propagate fast-math-flags on DAG nodes

After D10403, we had FMF in the DAG but disabled by default. Nick reported no crashing errors after some stress testing, 
so I enabled them at r243687. However, Escha soon notified us of a bug not covered by any in-tree regression tests: 
if we don't propagate the flags, we may fail to CSE DAG nodes because differing FMF causes them to not match. There is
one test case in this patch to prove that point.

This patch hopes to fix or leave a 'TODO' for all of the in-tree places where we create nodes that are FMF-capable. I 
did this by putting an assert in SelectionDAG.getNode() to find any FMF-capable node that was being created without FMF
( D11807 ). I then ran all regression tests and test-suite and confirmed that everything passes.

This patch exposes remaining work to get DAG FMF to be fully functional: (1) add the flags to non-binary nodes such as
FCMP, FMA and FNEG; (2) add the flags to intrinsics; (3) use the flags as conditions for transforms rather than the
current global settings.

Differential Revision: http://reviews.llvm.org/D12095

llvm-svn: 247815

7 files changed, 59 insertions, 15 deletions

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
index 212ae7ba74f..8300431ec01 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -1088,6 +1088,7 @@ SDValue AMDGPUTargetLowering::LowerIntrinsicLRP(SDValue Op,
                                                 SelectionDAG &DAG) const {
   SDLoc DL(Op);
   EVT VT = Op.getValueType();
+  // TODO: Should this propagate fast-math-flags?
   SDValue OneSubA = DAG.getNode(ISD::FSUB, DL, VT,
                                 DAG.getConstantFP(1.0f, DL, MVT::f32),
                                 Op.getOperand(1));
@@ -1602,6 +1603,7 @@ SDValue AMDGPUTargetLowering::LowerDIVREM24(SDValue Op, SelectionDAG &DAG, bool
   // float fb = (float)ib;
   SDValue fb = DAG.getNode(ToFp, DL, FltVT, ib);
 
+  // TODO: Should this propagate fast-math-flags?
   // float fq = native_divide(fa, fb);
   SDValue fq = DAG.getNode(ISD::FMUL, DL, FltVT,
                            fa, DAG.getNode(AMDGPUISD::RCP, DL, FltVT, fb));
@@ -1912,6 +1914,8 @@ SDValue AMDGPUTargetLowering::LowerFREM(SDValue Op, SelectionDAG &DAG) const {
   SDValue X = Op.getOperand(0);
   SDValue Y = Op.getOperand(1);
 
+  // TODO: Should this propagate fast-math-flags?
+
   SDValue Div = DAG.getNode(ISD::FDIV, SL, VT, X, Y);
   SDValue Floor = DAG.getNode(ISD::FTRUNC, SL, VT, Div);
   SDValue Mul = DAG.getNode(ISD::FMUL, SL, VT, Floor, Y);
@@ -1940,6 +1944,7 @@ SDValue AMDGPUTargetLowering::LowerFCEIL(SDValue Op, SelectionDAG &DAG) const {
   SDValue And = DAG.getNode(ISD::AND, SL, SetCCVT, Lt0, NeTrunc);
 
   SDValue Add = DAG.getNode(ISD::SELECT, SL, MVT::f64, And, One, Zero);
+  // TODO: Should this propagate fast-math-flags?
   return DAG.getNode(ISD::FADD, SL, MVT::f64, Trunc, Add);
 }
 
@@ -2017,6 +2022,8 @@ SDValue AMDGPUTargetLowering::LowerFRINT(SDValue Op, SelectionDAG &DAG) const {
   SDValue C1 = DAG.getConstantFP(C1Val, SL, MVT::f64);
   SDValue CopySign = DAG.getNode(ISD::FCOPYSIGN, SL, MVT::f64, C1, Src);
 
+  // TODO: Should this propagate fast-math-flags?
+
   SDValue Tmp1 = DAG.getNode(ISD::FADD, SL, MVT::f64, Src, CopySign);
   SDValue Tmp2 = DAG.getNode(ISD::FSUB, SL, MVT::f64, Tmp1, CopySign);
 
@@ -2046,6 +2053,8 @@ SDValue AMDGPUTargetLowering::LowerFROUND32(SDValue Op, SelectionDAG &DAG) const
 
   SDValue T = DAG.getNode(ISD::FTRUNC, SL, MVT::f32, X);
 
+  // TODO: Should this propagate fast-math-flags?
+
   SDValue Diff = DAG.getNode(ISD::FSUB, SL, MVT::f32, X, T);
 
   SDValue AbsDiff = DAG.getNode(ISD::FABS, SL, MVT::f32, Diff);
@@ -2156,6 +2165,7 @@ SDValue AMDGPUTargetLowering::LowerFFLOOR(SDValue Op, SelectionDAG &DAG) const {
   SDValue And = DAG.getNode(ISD::AND, SL, SetCCVT, Lt0, NeTrunc);
 
   SDValue Add = DAG.getNode(ISD::SELECT, SL, MVT::f64, And, NegOne, Zero);
+  // TODO: Should this propagate fast-math-flags?
   return DAG.getNode(ISD::FADD, SL, MVT::f64, Trunc, Add);
 }
 
@@ -2178,7 +2188,7 @@ SDValue AMDGPUTargetLowering::LowerINT_TO_FP64(SDValue Op, SelectionDAG &DAG,
 
   SDValue LdExp = DAG.getNode(AMDGPUISD::LDEXP, SL, MVT::f64, CvtHi,
                               DAG.getConstant(32, SL, MVT::i32));
-
+  // TODO: Should this propagate fast-math-flags?
   return DAG.getNode(ISD::FADD, SL, MVT::f64, LdExp, CvtLo);
 }
 
@@ -2203,6 +2213,7 @@ SDValue AMDGPUTargetLowering::LowerUINT_TO_FP(SDValue Op,
   SDValue Hi = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, MVT::i32, S0,
                            DAG.getConstant(1, DL, MVT::i32));
   SDValue FloatHi = DAG.getNode(ISD::UINT_TO_FP, DL, MVT::f32, Hi);
+  // TODO: Should this propagate fast-math-flags?
   FloatHi = DAG.getNode(ISD::FMUL, DL, MVT::f32, FloatHi,
                         DAG.getConstantFP(4294967296.0f, DL, MVT::f32)); // 2^32
   return DAG.getNode(ISD::FADD, DL, MVT::f32, FloatLo, FloatHi);
@@ -2229,7 +2240,7 @@ SDValue AMDGPUTargetLowering::LowerFP64_TO_INT(SDValue Op, SelectionDAG &DAG,
                                  MVT::f64);
   SDValue K1 = DAG.getConstantFP(BitsToDouble(UINT64_C(0xc1f0000000000000)), SL,
                                  MVT::f64);
-
+  // TODO: Should this propagate fast-math-flags?
   SDValue Mul = DAG.getNode(ISD::FMUL, SL, MVT::f64, Trunc, K0);
 
   SDValue FloorMul = DAG.getNode(ISD::FFLOOR, SL, MVT::f64, Mul);
diff --git a/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp b/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp
index ecda332ed66..5699941d735 100644
--- a/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp
@@ -946,6 +946,8 @@ SDValue R600TargetLowering::LowerTrig(SDValue Op, SelectionDAG &DAG) const {
   EVT VT = Op.getValueType();
   SDValue Arg = Op.getOperand(0);
   SDLoc DL(Op);
+
+  // TODO: Should this propagate fast-math-flags?
   SDValue FractPart = DAG.getNode(AMDGPUISD::FRACT, DL, VT,
       DAG.getNode(ISD::FADD, DL, VT,
         DAG.getNode(ISD::FMUL, DL, VT, Arg,
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index ef42a2972bf..d0830a9e583 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -1000,6 +1000,8 @@ SDValue SITargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
   SDLoc DL(Op);
   unsigned IntrinsicID = cast<ConstantSDNode>(Op.getOperand(0))->getZExtValue();
 
+  // TODO: Should this propagate fast-math-flags?
+
   switch (IntrinsicID) {
   case Intrinsic::r600_read_ngroups_x:
     return LowerParameter(DAG, VT, VT, DL, DAG.getEntryNode(),
@@ -1248,8 +1250,10 @@ SDValue SITargetLowering::LowerFastFDIV(SDValue Op, SelectionDAG &DAG) const {
   if (Unsafe) {
     // Turn into multiply by the reciprocal.
     // x / y -> x * (1.0 / y)
+    SDNodeFlags Flags;
+    Flags.setUnsafeAlgebra(true);
     SDValue Recip = DAG.getNode(AMDGPUISD::RCP, SL, VT, RHS);
-    return DAG.getNode(ISD::FMUL, SL, VT, LHS, Recip);
+    return DAG.getNode(ISD::FMUL, SL, VT, LHS, Recip, &Flags);
   }
 
   return SDValue();
@@ -1286,6 +1290,8 @@ SDValue SITargetLowering::LowerFDIV32(SDValue Op, SelectionDAG &DAG) const {
 
   SDValue r3 = DAG.getNode(ISD::SELECT, SL, MVT::f32, r2, K1, One);
 
+  // TODO: Should this propagate fast-math-flags?
+
   r1 = DAG.getNode(ISD::FMUL, SL, MVT::f32, RHS, r3);
 
   SDValue r0 = DAG.getNode(AMDGPUISD::RCP, SL, MVT::f32, r1);
@@ -1405,6 +1411,7 @@ SDValue SITargetLowering::LowerTrig(SDValue Op, SelectionDAG &DAG) const {
   SDLoc DL(Op);
   EVT VT = Op.getValueType();
   SDValue Arg = Op.getOperand(0);
+  // TODO: Should this propagate fast-math-flags?
   SDValue FractPart = DAG.getNode(AMDGPUISD::FRACT, DL, VT,
                                   DAG.getNode(ISD::FMUL, DL, VT, Arg,
                                               DAG.getConstantFP(0.5/M_PI, DL,
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index 61705fcdc01..7c9df0e7b50 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -6385,6 +6385,8 @@ static SDValue LowerMUL(SDValue Op, SelectionDAG &DAG) {
 
 static SDValue
 LowerSDIV_v4i8(SDValue X, SDValue Y, SDLoc dl, SelectionDAG &DAG) {
+  // TODO: Should this propagate fast-math-flags?
+
   // Convert to float
   // float4 xf = vcvt_f32_s32(vmovl_s16(a.lo));
   // float4 yf = vcvt_f32_s32(vmovl_s16(b.lo));
@@ -6415,6 +6417,8 @@ LowerSDIV_v4i8(SDValue X, SDValue Y, SDLoc dl, SelectionDAG &DAG) {
 
 static SDValue
 LowerSDIV_v4i16(SDValue N0, SDValue N1, SDLoc dl, SelectionDAG &DAG) {
+  // TODO: Should this propagate fast-math-flags?
+
   SDValue N2;
   // Convert to float.
   // float4 yf = vcvt_f32_s32(vmovl_s16(y));
@@ -6487,6 +6491,7 @@ static SDValue LowerSDIV(SDValue Op, SelectionDAG &DAG) {
 }
 
 static SDValue LowerUDIV(SDValue Op, SelectionDAG &DAG) {
+  // TODO: Should this propagate fast-math-flags?
   EVT VT = Op.getValueType();
   assert((VT == MVT::v4i16 || VT == MVT::v8i8) &&
          "unexpected type for custom-lowering ISD::UDIV");
diff --git a/llvm/lib/Target/Mips/MipsSEISelLowering.cpp b/llvm/lib/Target/Mips/MipsSEISelLowering.cpp
index b319fd07884..5167b6baf98 100644
--- a/llvm/lib/Target/Mips/MipsSEISelLowering.cpp
+++ b/llvm/lib/Target/Mips/MipsSEISelLowering.cpp
@@ -1786,9 +1786,11 @@ SDValue MipsSETargetLowering::lowerINTRINSIC_WO_CHAIN(SDValue Op,
     return DAG.getNode(ISD::UDIV, DL, Op->getValueType(0), Op->getOperand(1),
                        Op->getOperand(2));
   case Intrinsic::mips_fadd_w:
-  case Intrinsic::mips_fadd_d:
+  case Intrinsic::mips_fadd_d: {
+    // TODO: If intrinsics have fast-math-flags, propagate them.
     return DAG.getNode(ISD::FADD, DL, Op->getValueType(0), Op->getOperand(1),
                        Op->getOperand(2));
+  }
   // Don't lower mips_fcaf_[wd] since LLVM folds SETFALSE condcodes away
   case Intrinsic::mips_fceq_w:
   case Intrinsic::mips_fceq_d:
@@ -1831,9 +1833,11 @@ SDValue MipsSETargetLowering::lowerINTRINSIC_WO_CHAIN(SDValue Op,
     return DAG.getSetCC(DL, Op->getValueType(0), Op->getOperand(1),
                         Op->getOperand(2), ISD::SETUNE);
   case Intrinsic::mips_fdiv_w:
-  case Intrinsic::mips_fdiv_d:
+  case Intrinsic::mips_fdiv_d: {
+    // TODO: If intrinsics have fast-math-flags, propagate them.
     return DAG.getNode(ISD::FDIV, DL, Op->getValueType(0), Op->getOperand(1),
                        Op->getOperand(2));
+  }
   case Intrinsic::mips_ffint_u_w:
   case Intrinsic::mips_ffint_u_d:
     return DAG.getNode(ISD::UINT_TO_FP, DL, Op->getValueType(0),
@@ -1856,6 +1860,7 @@ SDValue MipsSETargetLowering::lowerINTRINSIC_WO_CHAIN(SDValue Op,
   }
   case Intrinsic::mips_fexp2_w:
   case Intrinsic::mips_fexp2_d: {
+    // TODO: If intrinsics have fast-math-flags, propagate them.
     EVT ResTy = Op->getValueType(0);
     return DAG.getNode(
         ISD::FMUL, SDLoc(Op), ResTy, Op->getOperand(1),
@@ -1869,11 +1874,14 @@ SDValue MipsSETargetLowering::lowerINTRINSIC_WO_CHAIN(SDValue Op,
     return DAG.getNode(ISD::FMA, SDLoc(Op), Op->getValueType(0),
                        Op->getOperand(1), Op->getOperand(2), Op->getOperand(3));
   case Intrinsic::mips_fmul_w:
-  case Intrinsic::mips_fmul_d:
+  case Intrinsic::mips_fmul_d: {
+    // TODO: If intrinsics have fast-math-flags, propagate them.
     return DAG.getNode(ISD::FMUL, DL, Op->getValueType(0), Op->getOperand(1),
                        Op->getOperand(2));
+  }
   case Intrinsic::mips_fmsub_w:
   case Intrinsic::mips_fmsub_d: {
+    // TODO: If intrinsics have fast-math-flags, propagate them.
     EVT ResTy = Op->getValueType(0);
     return DAG.getNode(ISD::FSUB, SDLoc(Op), ResTy, Op->getOperand(1),
                        DAG.getNode(ISD::FMUL, SDLoc(Op), ResTy,
@@ -1886,9 +1894,11 @@ SDValue MipsSETargetLowering::lowerINTRINSIC_WO_CHAIN(SDValue Op,
   case Intrinsic::mips_fsqrt_d:
     return DAG.getNode(ISD::FSQRT, DL, Op->getValueType(0), Op->getOperand(1));
   case Intrinsic::mips_fsub_w:
-  case Intrinsic::mips_fsub_d:
+  case Intrinsic::mips_fsub_d: {
+    // TODO: If intrinsics have fast-math-flags, propagate them.
     return DAG.getNode(ISD::FSUB, DL, Op->getValueType(0), Op->getOperand(1),
                        Op->getOperand(2));
+  }
   case Intrinsic::mips_ftrunc_u_w:
   case Intrinsic::mips_ftrunc_u_d:
     return DAG.getNode(ISD::FP_TO_UINT, DL, Op->getValueType(0),
diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 804aec92164..882af7580ee 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -5999,7 +5999,11 @@ SDValue PPCTargetLowering::LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const {
   if (!DAG.getTarget().Options.NoInfsFPMath ||
       !DAG.getTarget().Options.NoNaNsFPMath)
     return Op;
-
+  // TODO: Propagate flags from the select rather than global settings.
+  SDNodeFlags Flags;
+  Flags.setNoInfs(true);
+  Flags.setNoNaNs(true);
+  
   ISD::CondCode CC = cast<CondCodeSDNode>(Op.getOperand(4))->get();
 
   EVT ResVT = Op.getValueType();
@@ -6049,7 +6053,7 @@ SDValue PPCTargetLowering::LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const {
   case ISD::SETNE:
     std::swap(TV, FV);
   case ISD::SETEQ:
-    Cmp = DAG.getNode(ISD::FSUB, dl, CmpVT, LHS, RHS);
+    Cmp = DAG.getNode(ISD::FSUB, dl, CmpVT, LHS, RHS, &Flags);
     if (Cmp.getValueType() == MVT::f32)   // Comparison is always 64-bits
       Cmp = DAG.getNode(ISD::FP_EXTEND, dl, MVT::f64, Cmp);
     Sel1 = DAG.getNode(PPCISD::FSEL, dl, ResVT, Cmp, TV, FV);
@@ -6059,25 +6063,25 @@ SDValue PPCTargetLowering::LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const {
                        DAG.getNode(ISD::FNEG, dl, MVT::f64, Cmp), Sel1, FV);
   case ISD::SETULT:
   case ISD::SETLT:
-    Cmp = DAG.getNode(ISD::FSUB, dl, CmpVT, LHS, RHS);
+    Cmp = DAG.getNode(ISD::FSUB, dl, CmpVT, LHS, RHS, &Flags);
     if (Cmp.getValueType() == MVT::f32)   // Comparison is always 64-bits
       Cmp = DAG.getNode(ISD::FP_EXTEND, dl, MVT::f64, Cmp);
     return DAG.getNode(PPCISD::FSEL, dl, ResVT, Cmp, FV, TV);
   case ISD::SETOGE:
   case ISD::SETGE:
-    Cmp = DAG.getNode(ISD::FSUB, dl, CmpVT, LHS, RHS);
+    Cmp = DAG.getNode(ISD::FSUB, dl, CmpVT, LHS, RHS, &Flags);
     if (Cmp.getValueType() == MVT::f32)   // Comparison is always 64-bits
       Cmp = DAG.getNode(ISD::FP_EXTEND, dl, MVT::f64, Cmp);
     return DAG.getNode(PPCISD::FSEL, dl, ResVT, Cmp, TV, FV);
   case ISD::SETUGT:
   case ISD::SETGT:
-    Cmp = DAG.getNode(ISD::FSUB, dl, CmpVT, RHS, LHS);
+    Cmp = DAG.getNode(ISD::FSUB, dl, CmpVT, RHS, LHS, &Flags);
     if (Cmp.getValueType() == MVT::f32)   // Comparison is always 64-bits
       Cmp = DAG.getNode(ISD::FP_EXTEND, dl, MVT::f64, Cmp);
     return DAG.getNode(PPCISD::FSEL, dl, ResVT, Cmp, FV, TV);
   case ISD::SETOLE:
   case ISD::SETLE:
-    Cmp = DAG.getNode(ISD::FSUB, dl, CmpVT, RHS, LHS);
+    Cmp = DAG.getNode(ISD::FSUB, dl, CmpVT, RHS, LHS, &Flags);
     if (Cmp.getValueType() == MVT::f32)   // Comparison is always 64-bits
       Cmp = DAG.getNode(ISD::FP_EXTEND, dl, MVT::f64, Cmp);
     return DAG.getNode(PPCISD::FSEL, dl, ResVT, Cmp, TV, FV);
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index ee7c445d0b1..00b88c68d5c 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -12229,6 +12229,7 @@ SDValue X86TargetLowering::LowerUINT_TO_FP_i64(SDValue Op,
                   MachinePointerInfo::getConstantPool(DAG.getMachineFunction()),
                   false, false, false, 16);
   SDValue XR2F = DAG.getBitcast(MVT::v2f64, Unpck1);
+  // TODO: Are there any fast-math-flags to propagate here?
   SDValue Sub = DAG.getNode(ISD::FSUB, dl, MVT::v2f64, XR2F, CLod1);
   SDValue Result;
 
@@ -12278,6 +12279,7 @@ SDValue X86TargetLowering::LowerUINT_TO_FP_i32(SDValue Op,
                   DAG.getBitcast(MVT::v2f64, Or), DAG.getIntPtrConstant(0, dl));
 
   // Subtract the bias.
+  // TODO: Are there any fast-math-flags to propagate here?
   SDValue Sub = DAG.getNode(ISD::FSUB, dl, MVT::f64, Or, Bias);
 
   // Handle final rounding.
@@ -12390,6 +12392,7 @@ static SDValue lowerUINT_TO_FP_vXi32(SDValue Op, SelectionDAG &DAG,
 
   //     float4 fhi = (float4) hi - (0x1.0p39f + 0x1.0p23f);
   SDValue HighBitcast = DAG.getBitcast(VecFloatVT, High);
+  // TODO: Are there any fast-math-flags to propagate here?
   SDValue FHigh =
       DAG.getNode(ISD::FADD, DL, VecFloatVT, HighBitcast, VecCstFAdd);
   //     return (float4) lo + fhi;
@@ -12509,6 +12512,7 @@ SDValue X86TargetLowering::LowerUINT_TO_FP(SDValue Op,
       MachinePointerInfo::getConstantPool(DAG.getMachineFunction()), MVT::f32,
       false, false, false, 4);
   // Extend everything to 80 bits to force it to be done on x87.
+  // TODO: Are there any fast-math-flags to propagate here?
   SDValue Add = DAG.getNode(ISD::FADD, dl, MVT::f80, Fild, Fudge);
   return DAG.getNode(ISD::FP_ROUND, dl, DstVT, Add,
                      DAG.getIntPtrConstant(0, dl));
@@ -15847,8 +15851,8 @@ static SDValue LowerINTRINSIC_WO_CHAIN(SDValue Op, const X86Subtarget *Subtarget
                                       Mask, PassThru, Subtarget, DAG);
         }
       }
-      return getVectorMaskingNode(DAG.getNode(IntrData->Opc0, dl, VT,
-                                              Src1,Src2),
+      // TODO: Intrinsics should have fast-math-flags to propagate.
+      return getVectorMaskingNode(DAG.getNode(IntrData->Opc0, dl, VT,Src1,Src2),
                                   Mask, PassThru, Subtarget, DAG);
     }
     case INTR_TYPE_2OP_MASK_RM: {
@@ -19266,6 +19270,7 @@ void X86TargetLowering::ReplaceNodeResults(SDNode *N,
     SDValue Or = DAG.getNode(ISD::OR, dl, MVT::v2i64, ZExtIn,
                              DAG.getBitcast(MVT::v2i64, VBias));
     Or = DAG.getBitcast(MVT::v2f64, Or);
+    // TODO: Are there any fast-math-flags to propagate here?
     SDValue Sub = DAG.getNode(ISD::FSUB, dl, MVT::v2f64, Or, VBias);
     Results.push_back(DAG.getNode(X86ISD::VFPROUND, dl, MVT::v4f32, Sub));
     return;