[PowerPC][FP128] Fix the incorrect signature for math library call

[steven.zhang]

Summary

The runtime library has two family library implementation for ppc_fp128 and fp128. For IBM Long double(ppc_fp128), it is suffixed with 'l', i.e(sqrtl). For IEEE Long double(fp128), it is suffixed with "ieee128" or "f128". We miss to map several libcall for IEEE Long double.

[steven.zhang]

Rebase.

[qiucf]

llvm/lib/CodeGen/TargetLoweringBase.cpp

150

I see in llvm/include/llvm/IR/RuntimeLibcalls.def:

HANDLE_LIBCALL(FPTOSINT_F128_I128, "__fixtfti")
HANDLE_LIBCALL(FPTOSINT_PPCF128_I128, "__fixtfti")

So only PPC uses KF instead of TF for IEEE f128?

And it seems compiler-rt doesn't have impl for __fixkfti now.

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

1308

Do we need to unify those names - *f128 or __*ieee128?

1314

Should be __llroundieee128

1317

Also, __llrintieee128.

[steven.zhang]

llvm/lib/CodeGen/TargetLoweringBase.cpp

150

Yes. See the comments in this code.

// For IEEE quad-precision libcall names, PPC uses "kf" instead of "tf".

Though the compiler-rt didn't have the implementation now, we still need to fix it.

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

1308

Good suggestion. Though the ieee128 version works, we should use f128 to align with old name convention.

1314

oops, typo.

[steven.zhang]

Address comments.

[steven.zhang]

Gentle ping.

[qiucf]

LGTM. Thanks for the fix.

llvm/lib/CodeGen/TargetLoweringBase.cpp

for (int LC = 0; LC < RTLIB::UNKNOWN_LIBCALL; ++LC)
     setLibcallCallingConv((RTLIB::Libcall)LC, CallingConv::C);
 
   // For IEEE quad-precision libcall names, PPC uses "kf" instead of "tf".
   if (TT.getArch() == Triple::ppc || TT.isPPC64()) {
     setLibcallName(RTLIB::ADD_F128, "__addkf3");
     setLibcallName(RTLIB::SUB_F128, "__subkf3");
     setLibcallName(RTLIB::MUL_F128, "__mulkf3");
     setLibcallName(RTLIB::DIV_F128, "__divkf3");
+    setLibcallName(RTLIB::POWI_F128, "__powikf2");
     setLibcallName(RTLIB::FPEXT_F32_F128, "__extendsfkf2");
     setLibcallName(RTLIB::FPEXT_F64_F128, "__extenddfkf2");
     setLibcallName(RTLIB::FPROUND_F128_F32, "__trunckfsf2");
     setLibcallName(RTLIB::FPROUND_F128_F64, "__trunckfdf2");
     setLibcallName(RTLIB::FPTOSINT_F128_I32, "__fixkfsi");
     setLibcallName(RTLIB::FPTOSINT_F128_I64, "__fixkfdi");
+    setLibcallName(RTLIB::FPTOSINT_F128_I128, "__fixkfti");
     setLibcallName(RTLIB::FPTOUINT_F128_I32, "__fixunskfsi");
     setLibcallName(RTLIB::FPTOUINT_F128_I64, "__fixunskfdi");
+    setLibcallName(RTLIB::FPTOUINT_F128_I128, "__fixunskfti");
     setLibcallName(RTLIB::SINTTOFP_I32_F128, "__floatsikf");
     setLibcallName(RTLIB::SINTTOFP_I64_F128, "__floatdikf");
+    setLibcallName(RTLIB::SINTTOFP_I128_F128, "__floattikf");
     setLibcallName(RTLIB::UINTTOFP_I32_F128, "__floatunsikf");
     setLibcallName(RTLIB::UINTTOFP_I64_F128, "__floatundikf");
+    setLibcallName(RTLIB::UINTTOFP_I128_F128, "__floatuntikf");
     setLibcallName(RTLIB::OEQ_F128, "__eqkf2");
     setLibcallName(RTLIB::UNE_F128, "__nekf2");
     setLibcallName(RTLIB::OGE_F128, "__gekf2");
     setLibcallName(RTLIB::OLT_F128, "__ltkf2");
     setLibcallName(RTLIB::OLE_F128, "__lekf2");
     setLibcallName(RTLIB::OGT_F128, "__gtkf2");
     setLibcallName(RTLIB::UO_F128, "__unordkf2");
   }

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

   setLibcallName(RTLIB::LOG10_F128, "log10f128");
   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");
+  setLibcallName(RTLIB::SQRT_F128, "__sqrtieee128");
+  setLibcallName(RTLIB::CEIL_F128, "__ceilieee128");
+  setLibcallName(RTLIB::FLOOR_F128, "__floorieee128");
+  setLibcallName(RTLIB::TRUNC_F128, "__truncieee128");
+  setLibcallName(RTLIB::ROUND_F128, "__roundieee128");
+  setLibcallName(RTLIB::LROUND_F128, "__lroundieee128");
+  setLibcallName(RTLIB::LLROUND_F128, "__lroundieee128");
+  setLibcallName(RTLIB::RINT_F128, "__rintieee128");
+  setLibcallName(RTLIB::LRINT_F128, "__lrintieee128");
+  setLibcallName(RTLIB::LLRINT_F128, "__lrintieee128");
+  setLibcallName(RTLIB::NEARBYINT_F128, "__nearbyintieee128");
+  setLibcallName(RTLIB::FMA_F128, "__fmaieee128");
 
   // With 32 condition bits, we don't need to sink (and duplicate) compares
   // aggressively in CodeGenPrep.
   if (Subtarget.useCRBits()) {
     setHasMultipleConditionRegisters();
     setJumpIsExpensive();
   }
 

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

 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl sqrtl
+; CHECK-P8-NEXT:    bl __sqrtieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    stvx v2, 0, r30
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl ceill
+; CHECK-P8-NEXT:    bl __ceilieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    stvx v2, 0, r30
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl floorl
+; CHECK-P8-NEXT:    bl __floorieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    stvx v2, 0, r30
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl truncl
+; CHECK-P8-NEXT:    bl __truncieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    stvx v2, 0, r30
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl roundl
+; CHECK-P8-NEXT:    bl __roundieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    stvx v2, 0, r30
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset lr, 16
 ; CHECK-NEXT:    .cfi_offset r30, -16
 ; CHECK-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std r0, 16(r1)
 ; CHECK-NEXT:    stdu r1, -48(r1)
 ; CHECK-NEXT:    lxv v2, 0(r3)
 ; CHECK-NEXT:    mr r30, r4
-; CHECK-NEXT:    bl lroundl
+; CHECK-NEXT:    bl __lroundieee128
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    stw r3, 0(r30)
 ; CHECK-NEXT:    addi r1, r1, 48
 ; CHECK-NEXT:    ld r0, 16(r1)
 ; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-P8-LABEL: qpLRound:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl lroundl
+; CHECK-P8-NEXT:    bl __lroundieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    stw r3, 0(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset lr, 16
 ; CHECK-NEXT:    .cfi_offset r30, -16
 ; CHECK-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std r0, 16(r1)
 ; CHECK-NEXT:    stdu r1, -48(r1)
 ; CHECK-NEXT:    lxv v2, 0(r3)
 ; CHECK-NEXT:    mr r30, r4
-; CHECK-NEXT:    bl llroundl
+; CHECK-NEXT:    bl __lroundieee128
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    std r3, 0(r30)
 ; CHECK-NEXT:    addi r1, r1, 48
 ; CHECK-NEXT:    ld r0, 16(r1)
 ; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-P8-LABEL: qpLLRound:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl llroundl
+; CHECK-P8-NEXT:    bl __lroundieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    std r3, 0(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl rintl
+; CHECK-P8-NEXT:    bl __rintieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    stvx v2, 0, r30
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset lr, 16
 ; CHECK-NEXT:    .cfi_offset r30, -16
 ; CHECK-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std r0, 16(r1)
 ; CHECK-NEXT:    stdu r1, -48(r1)
 ; CHECK-NEXT:    lxv v2, 0(r3)
 ; CHECK-NEXT:    mr r30, r4
-; CHECK-NEXT:    bl lrintl
+; CHECK-NEXT:    bl __lrintieee128
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    stw r3, 0(r30)
 ; CHECK-NEXT:    addi r1, r1, 48
 ; CHECK-NEXT:    ld r0, 16(r1)
 ; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-P8-LABEL: qpLRint:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl lrintl
+; CHECK-P8-NEXT:    bl __lrintieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    stw r3, 0(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-NEXT:    .cfi_offset lr, 16
 ; CHECK-NEXT:    .cfi_offset r30, -16
 ; CHECK-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std r0, 16(r1)
 ; CHECK-NEXT:    stdu r1, -48(r1)
 ; CHECK-NEXT:    lxv v2, 0(r3)
 ; CHECK-NEXT:    mr r30, r4
-; CHECK-NEXT:    bl llrintl
+; CHECK-NEXT:    bl __lrintieee128
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    std r3, 0(r30)
 ; CHECK-NEXT:    addi r1, r1, 48
 ; CHECK-NEXT:    ld r0, 16(r1)
 ; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-P8-LABEL: qpLLRint:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl llrintl
+; CHECK-P8-NEXT:    bl __lrintieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    std r3, 0(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    mr r30, r4
-; CHECK-P8-NEXT:    bl nearbyintl
+; CHECK-P8-NEXT:    bl __nearbyintieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    stvx v2, 0, r30
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:

 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    lvx v2, 0, r3
 ; CHECK-P8-NEXT:    lvx v3, 0, r4
 ; CHECK-P8-NEXT:    lvx v4, 0, r5
 ; CHECK-P8-NEXT:    mr r30, r6
-; CHECK-P8-NEXT:    bl fmal
+; CHECK-P8-NEXT:    bl __fmaieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    stvx v2, 0, r30
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:
   %0 = load fp128, fp128* %a, align 16
   %1 = load fp128, fp128* %b, align 16
   %2 = load fp128, fp128* %c, align 16
   %3 = tail call fp128 @llvm.fma.f128(fp128 %0, fp128 %1, fp128 %2)
   store fp128 %3, fp128* %res, align 16
   ret void
 }
 declare fp128 @llvm.fma.f128(fp128, fp128, fp128)

llvm/test/CodeGen/PowerPC/f128-conv.ll

 ; CHECK-NEXT:    .cfi_offset lr, 16
 ; CHECK-NEXT:    .cfi_offset r30, -16
 ; CHECK-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std r0, 16(r1)
 ; CHECK-NEXT:    stdu r1, -48(r1)
 ; CHECK-NEXT:    mr r30, r3
 ; CHECK-NEXT:    mr r3, r4
 ; CHECK-NEXT:    mr r4, r5
-; CHECK-NEXT:    bl __floattitf
+; CHECK-NEXT:    bl __floattikf
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    stxv v2, 0(r30)
 ; CHECK-NEXT:    addi r1, r1, 48
 ; CHECK-NEXT:    ld r0, 16(r1)
 ; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-P8-LABEL: sdwConv2qp_01:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    mr r30, r3
 ; CHECK-P8-NEXT:    mr r3, r4
 ; CHECK-P8-NEXT:    mr r4, r5
-; CHECK-P8-NEXT:    bl __floattitf
+; CHECK-P8-NEXT:    bl __floattikf
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    std r4, 8(r30)
 ; CHECK-P8-NEXT:    std r3, 0(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr

 ; CHECK-NEXT:    .cfi_offset lr, 16
 ; CHECK-NEXT:    .cfi_offset r30, -16
 ; CHECK-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-NEXT:    std r0, 16(r1)
 ; CHECK-NEXT:    stdu r1, -48(r1)
 ; CHECK-NEXT:    mr r30, r3
 ; CHECK-NEXT:    mr r3, r4
 ; CHECK-NEXT:    mr r4, r5
-; CHECK-NEXT:    bl __floatuntitf
+; CHECK-NEXT:    bl __floatuntikf
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    stxv v2, 0(r30)
 ; CHECK-NEXT:    addi r1, r1, 48
 ; CHECK-NEXT:    ld r0, 16(r1)
 ; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-P8-LABEL: udwConv2qp_01:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 48
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    .cfi_offset r30, -16
 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    mr r30, r3
 ; CHECK-P8-NEXT:    mr r3, r4
 ; CHECK-P8-NEXT:    mr r4, r5
-; CHECK-P8-NEXT:    bl __floatuntitf
+; CHECK-P8-NEXT:    bl __floatuntikf
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    std r4, 8(r30)
 ; CHECK-P8-NEXT:    std r3, 0(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr

 ; CHECK-LABEL: qpConv2i128:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    mflr r0
 ; CHECK-NEXT:    std r0, 16(r1)
 ; CHECK-NEXT:    stdu r1, -32(r1)
 ; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset lr, 16
 ; CHECK-NEXT:    lxv v2, 0(r3)
-; CHECK-NEXT:    bl __fixtfti
+; CHECK-NEXT:    bl __fixkfti
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    addi r1, r1, 32
 ; CHECK-NEXT:    ld r0, 16(r1)
 ; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-P8-LABEL: qpConv2i128:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    ld r5, 0(r3)
 ; CHECK-P8-NEXT:    ld r4, 8(r3)
 ; CHECK-P8-NEXT:    mr r3, r5
-; CHECK-P8-NEXT:    bl __fixtfti
+; CHECK-P8-NEXT:    bl __fixkfti
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    addi r1, r1, 32
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:
   %0 = load fp128, fp128* %a, align 16
   %conv = fptosi fp128 %0 to i128
   ret i128 %conv
 }
 
 ; Function Attrs: norecurse nounwind readonly
 define i128 @qpConv2ui128(fp128* nocapture readonly %a) {
 ; CHECK-LABEL: qpConv2ui128:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    mflr r0
 ; CHECK-NEXT:    std r0, 16(r1)
 ; CHECK-NEXT:    stdu r1, -32(r1)
 ; CHECK-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-NEXT:    .cfi_offset lr, 16
 ; CHECK-NEXT:    lxv v2, 0(r3)
-; CHECK-NEXT:    bl __fixunstfti
+; CHECK-NEXT:    bl __fixunskfti
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    addi r1, r1, 32
 ; CHECK-NEXT:    ld r0, 16(r1)
 ; CHECK-NEXT:    mtlr r0
 ; CHECK-NEXT:    blr
 ;
 ; CHECK-P8-LABEL: qpConv2ui128:
 ; CHECK-P8:       # %bb.0: # %entry
 ; CHECK-P8-NEXT:    mflr r0
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -32(r1)
 ; CHECK-P8-NEXT:    .cfi_def_cfa_offset 32
 ; CHECK-P8-NEXT:    .cfi_offset lr, 16
 ; CHECK-P8-NEXT:    ld r5, 0(r3)
 ; CHECK-P8-NEXT:    ld r4, 8(r3)
 ; CHECK-P8-NEXT:    mr r3, r5
-; CHECK-P8-NEXT:    bl __fixunstfti
+; CHECK-P8-NEXT:    bl __fixunskfti
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    addi r1, r1, 32
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:
   %0 = load fp128, fp128* %a, align 16
   %conv = fptoui fp128 %0 to i128
   ret i128 %conv
 }
 

llvm/test/CodeGen/PowerPC/f128-rounding.ll

 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    ld r5, 0(r3)
 ; CHECK-P8-NEXT:    ld r6, 8(r3)
 ; CHECK-P8-NEXT:    mr r30, r4
 ; CHECK-P8-NEXT:    mr r3, r5
 ; CHECK-P8-NEXT:    mr r4, r6
-; CHECK-P8-NEXT:    bl truncl
+; CHECK-P8-NEXT:    bl __truncieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    std r3, 0(r30)
 ; CHECK-P8-NEXT:    std r4, 8(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr

 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    ld r5, 0(r3)
 ; CHECK-P8-NEXT:    ld r6, 8(r3)
 ; CHECK-P8-NEXT:    mr r30, r4
 ; CHECK-P8-NEXT:    mr r3, r5
 ; CHECK-P8-NEXT:    mr r4, r6
-; CHECK-P8-NEXT:    bl rintl
+; CHECK-P8-NEXT:    bl __rintieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    std r3, 0(r30)
 ; CHECK-P8-NEXT:    std r4, 8(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr

 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    ld r5, 0(r3)
 ; CHECK-P8-NEXT:    ld r6, 8(r3)
 ; CHECK-P8-NEXT:    mr r30, r4
 ; CHECK-P8-NEXT:    mr r3, r5
 ; CHECK-P8-NEXT:    mr r4, r6
-; CHECK-P8-NEXT:    bl nearbyintl
+; CHECK-P8-NEXT:    bl __nearbyintieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    std r3, 0(r30)
 ; CHECK-P8-NEXT:    std r4, 8(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr

 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    ld r5, 0(r3)
 ; CHECK-P8-NEXT:    ld r6, 8(r3)
 ; CHECK-P8-NEXT:    mr r30, r4
 ; CHECK-P8-NEXT:    mr r3, r5
 ; CHECK-P8-NEXT:    mr r4, r6
-; CHECK-P8-NEXT:    bl roundl
+; CHECK-P8-NEXT:    bl __roundieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    std r3, 0(r30)
 ; CHECK-P8-NEXT:    std r4, 8(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr

 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    ld r5, 0(r3)
 ; CHECK-P8-NEXT:    ld r6, 8(r3)
 ; CHECK-P8-NEXT:    mr r30, r4
 ; CHECK-P8-NEXT:    mr r3, r5
 ; CHECK-P8-NEXT:    mr r4, r6
-; CHECK-P8-NEXT:    bl floorl
+; CHECK-P8-NEXT:    bl __floorieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    std r3, 0(r30)
 ; CHECK-P8-NEXT:    std r4, 8(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr

 ; CHECK-P8-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
 ; CHECK-P8-NEXT:    std r0, 16(r1)
 ; CHECK-P8-NEXT:    stdu r1, -48(r1)
 ; CHECK-P8-NEXT:    ld r5, 0(r3)
 ; CHECK-P8-NEXT:    ld r6, 8(r3)
 ; CHECK-P8-NEXT:    mr r30, r4
 ; CHECK-P8-NEXT:    mr r3, r5
 ; CHECK-P8-NEXT:    mr r4, r6
-; CHECK-P8-NEXT:    bl ceill
+; CHECK-P8-NEXT:    bl __ceilieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    std r3, 0(r30)
 ; CHECK-P8-NEXT:    std r4, 8(r30)
 ; CHECK-P8-NEXT:    addi r1, r1, 48
 ; CHECK-P8-NEXT:    ld r0, 16(r1)
 ; CHECK-P8-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
 ; CHECK-P8-NEXT:    mtlr r0
 ; CHECK-P8-NEXT:    blr
 entry:
   %0 = load fp128, fp128* %a, align 16
   %1 = tail call fp128 @llvm.ceil.f128(fp128 %0)
   store fp128 %1, fp128* %res, align 16
   ret void
 }
 declare fp128     @llvm.ceil.f128(fp128 %Val)
 

llvm/test/CodeGen/PowerPC/fp-strict-conv-f128.ll

 define i128 @q_to_i128(fp128 %m) #0 {
 ; P8-LABEL: q_to_i128:
 ; P8:       # %bb.0: # %entry
 ; P8-NEXT:    mflr r0
 ; P8-NEXT:    std r0, 16(r1)
 ; P8-NEXT:    stdu r1, -112(r1)
 ; P8-NEXT:    .cfi_def_cfa_offset 112
 ; P8-NEXT:    .cfi_offset lr, 16
-; P8-NEXT:    bl __fixtfti
+; P8-NEXT:    bl __fixkfti
 ; P8-NEXT:    nop
 ; P8-NEXT:    addi r1, r1, 112
 ; P8-NEXT:    ld r0, 16(r1)
 ; P8-NEXT:    mtlr r0
 ; P8-NEXT:    blr
 ;
 ; P9-LABEL: q_to_i128:
 ; P9:       # %bb.0: # %entry
 ; P9-NEXT:    mflr r0
 ; P9-NEXT:    std r0, 16(r1)
 ; P9-NEXT:    stdu r1, -32(r1)
 ; P9-NEXT:    .cfi_def_cfa_offset 32
 ; P9-NEXT:    .cfi_offset lr, 16
-; P9-NEXT:    bl __fixtfti
+; P9-NEXT:    bl __fixkfti
 ; P9-NEXT:    nop
 ; P9-NEXT:    addi r1, r1, 32
 ; P9-NEXT:    ld r0, 16(r1)
 ; P9-NEXT:    mtlr r0
 ; P9-NEXT:    blr
 ;
 ; NOVSX-LABEL: q_to_i128:
 ; NOVSX:       # %bb.0: # %entry
 ; NOVSX-NEXT:    mflr r0
 ; NOVSX-NEXT:    std r0, 16(r1)
 ; NOVSX-NEXT:    stdu r1, -32(r1)
 ; NOVSX-NEXT:    .cfi_def_cfa_offset 32
 ; NOVSX-NEXT:    .cfi_offset lr, 16
-; NOVSX-NEXT:    bl __fixtfti
+; NOVSX-NEXT:    bl __fixkfti
 ; NOVSX-NEXT:    nop
 ; NOVSX-NEXT:    addi r1, r1, 32
 ; NOVSX-NEXT:    ld r0, 16(r1)
 ; NOVSX-NEXT:    mtlr r0
 ; NOVSX-NEXT:    blr
 entry:
   %conv = tail call i128 @llvm.experimental.constrained.fptosi.i128.f128(fp128 %m, metadata !"fpexcept.strict") #0
   ret i128 %conv
 }
 
 define i128 @q_to_u128(fp128 %m) #0 {
 ; P8-LABEL: q_to_u128:
 ; P8:       # %bb.0: # %entry
 ; P8-NEXT:    mflr r0
 ; P8-NEXT:    std r0, 16(r1)
 ; P8-NEXT:    stdu r1, -112(r1)
 ; P8-NEXT:    .cfi_def_cfa_offset 112
 ; P8-NEXT:    .cfi_offset lr, 16
-; P8-NEXT:    bl __fixunstfti
+; P8-NEXT:    bl __fixunskfti
 ; P8-NEXT:    nop
 ; P8-NEXT:    addi r1, r1, 112
 ; P8-NEXT:    ld r0, 16(r1)
 ; P8-NEXT:    mtlr r0
 ; P8-NEXT:    blr
 ;
 ; P9-LABEL: q_to_u128:
 ; P9:       # %bb.0: # %entry
 ; P9-NEXT:    mflr r0
 ; P9-NEXT:    std r0, 16(r1)
 ; P9-NEXT:    stdu r1, -32(r1)
 ; P9-NEXT:    .cfi_def_cfa_offset 32
 ; P9-NEXT:    .cfi_offset lr, 16
-; P9-NEXT:    bl __fixunstfti
+; P9-NEXT:    bl __fixunskfti
 ; P9-NEXT:    nop
 ; P9-NEXT:    addi r1, r1, 32
 ; P9-NEXT:    ld r0, 16(r1)
 ; P9-NEXT:    mtlr r0
 ; P9-NEXT:    blr
 ;
 ; NOVSX-LABEL: q_to_u128:
 ; NOVSX:       # %bb.0: # %entry
 ; NOVSX-NEXT:    mflr r0
 ; NOVSX-NEXT:    std r0, 16(r1)
 ; NOVSX-NEXT:    stdu r1, -32(r1)
 ; NOVSX-NEXT:    .cfi_def_cfa_offset 32
 ; NOVSX-NEXT:    .cfi_offset lr, 16
-; NOVSX-NEXT:    bl __fixunstfti
+; NOVSX-NEXT:    bl __fixunskfti
 ; NOVSX-NEXT:    nop
 ; NOVSX-NEXT:    addi r1, r1, 32
 ; NOVSX-NEXT:    ld r0, 16(r1)
 ; NOVSX-NEXT:    mtlr r0
 ; NOVSX-NEXT:    blr
 entry:
   %conv = tail call i128 @llvm.experimental.constrained.fptoui.i128.f128(fp128 %m, metadata !"fpexcept.strict") #0
   ret i128 %conv

llvm/test/CodeGen/PowerPC/recipest.ll

 }
 
 define fp128 @hoo5_fmf(fp128 %a) #1 {
 ; CHECK-P7-LABEL: hoo5_fmf:
 ; CHECK-P7:       # %bb.0:
 ; CHECK-P7-NEXT:    mflr 0
 ; CHECK-P7-NEXT:    std 0, 16(1)
 ; CHECK-P7-NEXT:    stdu 1, -112(1)
-; CHECK-P7-NEXT:    bl sqrtl
+; CHECK-P7-NEXT:    bl __sqrtieee128
 ; CHECK-P7-NEXT:    nop
 ; CHECK-P7-NEXT:    addi 1, 1, 112
 ; CHECK-P7-NEXT:    ld 0, 16(1)
 ; CHECK-P7-NEXT:    mtlr 0
 ; CHECK-P7-NEXT:    blr
 ;
 ; CHECK-P8-LABEL: hoo5_fmf:
 ; CHECK-P8:       # %bb.0:
 ; CHECK-P8-NEXT:    mflr 0
 ; CHECK-P8-NEXT:    std 0, 16(1)
 ; CHECK-P8-NEXT:    stdu 1, -32(1)
-; CHECK-P8-NEXT:    bl sqrtl
+; CHECK-P8-NEXT:    bl __sqrtieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    addi 1, 1, 32
 ; CHECK-P8-NEXT:    ld 0, 16(1)
 ; CHECK-P8-NEXT:    mtlr 0
 ; CHECK-P8-NEXT:    blr
 ;
 ; CHECK-P9-LABEL: hoo5_fmf:
 ; CHECK-P9:       # %bb.0:
 ; CHECK-P9-NEXT:    xssqrtqp 2, 2
 ; CHECK-P9-NEXT:    blr
   %r = call reassoc ninf afn fp128 @llvm.sqrt.f128(fp128 %a)
   ret fp128 %r
 }
 
 define fp128 @hoo5_safe(fp128 %a) #1 {
 ; CHECK-P7-LABEL: hoo5_safe:
 ; CHECK-P7:       # %bb.0:
 ; CHECK-P7-NEXT:    mflr 0
 ; CHECK-P7-NEXT:    std 0, 16(1)
 ; CHECK-P7-NEXT:    stdu 1, -112(1)
-; CHECK-P7-NEXT:    bl sqrtl
+; CHECK-P7-NEXT:    bl __sqrtieee128
 ; CHECK-P7-NEXT:    nop
 ; CHECK-P7-NEXT:    addi 1, 1, 112
 ; CHECK-P7-NEXT:    ld 0, 16(1)
 ; CHECK-P7-NEXT:    mtlr 0
 ; CHECK-P7-NEXT:    blr
 ;
 ; CHECK-P8-LABEL: hoo5_safe:
 ; CHECK-P8:       # %bb.0:
 ; CHECK-P8-NEXT:    mflr 0
 ; CHECK-P8-NEXT:    std 0, 16(1)
 ; CHECK-P8-NEXT:    stdu 1, -32(1)
-; CHECK-P8-NEXT:    bl sqrtl
+; CHECK-P8-NEXT:    bl __sqrtieee128
 ; CHECK-P8-NEXT:    nop
 ; CHECK-P8-NEXT:    addi 1, 1, 32
 ; CHECK-P8-NEXT:    ld 0, 16(1)
 ; CHECK-P8-NEXT:    mtlr 0
 ; CHECK-P8-NEXT:    blr
 ;
 ; CHECK-P9-LABEL: hoo5_safe:
 ; CHECK-P9:       # %bb.0:
 ; CHECK-P9-NEXT:    xssqrtqp 2, 2
 ; CHECK-P9-NEXT:    blr
   %r = call fp128 @llvm.sqrt.f128(fp128 %a)
   ret fp128 %r
 }
 
 attributes #0 = { nounwind "reciprocal-estimates"="sqrtf:0,sqrtd:0" }
 attributes #1 = { nounwind "denormal-fp-math"="preserve-sign,preserve-sign" }