// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -mvscale-min=4 -mvscale-max=4 -S -O1 -emit-llvm -o - %s | FileCheck %s

// REQUIRES: aarch64-registered-target

#include <arm_sve.h>

#define N __ARM_FEATURE_SVE_BITS

typedef svint32_t fixed_int32_t __attribute__((arm_sve_vector_bits(N)));
typedef svfloat64_t fixed_float64_t __attribute__((arm_sve_vector_bits(N)));
typedef svbool_t fixed_bool_t __attribute__((arm_sve_vector_bits(N)));

//===----------------------------------------------------------------------===//
// Test caller/callee with VLST <-> VLAT
//===----------------------------------------------------------------------===//

// CHECK-LABEL: @sizeless_callee(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    ret <vscale x 4 x i32> [[X:%.*]]
//
svint32_t sizeless_callee(svint32_t x) {
  return x;
}

// CHECK-LABEL: @fixed_caller(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    ret <vscale x 4 x i32> [[X_COERCE:%.*]]
//
fixed_int32_t fixed_caller(fixed_int32_t x) {
  return sizeless_callee(x);
}

// CHECK-LABEL: @fixed_callee(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    ret <vscale x 4 x i32> [[X_COERCE:%.*]]
//
fixed_int32_t fixed_callee(fixed_int32_t x) {
  return x;
}

// CHECK-LABEL: @sizeless_caller(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[COERCE1:%.*]] = alloca <16 x i32>, align 16
// CHECK-NEXT:    store <vscale x 4 x i32> [[X:%.*]], ptr [[COERCE1]], align 16
// CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i32>, ptr [[COERCE1]], align 16, !tbaa [[TBAA6:![0-9]+]]
// CHECK-NEXT:    [[CASTSCALABLESVE2:%.*]] = tail call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> undef, <16 x i32> [[TMP1]], i64 0)
// CHECK-NEXT:    ret <vscale x 4 x i32> [[CASTSCALABLESVE2]]
//
svint32_t sizeless_caller(svint32_t x) {
  return fixed_callee(x);
}

//===----------------------------------------------------------------------===//
// fixed, fixed
//===----------------------------------------------------------------------===//

// CHECK-LABEL: @call_int32_ff(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1_COERCE:%.*]], <vscale x 4 x i32> [[OP2_COERCE:%.*]]
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
fixed_int32_t call_int32_ff(svbool_t pg, fixed_int32_t op1, fixed_int32_t op2) {
  return svsel(pg, op1, op2);
}

// CHECK-LABEL: @call_float64_ff(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1_COERCE:%.*]], <vscale x 2 x double> [[OP2_COERCE:%.*]]
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
fixed_float64_t call_float64_ff(svbool_t pg, fixed_float64_t op1, fixed_float64_t op2) {
  return svsel(pg, op1, op2);
}

// CHECK-LABEL: @call_bool_ff(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP2:%.*]] = select <vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i1> [[TMP0:%.*]], <vscale x 16 x i1> [[TMP1:%.*]]
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP2]]
//
fixed_bool_t call_bool_ff(svbool_t pg, fixed_bool_t op1, fixed_bool_t op2) {
  return svsel(pg, op1, op2);
}

//===----------------------------------------------------------------------===//
// fixed, scalable
//===----------------------------------------------------------------------===//

// CHECK-LABEL: @call_int32_fs(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1_COERCE:%.*]], <vscale x 4 x i32> [[OP2:%.*]]
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
fixed_int32_t call_int32_fs(svbool_t pg, fixed_int32_t op1, svint32_t op2) {
  return svsel(pg, op1, op2);
}

// CHECK-LABEL: @call_float64_fs(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1_COERCE:%.*]], <vscale x 2 x double> [[OP2:%.*]]
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
fixed_float64_t call_float64_fs(svbool_t pg, fixed_float64_t op1, svfloat64_t op2) {
  return svsel(pg, op1, op2);
}

// CHECK-LABEL: @call_bool_fs(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i1> [[TMP0:%.*]], <vscale x 16 x i1> [[OP2:%.*]]
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
//
fixed_bool_t call_bool_fs(svbool_t pg, fixed_bool_t op1, svbool_t op2) {
  return svsel(pg, op1, op2);
}

//===----------------------------------------------------------------------===//
// scalable, scalable
//===----------------------------------------------------------------------===//

// CHECK-LABEL: @call_int32_ss(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 4 x i1> [[TMP0]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]]
// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
//
fixed_int32_t call_int32_ss(svbool_t pg, svint32_t op1, svint32_t op2) {
  return svsel(pg, op1, op2);
}

// CHECK-LABEL: @call_float64_ss(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[PG:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = select <vscale x 2 x i1> [[TMP0]], <vscale x 2 x double> [[OP1:%.*]], <vscale x 2 x double> [[OP2:%.*]]
// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
//
fixed_float64_t call_float64_ss(svbool_t pg, svfloat64_t op1, svfloat64_t op2) {
  return svsel(pg, op1, op2);
}

// CHECK-LABEL: @call_bool_ss(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = select <vscale x 16 x i1> [[PG:%.*]], <vscale x 16 x i1> [[OP1:%.*]], <vscale x 16 x i1> [[OP2:%.*]]
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP0]]
//
fixed_bool_t call_bool_ss(svbool_t pg, svbool_t op1, svbool_t op2) {
  return svsel(pg, op1, op2);
}