// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -mvscale-min=1 -mvscale-max=1 -S -O1 -emit-llvm -o - %s -fhalf-no-semantic-interposition | FileCheck %s --check-prefix=CHECK-128
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -target-feature +bf16 -mvscale-min=4 -mvscale-max=4 -S -O1 -emit-llvm -o - %s -fhalf-no-semantic-interposition | FileCheck %s --check-prefix=CHECK-512

// REQUIRES: aarch64-registered-target

#include <arm_sve.h>

#define N __ARM_FEATURE_SVE_BITS

typedef svint64_t fixed_int64_t __attribute__((arm_sve_vector_bits(N)));
typedef svbfloat16_t fixed_bfloat16_t __attribute__((arm_sve_vector_bits(N)));
typedef svbool_t fixed_bool_t __attribute__((arm_sve_vector_bits(N)));

fixed_int64_t global_i64;
fixed_bfloat16_t global_bf16;
fixed_bool_t global_bool;

//===----------------------------------------------------------------------===//
// WRITES
//===----------------------------------------------------------------------===//

// CHECK-128-LABEL: @write_global_i64(
// CHECK-128-NEXT:  entry:
// CHECK-128-NEXT:    [[CASTFIXEDSVE:%.*]] = tail call <2 x i64> @llvm.vector.extract.v2i64.nxv2i64(<vscale x 2 x i64> [[V:%.*]], i64 0)
// CHECK-128-NEXT:    store <2 x i64> [[CASTFIXEDSVE]], ptr @global_i64, align 16, !tbaa [[TBAA6:![0-9]+]]
// CHECK-128-NEXT:    ret void
//
// CHECK-512-LABEL: @write_global_i64(
// CHECK-512-NEXT:  entry:
// CHECK-512-NEXT:    [[CASTFIXEDSVE:%.*]] = tail call <8 x i64> @llvm.vector.extract.v8i64.nxv2i64(<vscale x 2 x i64> [[V:%.*]], i64 0)
// CHECK-512-NEXT:    store <8 x i64> [[CASTFIXEDSVE]], ptr @global_i64, align 16, !tbaa [[TBAA6:![0-9]+]]
// CHECK-512-NEXT:    ret void
//
void write_global_i64(svint64_t v) { global_i64 = v; }

// CHECK-128-LABEL: @write_global_bf16(
// CHECK-128-NEXT:  entry:
// CHECK-128-NEXT:    [[CASTFIXEDSVE:%.*]] = tail call <8 x bfloat> @llvm.vector.extract.v8bf16.nxv8bf16(<vscale x 8 x bfloat> [[V:%.*]], i64 0)
// CHECK-128-NEXT:    store <8 x bfloat> [[CASTFIXEDSVE]], ptr @global_bf16, align 16, !tbaa [[TBAA6]]
// CHECK-128-NEXT:    ret void
//
// CHECK-512-LABEL: @write_global_bf16(
// CHECK-512-NEXT:  entry:
// CHECK-512-NEXT:    [[CASTFIXEDSVE:%.*]] = tail call <32 x bfloat> @llvm.vector.extract.v32bf16.nxv8bf16(<vscale x 8 x bfloat> [[V:%.*]], i64 0)
// CHECK-512-NEXT:    store <32 x bfloat> [[CASTFIXEDSVE]], ptr @global_bf16, align 16, !tbaa [[TBAA6]]
// CHECK-512-NEXT:    ret void
//
void write_global_bf16(svbfloat16_t v) { global_bf16 = v; }

// CHECK-128-LABEL: @write_global_bool(
// CHECK-128-NEXT:  entry:
// CHECK-128-NEXT:    [[TMP0:%.*]] = bitcast <vscale x 16 x i1> [[V:%.*]] to <vscale x 2 x i8>
// CHECK-128-NEXT:    [[CASTFIXEDSVE:%.*]] = tail call <2 x i8> @llvm.vector.extract.v2i8.nxv2i8(<vscale x 2 x i8> [[TMP0]], i64 0)
// CHECK-128-NEXT:    store <2 x i8> [[CASTFIXEDSVE]], ptr @global_bool, align 2, !tbaa [[TBAA6]]
// CHECK-128-NEXT:    ret void
//
// CHECK-512-LABEL: @write_global_bool(
// CHECK-512-NEXT:  entry:
// CHECK-512-NEXT:    [[TMP0:%.*]] = bitcast <vscale x 16 x i1> [[V:%.*]] to <vscale x 2 x i8>
// CHECK-512-NEXT:    [[CASTFIXEDSVE:%.*]] = tail call <8 x i8> @llvm.vector.extract.v8i8.nxv2i8(<vscale x 2 x i8> [[TMP0]], i64 0)
// CHECK-512-NEXT:    store <8 x i8> [[CASTFIXEDSVE]], ptr @global_bool, align 2, !tbaa [[TBAA6]]
// CHECK-512-NEXT:    ret void
//
void write_global_bool(svbool_t v) { global_bool = v; }

//===----------------------------------------------------------------------===//
// READS
//===----------------------------------------------------------------------===//

// CHECK-128-LABEL: @read_global_i64(
// CHECK-128-NEXT:  entry:
// CHECK-128-NEXT:    [[TMP0:%.*]] = load <2 x i64>, ptr @global_i64, align 16, !tbaa [[TBAA6]]
// CHECK-128-NEXT:    [[CASTSCALABLESVE:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v2i64(<vscale x 2 x i64> undef, <2 x i64> [[TMP0]], i64 0)
// CHECK-128-NEXT:    ret <vscale x 2 x i64> [[CASTSCALABLESVE]]
//
// CHECK-512-LABEL: @read_global_i64(
// CHECK-512-NEXT:  entry:
// CHECK-512-NEXT:    [[TMP0:%.*]] = load <8 x i64>, ptr @global_i64, align 16, !tbaa [[TBAA6]]
// CHECK-512-NEXT:    [[CASTSCALABLESVE:%.*]] = tail call <vscale x 2 x i64> @llvm.vector.insert.nxv2i64.v8i64(<vscale x 2 x i64> undef, <8 x i64> [[TMP0]], i64 0)
// CHECK-512-NEXT:    ret <vscale x 2 x i64> [[CASTSCALABLESVE]]
//
svint64_t read_global_i64() { return global_i64; }

// CHECK-128-LABEL: @read_global_bf16(
// CHECK-128-NEXT:  entry:
// CHECK-128-NEXT:    [[TMP0:%.*]] = load <8 x bfloat>, ptr @global_bf16, align 16, !tbaa [[TBAA6]]
// CHECK-128-NEXT:    [[CASTSCALABLESVE:%.*]] = tail call <vscale x 8 x bfloat> @llvm.vector.insert.nxv8bf16.v8bf16(<vscale x 8 x bfloat> undef, <8 x bfloat> [[TMP0]], i64 0)
// CHECK-128-NEXT:    ret <vscale x 8 x bfloat> [[CASTSCALABLESVE]]
//
// CHECK-512-LABEL: @read_global_bf16(
// CHECK-512-NEXT:  entry:
// CHECK-512-NEXT:    [[TMP0:%.*]] = load <32 x bfloat>, ptr @global_bf16, align 16, !tbaa [[TBAA6]]
// CHECK-512-NEXT:    [[CASTSCALABLESVE:%.*]] = tail call <vscale x 8 x bfloat> @llvm.vector.insert.nxv8bf16.v32bf16(<vscale x 8 x bfloat> undef, <32 x bfloat> [[TMP0]], i64 0)
// CHECK-512-NEXT:    ret <vscale x 8 x bfloat> [[CASTSCALABLESVE]]
//
svbfloat16_t read_global_bf16() { return global_bf16; }

// CHECK-128-LABEL: @read_global_bool(
// CHECK-128-NEXT:  entry:
// CHECK-128-NEXT:    [[TMP0:%.*]] = load <2 x i8>, ptr @global_bool, align 2, !tbaa [[TBAA6]]
// CHECK-128-NEXT:    [[CASTSCALABLESVE:%.*]] = tail call <vscale x 2 x i8> @llvm.vector.insert.nxv2i8.v2i8(<vscale x 2 x i8> undef, <2 x i8> [[TMP0]], i64 0)
// CHECK-128-NEXT:    [[TMP1:%.*]] = bitcast <vscale x 2 x i8> [[CASTSCALABLESVE]] to <vscale x 16 x i1>
// CHECK-128-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
//
// CHECK-512-LABEL: @read_global_bool(
// CHECK-512-NEXT:  entry:
// CHECK-512-NEXT:    [[TMP0:%.*]] = load <8 x i8>, ptr @global_bool, align 2, !tbaa [[TBAA6]]
// CHECK-512-NEXT:    [[CASTSCALABLESVE:%.*]] = tail call <vscale x 2 x i8> @llvm.vector.insert.nxv2i8.v8i8(<vscale x 2 x i8> undef, <8 x i8> [[TMP0]], i64 0)
// CHECK-512-NEXT:    [[TMP1:%.*]] = bitcast <vscale x 2 x i8> [[CASTSCALABLESVE]] to <vscale x 16 x i1>
// CHECK-512-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
//
svbool_t read_global_bool() { return global_bool; }