Constfold trunc,rint,nearbyint,ceil and floor using APFloat

A patch by Chakshu Grover!
This patch allows constfolding of trunc,rint,nearbyint,ceil and floor intrinsics using APFloat class.
Differential Revision: http://reviews.llvm.org/D11144

llvm-svn: 242763

diff --git a/llvm/lib/Analysis/ConstantFolding.cpp b/llvm/lib/Analysis/ConstantFolding.cpp
index 02a5aef..bd9439e 100644 (file)
--- a/llvm/lib/Analysis/ConstantFolding.cpp
+++ b/llvm/lib/Analysis/ConstantFolding.cpp
@@ -1236,6 +1236,9 @@ bool llvm::canConstantFoldCallTo(const Function *F) {
   case Intrinsic::sqrt:
   case Intrinsic::sin:
   case Intrinsic::cos:
+  case Intrinsic::trunc:
+  case Intrinsic::rint:
+  case Intrinsic::nearbyint:
   case Intrinsic::pow:
   case Intrinsic::powi:
   case Intrinsic::bswap:
@@ -1422,6 +1425,36 @@ static Constant *ConstantFoldScalarCall(StringRef Name, unsigned IntrinsicID,
         return ConstantFP::get(Ty->getContext(), V);
       }
 
+      if (IntrinsicID == Intrinsic::floor) {
+        APFloat V = Op->getValueAPF();
+        V.roundToIntegral(APFloat::rmTowardNegative);
+        return ConstantFP::get(Ty->getContext(), V);
+      }
+
+      if (IntrinsicID == Intrinsic::ceil) {
+        APFloat V = Op->getValueAPF();
+        V.roundToIntegral(APFloat::rmTowardPositive);
+        return ConstantFP::get(Ty->getContext(), V);
+      }
+
+      if (IntrinsicID == Intrinsic::trunc) {
+        APFloat V = Op->getValueAPF();
+        V.roundToIntegral(APFloat::rmTowardZero);
+        return ConstantFP::get(Ty->getContext(), V);
+      }
+
+      if (IntrinsicID == Intrinsic::rint) {
+        APFloat V = Op->getValueAPF();
+        V.roundToIntegral(APFloat::rmNearestTiesToEven);
+        return ConstantFP::get(Ty->getContext(), V);
+      }
+
+      if (IntrinsicID == Intrinsic::nearbyint) {
+        APFloat V = Op->getValueAPF();
+        V.roundToIntegral(APFloat::rmNearestTiesToEven);
+        return ConstantFP::get(Ty->getContext(), V);
+      }
+
       /// We only fold functions with finite arguments. Folding NaN and inf is
       /// likely to be aborted with an exception anyway, and some host libms
       /// have known errors raising exceptions.
@@ -1448,10 +1481,6 @@ static Constant *ConstantFoldScalarCall(StringRef Name, unsigned IntrinsicID,
           return ConstantFoldFP(exp, V, Ty);
         case Intrinsic::exp2:
           return ConstantFoldFP(exp2, V, Ty);
-        case Intrinsic::floor:
-          return ConstantFoldFP(floor, V, Ty);
-        case Intrinsic::ceil:
-          return ConstantFoldFP(ceil, V, Ty);
         case Intrinsic::sin:
           return ConstantFoldFP(sin, V, Ty);
         case Intrinsic::cos:

diff --git a/llvm/test/Transforms/InstCombine/intrinsics.ll b/llvm/test/Transforms/InstCombine/intrinsics.ll
index bea0637..88f0324 100644 (file)
--- a/llvm/test/Transforms/InstCombine/intrinsics.ll
+++ b/llvm/test/Transforms/InstCombine/intrinsics.ll
@@ -19,6 +19,11 @@ declare i32 @llvm.ctpop.i32(i32) nounwind readnone
 declare i8 @llvm.ctlz.i8(i8, i1) nounwind readnone
 declare double @llvm.cos.f64(double %Val) nounwind readonly
 declare double @llvm.sin.f64(double %Val) nounwind readonly
+declare double @llvm.floor.f64(double %Val) nounwind readonly
+declare double @llvm.ceil.f64(double %Val) nounwind readonly
+declare double @llvm.trunc.f64(double %Val) nounwind readonly
+declare double @llvm.rint.f64(double %Val) nounwind readonly
+declare double @llvm.nearbyint.f64(double %Val) nounwind readonly
 
 define i8 @uaddtest1(i8 %A, i8 %B) {
   %x = call %overflow.result @llvm.uadd.with.overflow.i8(i8 %A, i8 %B)
@@ -447,3 +452,63 @@ entry:
 ; CHECK-LABEL: @sin(
 ; CHECK: store volatile double 0.000000e+00, double* %P
 }
+
+define void @floor(double *%P) {
+entry:
+  %B = tail call double @llvm.floor.f64(double 1.5) nounwind
+  store volatile double %B, double* %P
+  %C = tail call double @llvm.floor.f64(double -1.5) nounwind
+  store volatile double %C, double* %P
+  ret void
+; CHECK-LABEL: @floor(
+; CHECK: store volatile double 1.000000e+00, double* %P, align 8
+; CHECK: store volatile double -2.000000e+00, double* %P, align 8
+}
+
+define void @ceil(double *%P) {
+entry:
+  %B = tail call double @llvm.ceil.f64(double 1.5) nounwind
+  store volatile double %B, double* %P
+  %C = tail call double @llvm.ceil.f64(double -1.5) nounwind
+  store volatile double %C, double* %P
+  ret void
+; CHECK-LABEL: @ceil(
+; CHECK: store volatile double 2.000000e+00, double* %P, align 8
+; CHECK: store volatile double -1.000000e+00, double* %P, align 8
+}
+
+define void @trunc(double *%P) {
+entry:
+  %B = tail call double @llvm.trunc.f64(double 1.5) nounwind
+  store volatile double %B, double* %P
+  %C = tail call double @llvm.trunc.f64(double -1.5) nounwind
+  store volatile double %C, double* %P
+  ret void
+; CHECK-LABEL: @trunc(
+; CHECK: store volatile double 1.000000e+00, double* %P, align 8
+; CHECK: store volatile double -1.000000e+00, double* %P, align 8
+}
+
+define void @rint(double *%P) {
+entry:
+  %B = tail call double @llvm.rint.f64(double 1.5) nounwind
+  store volatile double %B, double* %P
+  %C = tail call double @llvm.rint.f64(double -1.5) nounwind
+  store volatile double %C, double* %P
+  ret void
+; CHECK-LABEL: @rint(
+; CHECK: store volatile double 2.000000e+00, double* %P, align 8
+; CHECK: store volatile double -2.000000e+00, double* %P, align 8
+}
+
+define void @nearbyint(double *%P) {
+entry:
+  %B = tail call double @llvm.nearbyint.f64(double 1.5) nounwind
+  store volatile double %B, double* %P
+  %C = tail call double @llvm.nearbyint.f64(double -1.5) nounwind
+  store volatile double %C, double* %P
+  ret void
+; CHECK-LABEL: @nearbyint(
+; CHECK: store volatile double 2.000000e+00, double* %P, align 8
+; CHECK: store volatile double -2.000000e+00, double* %P, align 8
+}