS{RL}O.
       setOperationAction(ISD::SHL, MVT::v1i128, Legal);
       setOperationAction(ISD::SRL, MVT::v1i128, Legal);
       setOperationAction(ISD::SRA, MVT::v1i128, Expand);
 
+      if (EnableQuadPrecision) {
         addRegisterClass(MVT::f128, &PPC::VRRCRegClass);
         setOperationAction(ISD::FADD, MVT::f128, Legal);
         setOperationAction(ISD::FSUB, MVT::f128, Legal);
         setOperationAction(ISD::FDIV, MVT::f128, Legal);
         setOperationAction(ISD::FMUL, MVT::f128, Legal);
+        setOperationAction(ISD::FP_EXTEND, MVT::f128, Legal);
+        setLoadExtAction(ISD::EXTLOAD, MVT::f128, MVT::f64, Expand);
+      }
 
     }
 
     if (Subtarget.hasP9Altivec()) {
       setOperationAction(ISD::INSERT_VECTOR_ELT, MVT::v8i16, Custom);
       setOperationAction(ISD::INSERT_VECTOR_ELT, MVT::v16i8, Custom);
     }
   }

llvm/trunk/lib/Target/PowerPC/PPCInstrVSX.td

let AddedComplexity = 400, Predicates = [HasP9Vector] in {
   def XSCMPGTDP : XX3_XT5_XA5_XB5<60, 11, "xscmpgtdp", vsrc, vsfrc, vsfrc,
                                   IIC_FPCompare, []>;
 
   //===--------------------------------------------------------------------===//
   // Quad-Precision Floating-Point Conversion Instructions:
 
   // Convert DP -> QP
   def XSCVDPQP  : X_VT5_XO5_VB5_TyVB<63, 22, 836, "xscvdpqp", vfrc, []>;
+  def : Pat<(f128 (fpextend f64:$src)), (f128 (XSCVDPQP $src))>;
 
   // Round & Convert QP -> DP (dword[1] is set to zero)
   def XSCVQPDP  : X_VT5_XO5_VB5   <63, 20, 836, "xscvqpdp" , []>;
   def XSCVQPDPO : X_VT5_XO5_VB5_Ro<63, 20, 836, "xscvqpdpo", []>;
 
   // Truncate & Convert QP -> (Un)Signed (D)Word (dword[1] is set to zero)
   def XSCVQPSDZ : X_VT5_XO5_VB5<63, 25, 836, "xscvqpsdz", []>;
   def XSCVQPSWZ : X_VT5_XO5_VB5<63,  9, 836, "xscvqpswz", []>;

llvm/trunk/test/CodeGen/PowerPC/f128-arith.ll

-; RUN: llc -mcpu=pwr9 -mtriple=powerpc64le-unknown-unknown < %s | FileCheck %s
+; RUN: llc -mcpu=pwr9 -mtriple=powerpc64le-unknown-unknown \
+; RUN:   -enable-ppc-quad-precision < %s | FileCheck %s
 
 ; Function Attrs: norecurse nounwind
 define void @qpAdd(fp128* nocapture readonly %a, fp128* nocapture %res) {
 entry:
   %0 = load fp128, fp128* %a, align 16
   %add = fadd fp128 %0, %0
   store fp128 %add, fp128* %res, align 16
   ret void
entry:
   ret void
 
 ; CHECK-LABEL: qpNeg
 ; CHECK-NOT: bl __subtf3
 ; CHECK: xsnegqp
 ; CHECK: stxv
 ; CHECK: blr
 }
+
+; Function Attrs: norecurse nounwind
+define void @dpConv2qp(double* nocapture readonly %a, fp128* nocapture %res) {
+entry:
+  %0 = load double, double* %a, align 8
+  %conv = fpext double %0 to fp128
+  store fp128 %conv, fp128* %res, align 16
+  ret void
+; CHECK-LABEL: dpConv2qp
+; CHECK-NOT: bl __extenddftf2
+; CHECK: lxsd
+; CHECK: xscvdpqp
+; CHECK: blr
+}
+
+; Function Attrs: norecurse nounwind
+define void @dpConv2qp_02(double %a, fp128* nocapture %res) {
+entry:
+  %conv = fpext double %a to fp128
+  store fp128 %conv, fp128* %res, align 16
+  ret void
+; CHECK-LABEL: dpConv2qp_02
+; CHECK-NOT: bl __extenddftf2
+; CHECK: xxlor
+; CHECK: xscvdpqp
+; CHECK: blr
+}