[VPlan] Support fast in FMF in VPRecipeWithIRFlags.

In current FastMathFlags implementation, we need to explicit set the
flags to fast. Otherwise it will show all the sub-flags in the FMF.

Author: ElvisWang123

llvm/lib/Transforms/Vectorize/VPlan.h

@@ -614,6 +614,7 @@ class VPRecipeWithIRFlags : public VPSingleDefRecipe {
     char AllowReciprocal : 1;
     char AllowContract : 1;
     char ApproxFunc : 1;
+    char Fast : 1;
 
     FastMathFlagsTy(const FastMathFlags &FMF);
   };

llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp

@@ -360,6 +360,7 @@ FastMathFlags VPRecipeWithIRFlags::getFastMathFlags() const {
   assert(OpType == OperationType::FPMathOp &&
          "recipe doesn't have fast math flags");
   FastMathFlags Res;
+  Res.setFast(FMFs.Fast);
   Res.setAllowReassoc(FMFs.AllowReassoc);
   Res.setNoNaNs(FMFs.NoNaNs);
   Res.setNoInfs(FMFs.NoInfs);
@@ -1393,6 +1394,7 @@ VPRecipeWithIRFlags::FastMathFlagsTy::FastMathFlagsTy(
   AllowReciprocal = FMF.allowReciprocal();
   AllowContract = FMF.allowContract();
   ApproxFunc = FMF.approxFunc();
+  Fast = FMF.isFast();
 }
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)

llvm/test/Transforms/LoopVectorize/AArch64/widen-call-with-intrinsic-or-libfunc.ll

@@ -26,7 +26,7 @@ target triple = "arm64-apple-ios"
 ; CHECK-NEXT:     vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%gep.src>
 ; CHECK-NEXT:     WIDEN ir<%l> = load vp<[[VEC_PTR]]>
 ; CHECK-NEXT:     WIDEN-CAST ir<%conv> = fpext ir<%l> to double
-; CHECK-NEXT:     WIDEN-CALL ir<%s> = call reassoc nnan ninf nsz arcp contract afn @llvm.sin.f64(ir<%conv>) (using library function: __simd_sin_v2f64)
+; CHECK-NEXT:     WIDEN-CALL ir<%s> = call fast @llvm.sin.f64(ir<%conv>) (using library function: __simd_sin_v2f64)
 ; CHECK-NEXT:     REPLICATE ir<%gep.dst> = getelementptr inbounds ir<%dst>, vp<[[STEPS]]>
 ; CHECK-NEXT:     REPLICATE store ir<%s>, ir<%gep.dst>
 ; CHECK-NEXT:     EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]>
@@ -72,7 +72,7 @@ target triple = "arm64-apple-ios"
 ; CHECK-NEXT:     vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%gep.src>
 ; CHECK-NEXT:     WIDEN ir<%l> = load vp<[[VEC_PTR]]>
 ; CHECK-NEXT:     WIDEN-CAST ir<%conv> = fpext ir<%l> to double
-; CHECK-NEXT:     WIDEN-INTRINSIC ir<%s> = call reassoc nnan ninf nsz arcp contract afn llvm.sin(ir<%conv>)
+; CHECK-NEXT:     WIDEN-INTRINSIC ir<%s> = call fast llvm.sin(ir<%conv>)
 ; CHECK-NEXT:     REPLICATE ir<%gep.dst> = getelementptr inbounds ir<%dst>, vp<[[STEPS]]>
 ; CHECK-NEXT:     REPLICATE store ir<%s>, ir<%gep.dst>
 ; CHECK-NEXT:     EMIT vp<[[CAN_IV_NEXT:%.+]]> = add nuw vp<[[CAN_IV]]>, vp<[[VFxUF]]>

llvm/test/Transforms/LoopVectorize/vplan-printing.ll

@@ -800,7 +800,7 @@ define void @print_fast_math_flags(i64 %n, ptr noalias %y, ptr noalias %x, ptr %
 ; CHECK-NEXT:   vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%gep.y>
 ; CHECK-NEXT:   WIDEN ir<%lv> = load vp<[[VEC_PTR]]>
 ; CHECK-NEXT:   WIDEN ir<%add> = fadd nnan ir<%lv>, ir<1.000000e+00>
-; CHECK-NEXT:   WIDEN ir<%mul> = fmul reassoc nnan ninf nsz arcp contract afn ir<%add>, ir<2.000000e+00>
+; CHECK-NEXT:   WIDEN ir<%mul> = fmul fast ir<%add>, ir<2.000000e+00>
 ; CHECK-NEXT:   WIDEN ir<%div> = fdiv reassoc nsz contract ir<%mul>, ir<2.000000e+00>
 ; CHECK-NEXT:   CLONE ir<%gep.x> = getelementptr inbounds ir<%x>, vp<[[STEPS]]>
 ; CHECK-NEXT:   vp<[[VEC_PTR:%.+]]> = vector-pointer ir<%gep.x>
@@ -1224,8 +1224,8 @@ define void @print_select_with_fastmath_flags(ptr noalias %a, ptr noalias %b, pt
 ; CHECK-NEXT:     vp<[[PTR2:%.+]]> = vector-pointer ir<[[GEP2]]>
 ; CHECK-NEXT:     WIDEN ir<[[LD2:%.+]]> = load vp<[[PTR2]]>
 ; CHECK-NEXT:     WIDEN ir<[[FCMP:%.+]]> = fcmp ogt ir<[[LD1]]>, ir<[[LD2]]>
-; CHECK-NEXT:     WIDEN ir<[[FADD:%.+]]> = fadd reassoc nnan ninf nsz arcp contract afn ir<[[LD1]]>, ir<1.000000e+01>
-; CHECK-NEXT:     WIDEN-SELECT ir<[[SELECT:%.+]]> = select reassoc nnan ninf nsz arcp contract afn ir<[[FCMP]]>, ir<[[FADD]]>, ir<[[LD2]]>
+; CHECK-NEXT:     WIDEN ir<[[FADD:%.+]]> = fadd fast ir<[[LD1]]>, ir<1.000000e+01>
+; CHECK-NEXT:     WIDEN-SELECT ir<[[SELECT:%.+]]> = select fast ir<[[FCMP]]>, ir<[[FADD]]>, ir<[[LD2]]>
 ; CHECK-NEXT:     CLONE ir<[[GEP3:%.+]]> = getelementptr inbounds nuw ir<%a>, vp<[[ST]]>
 ; CHECK-NEXT:     vp<[[PTR3:%.+]]> = vector-pointer ir<[[GEP3]]>
 ; CHECK-NEXT:     WIDEN store vp<[[PTR3]]>, ir<[[SELECT]]>