Index: lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64ISelLowering.cpp
+++ lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -582,7 +582,7 @@
 
     setOperationAction(ISD::STORE, VT.getSimpleVT(), Promote);
     AddPromotedToType(ISD::STORE, VT.getSimpleVT(), MVT::v2i32);
-  } else if (VT == MVT::v2f64 || VT == MVT::v4f32) {
+  } else if (VT == MVT::v2f64 || VT == MVT::v4f32 || VT == MVT::v8f16) {
     setOperationAction(ISD::LOAD, VT.getSimpleVT(), Promote);
     AddPromotedToType(ISD::LOAD, VT.getSimpleVT(), MVT::v2i64);
 
Index: lib/Target/AArch64/AArch64InstrInfo.td
===================================================================
--- lib/Target/AArch64/AArch64InstrInfo.td
+++ lib/Target/AArch64/AArch64InstrInfo.td
@@ -5233,6 +5233,9 @@
 def : Pat<(f128 (bitconvert (v8i16 FPR128:$src))),
                             (f128 (EXTv16i8 (REV64v8i16 FPR128:$src),
                                             (REV64v8i16 FPR128:$src), (i32 8)))>;
+def : Pat<(f128 (bitconvert (v8f16 FPR128:$src))),
+                            (f128 (EXTv16i8 (REV64v8i16 FPR128:$src),
+                                            (REV64v8i16 FPR128:$src), (i32 8)))>;
 def : Pat<(f128 (bitconvert (v2f64 FPR128:$src))),
                             (f128 (EXTv16i8 FPR128:$src, FPR128:$src, (i32 8)))>;
 def : Pat<(f128 (bitconvert (v4f32 FPR128:$src))),
@@ -5247,6 +5250,7 @@
 def : Pat<(v2f64 (bitconvert (f128  FPR128:$src))), (v2f64 FPR128:$src)>;
 def : Pat<(v2f64 (bitconvert (v4i32 FPR128:$src))), (v2f64 FPR128:$src)>;
 def : Pat<(v2f64 (bitconvert (v8i16 FPR128:$src))), (v2f64 FPR128:$src)>;
+def : Pat<(v2f64 (bitconvert (v8f16 FPR128:$src))), (v2f64 FPR128:$src)>;
 def : Pat<(v2f64 (bitconvert (v16i8 FPR128:$src))), (v2f64 FPR128:$src)>;
 def : Pat<(v2f64 (bitconvert (v4f32 FPR128:$src))), (v2f64 FPR128:$src)>;
 }
@@ -5258,6 +5262,8 @@
                              (v2f64 (REV64v4i32 FPR128:$src))>;
 def : Pat<(v2f64 (bitconvert (v8i16 FPR128:$src))),
                              (v2f64 (REV64v8i16 FPR128:$src))>;
+def : Pat<(v2f64 (bitconvert (v8f16 FPR128:$src))),
+                             (v2f64 (REV64v8i16 FPR128:$src))>;
 def : Pat<(v2f64 (bitconvert (v16i8 FPR128:$src))),
                              (v2f64 (REV64v16i8 FPR128:$src))>;
 def : Pat<(v2f64 (bitconvert (v4f32 FPR128:$src))),
@@ -5268,6 +5274,7 @@
 let Predicates = [IsLE] in {
 def : Pat<(v4f32 (bitconvert (f128  FPR128:$src))), (v4f32 FPR128:$src)>;
 def : Pat<(v4f32 (bitconvert (v8i16 FPR128:$src))), (v4f32 FPR128:$src)>;
+def : Pat<(v4f32 (bitconvert (v8f16 FPR128:$src))), (v4f32 FPR128:$src)>;
 def : Pat<(v4f32 (bitconvert (v16i8 FPR128:$src))), (v4f32 FPR128:$src)>;
 def : Pat<(v4f32 (bitconvert (v2i64 FPR128:$src))), (v4f32 FPR128:$src)>;
 def : Pat<(v4f32 (bitconvert (v2f64 FPR128:$src))), (v4f32 FPR128:$src)>;
@@ -5278,6 +5285,8 @@
                                     (REV64v4i32 FPR128:$src), (i32 8)))>;
 def : Pat<(v4f32 (bitconvert (v8i16 FPR128:$src))),
                              (v4f32 (REV32v8i16 FPR128:$src))>;
+def : Pat<(v4f32 (bitconvert (v8f16 FPR128:$src))),
+                             (v4f32 (REV32v8i16 FPR128:$src))>;
 def : Pat<(v4f32 (bitconvert (v16i8 FPR128:$src))),
                              (v4f32 (REV32v16i8 FPR128:$src))>;
 def : Pat<(v4f32 (bitconvert (v2i64 FPR128:$src))),
Index: test/CodeGen/AArch64/aarch64_f16_be.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AArch64/aarch64_f16_be.ll
@@ -0,0 +1,41 @@
+; RUN: llc -mtriple=aarch64-linux-gnuabi -O0 < %s | FileCheck %s
+; RUN: llc -mtriple=aarch64_be-linux-gnuabi -O0 < %s | FileCheck %s --check-prefix=CHECK-BE
+
+define void @test_bitcast_v8f16_to_v4f32(<8 x half> %a) {
+; CHECK-LABEL: test_bitcast_v8f16_to_v4f32:
+; CHECK-NOT: st1
+
+; CHECK-BE-LABEL: test_bitcast_v8f16_to_v4f32:
+; CHECK-BE: st1
+
+  %x = alloca <4 x float>, align 16
+  %y = bitcast <8 x half> %a to <4 x float>
+  store <4 x float> %y, <4 x float>* %x, align 16
+  ret void
+}
+
+define void @test_bitcast_v8f16_to_v2f64(<8 x half> %a) {
+; CHECK-LABEL: test_bitcast_v8f16_to_v2f64:
+; CHECK-NOT: st1
+
+; CHECK-BE-LABEL: test_bitcast_v8f16_to_v2f64:
+; CHECK-BE: st1
+
+  %x = alloca <2 x double>, align 16
+  %y = bitcast <8 x half> %a to <2 x double>
+  store <2 x double> %y, <2 x double>* %x, align 16
+  ret void
+}
+
+define void @test_bitcast_v8f16_to_fp128(<8 x half> %a) {
+; CHECK-LABEL: test_bitcast_v8f16_to_fp128:
+; CHECK-NOT: st1
+
+; CHECK-BE-LABEL: test_bitcast_v8f16_to_fp128:
+; CHECK-BE: st1
+
+  %x = alloca fp128, align 16
+  %y = bitcast <8 x half> %a to fp128
+  store fp128 %y, fp128* %x, align 16
+  ret void
+}