nuudlman/llvm: clang/test/CodeGen/aarch64_neon_sve_bridge_intrinsics/acle_neon_sve_bridge_dup

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: aarch64-registered-target
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -o /dev/null %s
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +sve -target-feature +bf16 -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
#include <arm_neon_sve_bridge.h>

#ifdef SVE_OVERLOADED_FORMS
// A simple used,unused... macro, long enough to represent any SVE builtin.
#define SVE_ACLE_FUNC(A1, A2_UNUSED, A3, A4_UNUSED) A1##A3
#else
#define SVE_ACLE_FUNC(A1, A2, A3, A4) A1##A2##A3##A4
#endif

// CHECK-LABEL: @test_svdup_neonq_s8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svdup_neonq_s811__Int8x16_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
//
svint8_t test_svdup_neonq_s8(int8x16_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _s8, , )(n);
}

// CHECK-LABEL: @test_svdup_neonq_s16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_s1611__Int16x8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
svint16_t test_svdup_neonq_s16(int16x8_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _s16, , )(n);
}

// CHECK-LABEL: @test_svdup_neonq_s32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_s3211__Int32x4_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
svint32_t test_svdup_neonq_s32(int32x4_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _s32, , )(n);
}

// CHECK-LABEL: @test_svdup_neonq_s64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_s6411__Int64x2_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
svint64_t test_svdup_neonq_s64(int64x2_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _s64, , )(n);
}

// CHECK-LABEL: @test_svdup_neonq_u8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z19test_svdup_neonq_u812__Uint8x16_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i8> @llvm.vector.insert.nxv16i8.v16i8(<vscale x 16 x i8> undef, <16 x i8> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dupq.lane.nxv16i8(<vscale x 16 x i8> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
//
svuint8_t test_svdup_neonq_u8(uint8x16_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _u8, , )(n);
}

// CHECK-LABEL: @test_svdup_neonq_u16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_u1612__Uint16x8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v8i16(<vscale x 8 x i16> undef, <8 x i16> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dupq.lane.nxv8i16(<vscale x 8 x i16> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
//
svuint16_t test_svdup_neonq_u16(uint16x8_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _u16, , )(n);
}

// CHECK-LABEL: @test_svdup_neonq_u32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_u3212__Uint32x4_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v4i32(<vscale x 4 x i32> undef, <4 x i32> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dupq.lane.nxv4i32(<vscale x 4 x i32> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
svuint32_t test_svdup_neonq_u32(uint32x4_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _u32, , )(n);
}

// CHECK-LABEL: @test_svdup_neonq_u64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_u6412__Uint64x2_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dupq.lane.nxv2i64(<vscale x 2 x i64> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
//
svuint64_t test_svdup_neonq_u64(uint64x2_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _u64, , )(n);
}

// CHECK-LABEL: @test_svdup_neonq_f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.vector.insert.nxv8f16.v8f16(<vscale x 8 x half> undef, <8 x half> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.dupq.lane.nxv8f16(<vscale x 8 x half> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_f1613__Float16x8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x half> @llvm.vector.insert.nxv8f16.v8f16(<vscale x 8 x half> undef, <8 x half> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.dupq.lane.nxv8f16(<vscale x 8 x half> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
//
svfloat16_t test_svdup_neonq_f16(float16x8_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _f16, , )(n);
}

// CHECK-NEXT  %0 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> %n, i64 0)
// CHECK-NEXT  %1 = call <vscale x 4 x float> @llvm.aarch64.sve.dupq.lane.nxv4f32(<vscale x 4 x float> %0, i64 0)
// CHECK-NEXT  ret <vscale x 4 x float> %1
// CHECK-LABEL: @test_svdup_neonq_f32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.dupq.lane.nxv4f32(<vscale x 4 x float> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_f3213__Float32x4_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> undef, <4 x float> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.dupq.lane.nxv4f32(<vscale x 4 x float> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
//
svfloat32_t test_svdup_neonq_f32(float32x4_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _f32, , )(n);
}

// CHECK-LABEL: @test_svdup_neonq_f64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.vector.insert.nxv2f64.v2f64(<vscale x 2 x double> undef, <2 x double> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.dupq.lane.nxv2f64(<vscale x 2 x double> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svdup_neonq_f6413__Float64x2_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x double> @llvm.vector.insert.nxv2f64.v2f64(<vscale x 2 x double> undef, <2 x double> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.dupq.lane.nxv2f64(<vscale x 2 x double> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
svfloat64_t test_svdup_neonq_f64(float64x2_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _f64, , )(n);
}

// CHECK-LABEL: @test_svdup_neonq_bf16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.vector.insert.nxv8bf16.v8bf16(<vscale x 8 x bfloat> undef, <8 x bfloat> [[N:%.*]], i64 0)
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.dupq.lane.nxv8bf16(<vscale x 8 x bfloat> [[TMP0]], i64 0)
// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z21test_svdup_neonq_bf1614__Bfloat16x8_t(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x bfloat> @llvm.vector.insert.nxv8bf16.v8bf16(<vscale x 8 x bfloat> undef, <8 x bfloat> [[N:%.*]], i64 0)
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.dupq.lane.nxv8bf16(<vscale x 8 x bfloat> [[TMP0]], i64 0)
// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
//
svbfloat16_t test_svdup_neonq_bf16(bfloat16x8_t n) {
  return SVE_ACLE_FUNC(svdup_neonq, _bf16, , )(n);
}