[Power9] Add __float128 library call for frem

[stefanp]

Summary

We do not have a hardware instruction for frem but we can call fmodf128 from libm.

[nemanjai]

LGTM.

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

if (Subtarget.hasP9Vector()) {
         setTruncStoreAction(MVT::f128, MVT::f64, Expand);
         setTruncStoreAction(MVT::f128, MVT::f32, Expand);
         setOperationAction(ISD::BITCAST, MVT::i128, Custom);
         // No implementation for these ops for PowerPC.
         setOperationAction(ISD::FSIN , MVT::f128, Expand);
         setOperationAction(ISD::FCOS , MVT::f128, Expand);
         setOperationAction(ISD::FPOW, MVT::f128, Expand);
         setOperationAction(ISD::FPOWI, MVT::f128, Expand);
+        setOperationAction(ISD::FREM, MVT::f128, Expand);
       }
 
     }
 
     if (Subtarget.hasP9Altivec()) {
       setOperationAction(ISD::INSERT_VECTOR_ELT, MVT::v8i16, Custom);
       setOperationAction(ISD::INSERT_VECTOR_ELT, MVT::v16i8, Custom);
     }
if (EnableQuadPrecision) {
     setLibcallName(RTLIB::EXP_F128, "expf128");
     setLibcallName(RTLIB::EXP2_F128, "exp2f128");
     setLibcallName(RTLIB::SIN_F128, "sinf128");
     setLibcallName(RTLIB::COS_F128, "cosf128");
     setLibcallName(RTLIB::POW_F128, "powf128");
     setLibcallName(RTLIB::FMIN_F128, "fminf128");
     setLibcallName(RTLIB::FMAX_F128, "fmaxf128");
     setLibcallName(RTLIB::POWI_F128, "__powikf2");
+    setLibcallName(RTLIB::REM_F128, "fmodf128");
   }
 
   // With 32 condition bits, we don't need to sink (and duplicate) compares
   // aggressively in CodeGenPrep.
   if (Subtarget.useCRBits()) {
     setHasMultipleConditionRegisters();
     setJumpIsExpensive();
   }

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

 entry:
   %0 = load fp128, fp128* %a, align 16
   %1 = load i32, i32* %b, align 8
   %2 = tail call fp128 @llvm.powi.f128(fp128 %0, i32 %1)
   store fp128 %2, fp128* %res, align 16
   ret void
 }
 declare fp128 @llvm.powi.f128(fp128 %Val, i32 %power)
+
+@a = common global fp128 0xL00000000000000000000000000000000, align 16
+@b = common global fp128 0xL00000000000000000000000000000000, align 16
+
+define fp128 @qp_frem() #0 {
+entry:
+  %0 = load fp128, fp128* @a, align 16
+  %1 = load fp128, fp128* @b, align 16
+  %rem = frem fp128 %0, %1
+  ret fp128 %rem
+; CHECK-LABEL: qp_frem
+; CHECK: bl fmodf128
+; CHECK: blr
+}