// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// REQUIRES: aarch64-registered-target
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu \
// RUN:   -target-feature +sve2p1 -S -O1 -Werror -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu \
// RUN:   -target-feature +sve2p1 -S -O1 -Werror -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sve2p1 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu \
// RUN:   -target-feature +sve2p1 -S -O1 -Werror -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu \
// RUN:   -target-feature +sve2p1 -S -O1 -Werror -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64-none-linux-gnu -target-feature +sve2p1 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu \
// RUN:   -target-feature +sme -S -DTEST_SME -O1 -Werror -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sme -S -DTEST_SME -disable-O0-optnone -Werror -Wall -o /dev/null %s
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve2p1 -S -disable-O0-optnone -Werror -Wall -o /dev/null %s

#include <arm_sve.h>

#ifndef TEST_SME
#define ATTR
#else
#define ATTR __arm_streaming
#endif

// CHECK-LABEL: @test_svpsel_lane_b8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[ADD:%.*]] = add i32 [[IDX:%.*]], 15
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.psel.nxv16i1(<vscale x 16 x i1> [[P1:%.*]], <vscale x 16 x i1> [[P2:%.*]], i32 [[ADD]])
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP0]]
//
// CPP-CHECK-LABEL: @_Z19test_svpsel_lane_b8u10__SVBool_tS_j(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[ADD:%.*]] = add i32 [[IDX:%.*]], 15
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.psel.nxv16i1(<vscale x 16 x i1> [[P1:%.*]], <vscale x 16 x i1> [[P2:%.*]], i32 [[ADD]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP0]]
//
svbool_t test_svpsel_lane_b8(svbool_t p1, svbool_t p2, uint32_t idx) ATTR {
  return svpsel_lane_b8(p1, p2, idx + 15);
}

// CHECK-LABEL: @test_svpsel_lane_b16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[ADD:%.*]] = add i32 [[IDX:%.*]], 7
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[P2:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.psel.nxv8i1(<vscale x 16 x i1> [[P1:%.*]], <vscale x 8 x i1> [[TMP0]], i32 [[ADD]])
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svpsel_lane_b16u10__SVBool_tS_j(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[ADD:%.*]] = add i32 [[IDX:%.*]], 7
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> [[P2:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.psel.nxv8i1(<vscale x 16 x i1> [[P1:%.*]], <vscale x 8 x i1> [[TMP0]], i32 [[ADD]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
//
svbool_t test_svpsel_lane_b16(svbool_t p1, svbool_t p2, uint32_t idx) ATTR {
  return svpsel_lane_b16(p1, p2, idx + 7);
}

// CHECK-LABEL: @test_svpsel_lane_b32(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[ADD:%.*]] = add i32 [[IDX:%.*]], 3
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[P2:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.psel.nxv4i1(<vscale x 16 x i1> [[P1:%.*]], <vscale x 4 x i1> [[TMP0]], i32 [[ADD]])
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svpsel_lane_b32u10__SVBool_tS_j(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[ADD:%.*]] = add i32 [[IDX:%.*]], 3
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> [[P2:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.psel.nxv4i1(<vscale x 16 x i1> [[P1:%.*]], <vscale x 4 x i1> [[TMP0]], i32 [[ADD]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
//
svbool_t test_svpsel_lane_b32(svbool_t p1, svbool_t p2, uint32_t idx) ATTR {
  return svpsel_lane_b32(p1, p2, idx + 3);
}

// CHECK-LABEL: @test_svpsel_lane_b64(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[ADD:%.*]] = add i32 [[IDX:%.*]], 1
// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[P2:%.*]])
// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.psel.nxv2i1(<vscale x 16 x i1> [[P1:%.*]], <vscale x 2 x i1> [[TMP0]], i32 [[ADD]])
// CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
//
// CPP-CHECK-LABEL: @_Z20test_svpsel_lane_b64u10__SVBool_tS_j(
// CPP-CHECK-NEXT:  entry:
// CPP-CHECK-NEXT:    [[ADD:%.*]] = add i32 [[IDX:%.*]], 1
// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> [[P2:%.*]])
// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i1> @llvm.aarch64.sve.psel.nxv2i1(<vscale x 16 x i1> [[P1:%.*]], <vscale x 2 x i1> [[TMP0]], i32 [[ADD]])
// CPP-CHECK-NEXT:    ret <vscale x 16 x i1> [[TMP1]]
//
svbool_t test_svpsel_lane_b64(svbool_t p1, svbool_t p2, uint32_t idx) ATTR {
  return svpsel_lane_b64(p1, p2, idx + 1);
}