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

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

Reviewers: pablooliveira, olista01, LukeGeeson, DavidSpickett

Reviewed By: DavidSpickett

Subscribers: DavidSpickett, javed.absar, kristof.beyls, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D60272

llvm-svn: 358276

2 files changed, 21 insertions, 0 deletions

diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 6b7ed4e8bfd..02969a1908b 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -7847,6 +7847,14 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
                           : 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);
diff --git a/clang/test/CodeGen/aarch64-v8.2a-neon-intrinsics.c b/clang/test/CodeGen/aarch64-v8.2a-neon-intrinsics.c
index a4bf8753363..a84445b62a2 100644
--- a/clang/test/CodeGen/aarch64-v8.2a-neon-intrinsics.c
+++ b/clang/test/CodeGen/aarch64-v8.2a-neon-intrinsics.c
@@ -1618,3 +1618,16 @@ 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);
+}