[arm][turbofan] Use NEON for unaligned float64 memory accesses

src/compiler/arm/code-generator-arm.cc

Index: src/compiler/arm/code-generator-arm.cc
diff --git a/src/compiler/arm/code-generator-arm.cc b/src/compiler/arm/code-generator-arm.cc
index 8f53d9901c6e4a2bb2bc268ceb1bb2128a5117a3..4e3868e38a1fd54680ecee807910547c517a5f64 100644
--- a/src/compiler/arm/code-generator-arm.cc
+++ b/src/compiler/arm/code-generator-arm.cc
@@ -1443,6 +1443,16 @@ CodeGenerator::CodeGenResult CodeGenerator::AssembleArchInstruction(
       __ vstr(i.InputFloatRegister(0), i.InputOffset(1));
       DCHECK_EQ(LeaveCC, i.OutputSBit());
       break;
+    case kArmVld1F64: {
+      __ vld1(NeonSize::Neon8, NeonListOperand(i.OutputDoubleRegister()),
+              NeonMemOperand(i.InputRegister(0)));
+      break;
+    }
+    case kArmVst1F64: {
+      __ vst1(Neon8, NeonListOperand(i.InputDoubleRegister(0)),
+              NeonMemOperand(i.InputRegister(1)));
+      break;
+    }
     case kArmVldrF64:
       __ vldr(i.OutputDoubleRegister(), i.InputOffset());
       DCHECK_EQ(LeaveCC, i.OutputSBit());