[Aarch64] Add v8.2-a half precision element extract intrinsics

[dnsampaio]

Summary

Implements the intrinsics define on the ACLE to extract half precision fp scalar elements from float16x4_t and float16x8_t vector types.
a.k.a:
vduph_lane_f16
vduph_laneq_f16

[dnsampaio]

Ping

[LukeGeeson]

couple of nits, besides from that LGTM

lib/CodeGen/CGBuiltin.cpp

7813 ↗

(On Diff #193727)

nit: spacing between : and {

7817 ↗

(On Diff #193727)

nit: spacing again

[dnsampaio]

• Used clang-format-diff

[DavidSpickett]

LGTM

cfe/trunk/lib/CodeGen/CGBuiltin.cpp

case NEON::BI__builtin_neon_vqdmlsls_laneq_s32: {
     Ops.pop_back();
 
     unsigned AccInt = (BuiltinID == NEON::BI__builtin_neon_vqdmlals_lane_s32 ||
                        BuiltinID == NEON::BI__builtin_neon_vqdmlals_laneq_s32)
                           ? Intrinsic::aarch64_neon_sqadd
                           : Intrinsic::aarch64_neon_sqsub;
     return EmitNeonCall(CGM.getIntrinsic(AccInt, Int64Ty), Ops, "vqdmlXl");
   }
+  case NEON::BI__builtin_neon_vduph_lane_f16: {
+    return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
+                                        "vget_lane");
+  }
+  case NEON::BI__builtin_neon_vduph_laneq_f16: {
+    return Builder.CreateExtractElement(Ops[0], EmitScalarExpr(E->getArg(1)),
+                                        "vgetq_lane");
+  }
   }
 
   llvm::VectorType *VTy = GetNeonType(this, Type);
   llvm::Type *Ty = VTy;
   if (!Ty)
     return nullptr;
 
   // Not all intrinsics handled by the common case work for AArch64 yet, so only

cfe/trunk/test/CodeGen/aarch64-v8.2a-neon-intrinsics.c

 
 // CHECK-LABEL: @test_vtrn2q_f16(
 // CHECK:   [[SHUFFLE_I:%.*]] = shufflevector <8 x half> %a, <8 x half> %b, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
 // CHECK:   ret <8 x half> [[SHUFFLE_I]]
 float16x8_t test_vtrn2q_f16(float16x8_t a, float16x8_t b) {
   return vtrn2q_f16(a, b);
 }
 
+// CHECK-LABEL: @test_vduph_laneq_f16(
+// CHECK:        [[V:%.*]] = extractelement <8 x half> [[V2:%.*]], i32 7
+// CHECK-NEXT:   ret half [[V]]
+float16_t test_vduph_laneq_f16(float16x8_t vec) {
+  return vduph_laneq_f16(vec, 7);
+}
+
+// CHECK-LABEL: @test_vduph_lane_f16(
+// CHECK:        [[V:%.*]] = extractelement <4 x half> [[V2:%.*]], i32 3
+// CHECK-NEXT:   ret half [[V]]
+float16_t test_vduph_lane_f16(float16x4_t vec) {
+  return vduph_lane_f16(vec, 3);
+}