ConstantFolding- Trunc, rint and nearbyint

[chakshu.grover8]

Summary

Allow constfolding of llvm.trunc.*, llvm.rint.* and llvm.nearbyint.* intrinsics
This patch const folds llvm.trunc.*, llvm.rint.* and llvm.nearbyint.* intrinsics whenever feasible.

[chakshu.grover8]

Abandoned as it accidently got submitted from multiple accounts

lib/Analysis/ConstantFolding.cpp

bool llvm::canConstantFoldCallTo(const Function *F) {
   case Intrinsic::log10:
   case Intrinsic::exp:
   case Intrinsic::exp2:
   case Intrinsic::floor:
   case Intrinsic::ceil:
   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:
   case Intrinsic::ctpop:
   case Intrinsic::ctlz:
   case Intrinsic::cttz:
   case Intrinsic::fma:
   case Intrinsic::fmuladd:
if (ConstantFP *Op = dyn_cast<ConstantFP>(Operands[0])) {
         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:
           return ConstantFoldFP(cos, V, Ty);
+        case Intrinsic::trunc:
+          return ConstantFoldFP(trunc, V, Ty);
+        case Intrinsic::rint:
+          return ConstantFoldFP(rint, V, Ty);
+        case Intrinsic::nearbyint:
+          return ConstantFoldFP(nearbyint, V, Ty);
       }
 
       if (!TLI)
         return nullptr;
 
       switch (Name[0]) {
       case 'a':
         if (Name == "acos" && TLI->has(LibFunc::acos))

test/Transforms/InstCombine/intrinsics.ll

 declare %ov.result.32 @llvm.umul.with.overflow.i32(i32, i32) nounwind readnone
 declare double @llvm.powi.f64(double, i32) nounwind readonly
 declare i32 @llvm.cttz.i32(i32, i1) nounwind readnone
 declare i32 @llvm.ctlz.i32(i32, i1) nounwind readnone
 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.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)
   %y = extractvalue %overflow.result %x, 0
   ret i8 %y
 ; CHECK-LABEL: @uaddtest1(
 ; CHECK-NEXT: %y = add i8 %A, %B
 ; CHECK-NEXT: ret i8 %y

 entry:
   %B = tail call double @llvm.sin.f64(double 0.0) nounwind
   store volatile double %B, double* %P
 
   ret void
 ; CHECK-LABEL: @sin(
 ; CHECK: store volatile double 0.000000e+00, double* %P
 }
+
+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
+}