Index: llvm/lib/Target/AArch64/AArch64ISelLowering.h
===================================================================
--- llvm/lib/Target/AArch64/AArch64ISelLowering.h
+++ llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -839,6 +839,8 @@
 
   bool fallBackToDAGISel(const Instruction &Inst) const override;
 
+  SDValue LowerCopyToReg(SDValue Op, SelectionDAG &DAG) const;
+
   /// SVE code generation for fixed length vectors does not custom lower
   /// BUILD_VECTOR. This makes BUILD_VECTOR legalisation a source of stores to
   /// merge. However, merging them creates a BUILD_VECTOR that is just as
Index: llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -284,6 +284,8 @@
   addRegisterClass(MVT::i32, &AArch64::GPR32allRegClass);
   addRegisterClass(MVT::i64, &AArch64::GPR64allRegClass);
 
+  setOperationAction(ISD::CopyToReg, MVT::Other, Custom);
+
   if (Subtarget->hasLS64()) {
     addRegisterClass(MVT::i64x8, &AArch64::GPR64x8ClassRegClass);
     setOperationAction(ISD::LOAD, MVT::i64x8, Custom);
@@ -5028,6 +5030,8 @@
   default:
     llvm_unreachable("unimplemented operand");
     return SDValue();
+  case ISD::CopyToReg:
+    return LowerCopyToReg(Op, DAG);
   case ISD::BITCAST:
     return LowerBITCAST(Op, DAG);
   case ISD::GlobalAddress:
@@ -5281,6 +5285,53 @@
   }
 }
 
+static SDValue tryAdvSIMDModImm32(unsigned NewOp, SDValue Op, SelectionDAG &DAG,
+                                  const APInt &Bits,
+                                  const SDValue *LHS = nullptr);
+static bool resolveBuildVector(BuildVectorSDNode *BVN, APInt &CnstBits,
+                               APInt &UndefBits);
+
+SDValue AArch64TargetLowering::LowerCopyToReg(SDValue Op,
+                                              SelectionDAG &DAG) const {
+  SDValue Chain = Op->getOperand(0);
+  SDValue LHS = Op->getOperand(1);
+  SDValue RHS = Op->getOperand(2);
+  ConstantFPSDNode *CFP = dyn_cast<ConstantFPSDNode>(RHS);
+  EVT VT = LHS->getValueType(0);
+  if (!CFP || !LHS->hasNUsesOfValue(2, 0) ||
+      VT.getSimpleVT().SimpleTy != MVT::f32)
+    return SDValue();
+
+  const APFloat &FPVal = CFP->getValueAPF();
+  const APInt ImmInt = FPVal.bitcastToAPInt();
+  uint64_t Imm = ImmInt.getZExtValue();
+  // Skip getFP32Imm as related value already deal with fmov.
+  if (AArch64_AM::getFP32Imm(ImmInt) != -1 || FPVal.isPosZero() ||
+      !AArch64_AM::isAdvSIMDModImmType4(Imm << 32 | Imm))
+    return SDValue();
+
+  SDLoc dl(Op);
+  MVT VecTy = MVT::v2f32;
+  APInt DefBits(VecTy.getSizeInBits(), 0);
+  APInt UndefBits(VecTy.getSizeInBits(), 0);
+  SDValue Parts[2];
+  for (int Elt = 0; Elt < 2; Elt++)
+    Parts[Elt] = RHS;
+  SDValue DupVal = DAG.getNode(ISD::BUILD_VECTOR, dl, MVT::v2f32, Parts);
+
+  BuildVectorSDNode *BVN = cast<BuildVectorSDNode>(DupVal.getNode());
+  if (!resolveBuildVector(BVN, DefBits, UndefBits))
+    return SDValue();
+
+  SDValue NewOp =
+      tryAdvSIMDModImm32(AArch64ISD::MOVIshift, DupVal, DAG, DefBits);
+  SDValue Elt = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, dl, VT, NewOp,
+                            DAG.getConstant(0, dl, MVT::i32));
+
+  DAG.ReplaceAllUsesWith(RHS, Elt);
+  return Op;
+}
+
 bool AArch64TargetLowering::mergeStoresAfterLegalization(EVT VT) const {
   return !Subtarget->useSVEForFixedLengthVectors();
 }
@@ -10288,8 +10339,7 @@
 
 // Try 32-bit splatted SIMD immediate.
 static SDValue tryAdvSIMDModImm32(unsigned NewOp, SDValue Op, SelectionDAG &DAG,
-                                  const APInt &Bits,
-                                  const SDValue *LHS = nullptr) {
+                                  const APInt &Bits, const SDValue *LHS) {
   if (Bits.getHiBits(64) == Bits.getLoBits(64)) {
     uint64_t Value = Bits.zextOrTrunc(64).getZExtValue();
     EVT VT = Op.getValueType();
Index: llvm/test/Transforms/LoopVectorize/AArch64/remat-const-float-simd.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/LoopVectorize/AArch64/remat-const-float-simd.ll
@@ -0,0 +1,13 @@
+; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -verify-machineinstrs | FileCheck %s
+
+; Check that float(0x7fffffff) can be rematerialized with simd instruction
+target triple = "aarch64-unknown-linux-gnu"
+
+; float foo(void) { return float(0x7fffffff); }
+define float @foo() {
+; CHECK: movi   v0.2s, #79, lsl #24
+entry:
+  ret float 0x41E0000000000000
+}
+
+