[ARM,MVE] Make the MVE intrinsics work in C++!

[simon_tatham]

Summary

Apparently nobody has tried this in months of development. It turns
out that FunctionDecl::getBuiltinID will never consider a function
to be a builtin if it is in C++ and not extern "C". So none of the
function declarations in <arm_mve.h> are recognized as builtins when
clang is compiling in C++ mode: it just emits calls to them as
ordinary functions, which then turn out not to exist at link time.

The trivial fix is to wrap most of arm_mve.h in an extern "C".

Added a test in clang/test/CodeGen/arm-mve-intrinsics which checks
basic functioning of the MVE header file in C++ mode. I've filled it
with copies of existing test functions from other files in that
directory, including a few moderately tricky cases of overloading (in
particular one that relies on the strict-polymorphism attribute added
in D72518).

(I considered making every test in that directory compile in both
C and C++ mode and check the code generation was identical. But I
think that would increase testing time by more than the value it adds,
and also update_cc_test_checks gets confused when the output function
name varies between RUN lines.)

[MarkMurrayARM]

LGTM

clang/test/CodeGen/arm-mve-intrinsics/cplusplus.cpp

+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O3 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+// RUN: %clang_cc1 -triple thumbv8.1m.main-arm-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O3 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
+
+#include <arm_mve.h>
+
+// CHECK-LABEL: @_Z16test_vbicq_n_s1617__simd128_int16_t(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = and <8 x i16> [[A:%.*]], <i16 11007, i16 11007, i16 11007, i16 11007, i16 11007, i16 11007, i16 11007, i16 11007>
+// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
+//
+int16x8_t test_vbicq_n_s16(int16x8_t a)
+{
+#ifdef POLYMORPHIC
+    return vbicq(a, 0xd500);
+#else /* POLYMORPHIC */
+    return vbicq_n_s16(a, 0xd500);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @_Z16test_vbicq_n_u3218__simd128_uint32_t(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = and <4 x i32> [[A:%.*]], <i32 -8193, i32 -8193, i32 -8193, i32 -8193>
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+uint32x4_t test_vbicq_n_u32(uint32x4_t a)
+{
+#ifdef POLYMORPHIC
+    return vbicq(a, 0x2000);
+#else /* POLYMORPHIC */
+    return vbicq_n_u32(a, 0x2000);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @_Z16test_vorrq_n_s3217__simd128_int32_t(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = or <4 x i32> [[A:%.*]], <i32 65536, i32 65536, i32 65536, i32 65536>
+// CHECK-NEXT:    ret <4 x i32> [[TMP0]]
+//
+int32x4_t test_vorrq_n_s32(int32x4_t a)
+{
+#ifdef POLYMORPHIC
+    return vorrq(a, 0x10000);
+#else /* POLYMORPHIC */
+    return vorrq_n_s32(a, 0x10000);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @_Z16test_vorrq_n_u1618__simd128_uint16_t(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = or <8 x i16> [[A:%.*]], <i16 -4096, i16 -4096, i16 -4096, i16 -4096, i16 -4096, i16 -4096, i16 -4096, i16 -4096>
+// CHECK-NEXT:    ret <8 x i16> [[TMP0]]
+//
+uint16x8_t test_vorrq_n_u16(uint16x8_t a)
+{
+#ifdef POLYMORPHIC
+    return vorrq(a, 0xf000);
+#else /* POLYMORPHIC */
+    return vorrq_n_u16(a, 0xf000);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @_Z16test_vcmpeqq_f1619__simd128_float16_tS_(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = fcmp oeq <8 x half> [[A:%.*]], [[B:%.*]]
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP0]]), !range !3
+// CHECK-NEXT:    [[TMP2:%.*]] = trunc i32 [[TMP1]] to i16
+// CHECK-NEXT:    ret i16 [[TMP2]]
+//
+mve_pred16_t test_vcmpeqq_f16(float16x8_t a, float16x8_t b)
+{
+#ifdef POLYMORPHIC
+    return vcmpeqq(a, b);
+#else /* POLYMORPHIC */
+    return vcmpeqq_f16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @_Z18test_vcmpeqq_n_f1619__simd128_float16_tDh(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = bitcast float [[B_COERCE:%.*]] to i32
+// CHECK-NEXT:    [[TMP_0_EXTRACT_TRUNC:%.*]] = trunc i32 [[TMP0]] to i16
+// CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16 [[TMP_0_EXTRACT_TRUNC]] to half
+// CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <8 x half> undef, half [[TMP1]], i32 0
+// CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <8 x half> [[DOTSPLATINSERT]], <8 x half> undef, <8 x i32> zeroinitializer
+// CHECK-NEXT:    [[TMP2:%.*]] = fcmp oeq <8 x half> [[DOTSPLAT]], [[A:%.*]]
+// CHECK-NEXT:    [[TMP3:%.*]] = tail call i32 @llvm.arm.mve.pred.v2i.v8i1(<8 x i1> [[TMP2]]), !range !3
+// CHECK-NEXT:    [[TMP4:%.*]] = trunc i32 [[TMP3]] to i16
+// CHECK-NEXT:    ret i16 [[TMP4]]
+//
+mve_pred16_t test_vcmpeqq_n_f16(float16x8_t a, float16_t b)
+{
+#ifdef POLYMORPHIC
+    return vcmpeqq(a, b);
+#else /* POLYMORPHIC */
+    return vcmpeqq_n_f16(a, b);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @_Z14test_vld1q_u16PKt(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = bitcast i16* [[BASE:%.*]] to <8 x i16>*
+// CHECK-NEXT:    [[TMP1:%.*]] = load <8 x i16>, <8 x i16>* [[TMP0]], align 2
+// CHECK-NEXT:    ret <8 x i16> [[TMP1]]
+//
+uint16x8_t test_vld1q_u16(const uint16_t *base)
+{
+#ifdef POLYMORPHIC
+    return vld1q(base);
+#else /* POLYMORPHIC */
+    return vld1q_u16(base);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @_Z16test_vst1q_p_s32Pi17__simd128_int32_tt(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[BASE:%.*]] to <4 x i32>*
+// CHECK-NEXT:    [[TMP1:%.*]] = zext i16 [[P:%.*]] to i32
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP1]])
+// CHECK-NEXT:    tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> [[VALUE:%.*]], <4 x i32>* [[TMP0]], i32 4, <4 x i1> [[TMP2]])
+// CHECK-NEXT:    ret void
+//
+void test_vst1q_p_s32(int32_t *base, int32x4_t value, mve_pred16_t p)
+{
+#ifdef POLYMORPHIC
+    vst1q_p(base, value, p);
+#else /* POLYMORPHIC */
+    vst1q_p_s32(base, value, p);
+#endif /* POLYMORPHIC */
+}
+
+// CHECK-LABEL: @_Z30test_vldrdq_gather_base_wb_s64P18__simd128_uint64_t(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x i64>, <2 x i64>* [[ADDR:%.*]], align 8
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call { <2 x i64>, <2 x i64> } @llvm.arm.mve.vldr.gather.base.wb.v2i64.v2i64(<2 x i64> [[TMP0]], i32 576)
+// CHECK-NEXT:    [[TMP2:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[TMP1]], 1
+// CHECK-NEXT:    store <2 x i64> [[TMP2]], <2 x i64>* [[ADDR]], align 8
+// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { <2 x i64>, <2 x i64> } [[TMP1]], 0
+// CHECK-NEXT:    ret <2 x i64> [[TMP3]]
+//
+int64x2_t test_vldrdq_gather_base_wb_s64(uint64x2_t *addr)
+{
+    return vldrdq_gather_base_wb_s64(addr, 0x240);
+}
+
+// CHECK-LABEL: @_Z31test_vstrwq_scatter_base_wb_u32P18__simd128_uint32_tS_(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, <4 x i32>* [[ADDR:%.*]], align 8
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <4 x i32> @llvm.arm.mve.vstr.scatter.base.wb.v4i32.v4i32(<4 x i32> [[TMP0]], i32 64, <4 x i32> [[VALUE:%.*]])
+// CHECK-NEXT:    store <4 x i32> [[TMP1]], <4 x i32>* [[ADDR]], align 8
+// CHECK-NEXT:    ret void
+//
+void test_vstrwq_scatter_base_wb_u32(uint32x4_t *addr, uint32x4_t value)
+{
+#ifdef POLYMORPHIC
+    vstrwq_scatter_base_wb(addr, 0x40, value);
+#else /* POLYMORPHIC */
+    vstrwq_scatter_base_wb_u32(addr, 0x40, value);
+#endif /* POLYMORPHIC */
+}

clang/utils/TableGen/MveEmitter.cpp

OS << "/*===---- arm_mve.h - ARM MVE intrinsics "
         "#ifndef __ARM_MVE_H\n"
         "#define __ARM_MVE_H\n"
         "\n"
         "#if !__ARM_FEATURE_MVE\n"
         "#error \"MVE support not enabled\"\n"
         "#endif\n"
         "\n"
         "#include <stdint.h>\n"
+        "\n"
+        "#ifdef __cplusplus\n"
+        "extern \"C\" {\n"
+        "#endif\n"
         "\n";
 
   for (size_t i = 0; i < NumParts; ++i) {
     std::vector<std::string> conditions;
     if (i & Float)
       conditions.push_back("(__ARM_FEATURE_MVE & 2)");
     if (i & UseUserNamespace)
       conditions.push_back("(!defined __ARM_MVE_PRESERVE_USER_NAMESPACE)");
 
     std::string condition =
         join(std::begin(conditions), std::end(conditions), " && ");
     if (!condition.empty())
       OS << "#if " << condition << "\n\n";
     OS << parts[i].str();
     if (!condition.empty())
       OS << "#endif /* " << condition << " */\n\n";
   }
 
-  OS << "#endif /* __ARM_MVE_H */\n";
+  OS << "#ifdef __cplusplus\n"
+        "} /* extern \"C\" */\n"
+        "#endif\n"
+        "\n"
+        "#endif /* __ARM_MVE_H */\n";
 }
 
 void MveEmitter::EmitBuiltinDef(raw_ostream &OS) {
   for (const auto &kv : ACLEIntrinsics) {
     const ACLEIntrinsic &Int = *kv.second;
     OS << "TARGET_HEADER_BUILTIN(__builtin_arm_mve_" << Int.fullName()
        << ", \"\", \"n\", \"arm_mve.h\", ALL_LANGUAGES, \"\")\n";
   }