[PATCH] D60272: [Aarch64] Add v8.2-a half precision element extract intrinsics

[Diogo N. Sampaio via Phabricator via cfe-commits]

dnsampaio created this revision.
dnsampaio added reviewers: pablooliveira, olista01, LukeGeeson.
Herald added subscribers: cfe-commits, kristof.beyls, javed.absar.
Herald added a project: clang.

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


Repository:
  rC Clang

https://reviews.llvm.org/D60272

Files:
  lib/CodeGen/CGBuiltin.cpp
  test/CodeGen/aarch64-v8.2a-neon-intrinsics.c


Index: test/CodeGen/aarch64-v8.2a-neon-intrinsics.c
===================================================================
--- test/CodeGen/aarch64-v8.2a-neon-intrinsics.c
+++ test/CodeGen/aarch64-v8.2a-neon-intrinsics.c
@@ -1618,3 +1618,16 @@
   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);
+}
Index: lib/CodeGen/CGBuiltin.cpp
===================================================================
--- lib/CodeGen/CGBuiltin.cpp
+++ lib/CodeGen/CGBuiltin.cpp
@@ -7810,6 +7810,14 @@
                           : 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);



Index: test/CodeGen/aarch64-v8.2a-neon-intrinsics.c
===================================================================
--- test/CodeGen/aarch64-v8.2a-neon-intrinsics.c
+++ test/CodeGen/aarch64-v8.2a-neon-intrinsics.c
@@ -1618,3 +1618,16 @@
   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);
+}
Index: lib/CodeGen/CGBuiltin.cpp
===================================================================
--- lib/CodeGen/CGBuiltin.cpp
+++ lib/CodeGen/CGBuiltin.cpp
@@ -7810,6 +7810,14 @@
                           : 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);

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits