Index: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -9636,6 +9636,7 @@
             VecOp, Plan->getVPValue(R->getOperand(1))};
         VPInstruction *FMulRecipe =
             new VPInstruction(Instruction::FMul, FMulOps);
+        FMulRecipe->setFastMathFlags(R->getFastMathFlags());
         WidenRecipe->getParent()->insert(FMulRecipe,
                                          WidenRecipe->getIterator());
         VecOp = FMulRecipe;
Index: llvm/lib/Transforms/Vectorize/VPlan.h
===================================================================
--- llvm/lib/Transforms/Vectorize/VPlan.h
+++ llvm/lib/Transforms/Vectorize/VPlan.h
@@ -789,6 +789,7 @@
 private:
   typedef unsigned char OpcodeTy;
   OpcodeTy Opcode;
+  FastMathFlags FMF;
 
   /// Utility method serving execute(): generates a single instance of the
   /// modeled instruction.
@@ -870,6 +871,9 @@
       return true;
     }
   }
+
+  // Set the fast-math flags.
+  void setFastMathFlags(FastMathFlags FMFNew) { FMF = FMFNew; }
 };
 
 /// VPWidenRecipe is a recipe for producing a copy of vector type its
Index: llvm/lib/Transforms/Vectorize/VPlan.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/VPlan.cpp
+++ llvm/lib/Transforms/Vectorize/VPlan.cpp
@@ -718,6 +718,8 @@
 
 void VPInstruction::execute(VPTransformState &State) {
   assert(!State.Instance && "VPInstruction executing an Instance");
+  IRBuilderBase::FastMathFlagGuard FMFGuard(State.Builder);
+  State.Builder.setFastMathFlags(FMF);
   for (unsigned Part = 0; Part < State.UF; ++Part)
     generateInstruction(State, Part);
 }
Index: llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
+++ llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
@@ -483,10 +483,10 @@
 ; CHECK-ORDERED: [[WIDE_LOAD5:%.*]] = load <vscale x 8 x float>, <vscale x 8 x float>*
 ; CHECK-ORDERED: [[WIDE_LOAD6:%.*]] = load <vscale x 8 x float>, <vscale x 8 x float>*
 ; CHECK-ORDERED: [[WIDE_LOAD7:%.*]] = load <vscale x 8 x float>, <vscale x 8 x float>*
-; CHECK-ORDERED: [[FMUL:%.*]] = fmul <vscale x 8 x float> [[WIDE_LOAD]], [[WIDE_LOAD4]]
-; CHECK-ORDERED: [[FMUL1:%.*]] = fmul <vscale x 8 x float> [[WIDE_LOAD1]], [[WIDE_LOAD5]]
-; CHECK-ORDERED: [[FMUL2:%.*]] = fmul <vscale x 8 x float> [[WIDE_LOAD2]], [[WIDE_LOAD6]]
-; CHECK-ORDERED: [[FMUL3:%.*]] = fmul <vscale x 8 x float> [[WIDE_LOAD3]], [[WIDE_LOAD7]]
+; CHECK-ORDERED: [[FMUL:%.*]] = fmul nnan <vscale x 8 x float> [[WIDE_LOAD]], [[WIDE_LOAD4]]
+; CHECK-ORDERED: [[FMUL1:%.*]] = fmul nnan <vscale x 8 x float> [[WIDE_LOAD1]], [[WIDE_LOAD5]]
+; CHECK-ORDERED: [[FMUL2:%.*]] = fmul nnan <vscale x 8 x float> [[WIDE_LOAD2]], [[WIDE_LOAD6]]
+; CHECK-ORDERED: [[FMUL3:%.*]] = fmul nnan <vscale x 8 x float> [[WIDE_LOAD3]], [[WIDE_LOAD7]]
 ; CHECK-ORDERED: [[RDX:%.*]] = call nnan float @llvm.vector.reduce.fadd.nxv8f32(float [[VEC_PHI]], <vscale x 8 x float> [[FMUL]])
 ; CHECK-ORDERED: [[RDX1:%.*]] = call nnan float @llvm.vector.reduce.fadd.nxv8f32(float [[RDX]], <vscale x 8 x float> [[FMUL1]])
 ; CHECK-ORDERED: [[RDX2:%.*]] = call nnan float @llvm.vector.reduce.fadd.nxv8f32(float [[RDX1]], <vscale x 8 x float> [[FMUL2]])