// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
// RUN: %clang_cc1 -triple thumbv8.1m.main-none-none-eabi -target-feature +mve.fp -mfloat-abi hard -fallow-half-arguments-and-returns -O0 -disable-O0-optnone -DPOLYMORPHIC -S -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
// REQUIRES: aarch64-registered-target || arm-registered-target
// CHECK-LABEL: @test_vshrnbq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 3, i32 0, i32 0, i32 0, i32 0, i32 0)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
int8x16_t
// CHECK-LABEL: @test_vshrnbq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 9, i32 0, i32 0, i32 0, i32 0, i32 0)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t
// CHECK-LABEL: @test_vshrnbq_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, i32 0, i32 0, i32 1, i32 1, i32 0)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vshrnbq_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 3, i32 0, i32 0, i32 1, i32 1, i32 0)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vshrntq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, i32 0, i32 0, i32 0, i32 0, i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
int8x16_t
// CHECK-LABEL: @test_vshrntq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 10, i32 0, i32 0, i32 0, i32 0, i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t
// CHECK-LABEL: @test_vshrntq_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 6, i32 0, i32 0, i32 1, i32 1, i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vshrntq_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 10, i32 0, i32 0, i32 1, i32 1, i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vshrnbq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 4, i32 0, i32 0, i32 0, i32 0, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t
// CHECK-LABEL: @test_vshrnbq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 13, i32 0, i32 0, i32 0, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t
// CHECK-LABEL: @test_vshrnbq_m_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 7, i32 0, i32 0, i32 1, i32 1, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vshrnbq_m_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 15, i32 0, i32 0, i32 1, i32 1, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vshrntq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 6, i32 0, i32 0, i32 0, i32 0, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t
// CHECK-LABEL: @test_vshrntq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 13, i32 0, i32 0, i32 0, i32 0, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t
// CHECK-LABEL: @test_vshrntq_m_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, i32 0, i32 0, i32 1, i32 1, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vshrntq_m_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 10, i32 0, i32 0, i32 1, i32 1, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vrshrnbq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 5, i32 0, i32 1, i32 0, i32 0, i32 0)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
int8x16_t
// CHECK-LABEL: @test_vrshrnbq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 10, i32 0, i32 1, i32 0, i32 0, i32 0)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t
// CHECK-LABEL: @test_vrshrnbq_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 2, i32 0, i32 1, i32 1, i32 1, i32 0)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vrshrnbq_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 12, i32 0, i32 1, i32 1, i32 1, i32 0)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vrshrntq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 4, i32 0, i32 1, i32 0, i32 0, i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
int8x16_t
// CHECK-LABEL: @test_vrshrntq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 11, i32 0, i32 1, i32 0, i32 0, i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t
// CHECK-LABEL: @test_vrshrntq_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, i32 0, i32 1, i32 1, i32 1, i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vrshrntq_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 6, i32 0, i32 1, i32 1, i32 1, i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vrshrnbq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, i32 0, i32 1, i32 0, i32 0, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t
// CHECK-LABEL: @test_vrshrnbq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 14, i32 0, i32 1, i32 0, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t
// CHECK-LABEL: @test_vrshrnbq_m_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 2, i32 0, i32 1, i32 1, i32 1, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vrshrnbq_m_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 12, i32 0, i32 1, i32 1, i32 1, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vrshrntq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 4, i32 0, i32 1, i32 0, i32 0, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t
// CHECK-LABEL: @test_vrshrntq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 6, i32 0, i32 1, i32 0, i32 0, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t
// CHECK-LABEL: @test_vrshrntq_m_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 6, i32 0, i32 1, i32 1, i32 1, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vrshrntq_m_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 10, i32 0, i32 1, i32 1, i32 1, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vqshrnbq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 7, i32 1, i32 0, i32 0, i32 0, i32 0)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
int8x16_t
// CHECK-LABEL: @test_vqshrnbq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 15, i32 1, i32 0, i32 0, i32 0, i32 0)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t
// CHECK-LABEL: @test_vqshrnbq_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 3, i32 1, i32 0, i32 1, i32 1, i32 0)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vqshrnbq_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 3, i32 1, i32 0, i32 1, i32 1, i32 0)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vqshrntq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 5, i32 1, i32 0, i32 0, i32 0, i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
int8x16_t
// CHECK-LABEL: @test_vqshrntq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 6, i32 1, i32 0, i32 0, i32 0, i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t
// CHECK-LABEL: @test_vqshrntq_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, i32 1, i32 0, i32 1, i32 1, i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vqshrntq_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 15, i32 1, i32 0, i32 1, i32 1, i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vqshrnbq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 7, i32 1, i32 0, i32 0, i32 0, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t
// CHECK-LABEL: @test_vqshrnbq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 1, i32 1, i32 0, i32 0, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t
// CHECK-LABEL: @test_vqshrnbq_m_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, i32 1, i32 0, i32 1, i32 1, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vqshrnbq_m_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 8, i32 1, i32 0, i32 1, i32 1, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vqshrntq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, i32 1, i32 0, i32 0, i32 0, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t
// CHECK-LABEL: @test_vqshrntq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 11, i32 1, i32 0, i32 0, i32 0, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t
// CHECK-LABEL: @test_vqshrntq_m_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 3, i32 1, i32 0, i32 1, i32 1, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vqshrntq_m_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 1, i32 1, i32 0, i32 1, i32 1, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vqshrunbq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 5, i32 1, i32 0, i32 1, i32 0, i32 0)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vqshrunbq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 13, i32 1, i32 0, i32 1, i32 0, i32 0)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vqshruntq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 2, i32 1, i32 0, i32 1, i32 0, i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vqshruntq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 7, i32 1, i32 0, i32 1, i32 0, i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vqshrunbq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 7, i32 1, i32 0, i32 1, i32 0, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vqshrunbq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 7, i32 1, i32 0, i32 1, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vqshruntq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 7, i32 1, i32 0, i32 1, i32 0, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vqshruntq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 7, i32 1, i32 0, i32 1, i32 0, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vqrshrnbq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 5, i32 1, i32 1, i32 0, i32 0, i32 0)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
int8x16_t
// CHECK-LABEL: @test_vqrshrnbq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 13, i32 1, i32 1, i32 0, i32 0, i32 0)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t
// CHECK-LABEL: @test_vqrshrnbq_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 7, i32 1, i32 1, i32 1, i32 1, i32 0)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vqrshrnbq_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 8, i32 1, i32 1, i32 1, i32 1, i32 0)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vqrshrntq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 7, i32 1, i32 1, i32 0, i32 0, i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
int8x16_t
// CHECK-LABEL: @test_vqrshrntq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 2, i32 1, i32 1, i32 0, i32 0, i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t
// CHECK-LABEL: @test_vqrshrntq_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, i32 1, i32 1, i32 1, i32 1, i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vqrshrntq_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 11, i32 1, i32 1, i32 1, i32 1, i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vqrshrnbq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 2, i32 1, i32 1, i32 0, i32 0, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t
// CHECK-LABEL: @test_vqrshrnbq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 12, i32 1, i32 1, i32 0, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t
// CHECK-LABEL: @test_vqrshrnbq_m_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 5, i32 1, i32 1, i32 1, i32 1, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vqrshrnbq_m_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 11, i32 1, i32 1, i32 1, i32 1, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vqrshrntq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 4, i32 1, i32 1, i32 0, i32 0, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t
// CHECK-LABEL: @test_vqrshrntq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 6, i32 1, i32 1, i32 0, i32 0, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t
// CHECK-LABEL: @test_vqrshrntq_m_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 7, i32 1, i32 1, i32 1, i32 1, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vqrshrntq_m_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 15, i32 1, i32 1, i32 1, i32 1, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vqrshrunbq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 7, i32 1, i32 1, i32 1, i32 0, i32 0)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vqrshrunbq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 1, i32 1, i32 1, i32 1, i32 0, i32 0)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vqrshruntq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, i32 1, i32 1, i32 1, i32 0, i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vqrshruntq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 3, i32 1, i32 1, i32 1, i32 0, i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vqrshrunbq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 4, i32 1, i32 1, i32 1, i32 0, i32 0, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vqrshrunbq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 10, i32 1, i32 1, i32 1, i32 0, i32 0, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vqrshruntq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vshrn.predicated.v16i8.v8i16.v8i1(<16 x i8> [[A:%.*]], <8 x i16> [[B:%.*]], i32 3, i32 1, i32 1, i32 1, i32 0, i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vqrshruntq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vshrn.predicated.v8i16.v4i32.v4i1(<8 x i16> [[A:%.*]], <4 x i32> [[B:%.*]], i32 13, i32 1, i32 1, i32 1, i32 0, i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vsliq_n_s8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vsli.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 2)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
int8x16_t
// CHECK-LABEL: @test_vsliq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vsli.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 10)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t
// CHECK-LABEL: @test_vsliq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vsli.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 1)
// CHECK-NEXT: ret <4 x i32> [[TMP0]]
//
int32x4_t
// CHECK-LABEL: @test_vsliq_n_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vsli.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 1)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vsliq_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vsli.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vsliq_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vsli.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 28)
// CHECK-NEXT: ret <4 x i32> [[TMP0]]
//
uint32x4_t
// CHECK-LABEL: @test_vsliq_m_n_s8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vsli.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 4, <16 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t
// CHECK-LABEL: @test_vsliq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vsli.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t
// CHECK-LABEL: @test_vsliq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vsli.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 1, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
int32x4_t
// CHECK-LABEL: @test_vsliq_m_n_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vsli.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 5, <16 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vsliq_m_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vsli.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 3, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vsliq_m_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vsli.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 9, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
uint32x4_t
// CHECK-LABEL: @test_vsriq_n_s8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vsri.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 3)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
int8x16_t
// CHECK-LABEL: @test_vsriq_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vsri.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 2)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
int16x8_t
// CHECK-LABEL: @test_vsriq_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vsri.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 28)
// CHECK-NEXT: ret <4 x i32> [[TMP0]]
//
int32x4_t
// CHECK-LABEL: @test_vsriq_n_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <16 x i8> @llvm.arm.mve.vsri.v16i8(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 3)
// CHECK-NEXT: ret <16 x i8> [[TMP0]]
//
uint8x16_t
// CHECK-LABEL: @test_vsriq_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <8 x i16> @llvm.arm.mve.vsri.v8i16(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 3)
// CHECK-NEXT: ret <8 x i16> [[TMP0]]
//
uint16x8_t
// CHECK-LABEL: @test_vsriq_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call <4 x i32> @llvm.arm.mve.vsri.v4i32(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 26)
// CHECK-NEXT: ret <4 x i32> [[TMP0]]
//
uint32x4_t
// CHECK-LABEL: @test_vsriq_m_n_s8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vsri.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 4, <16 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
int8x16_t
// CHECK-LABEL: @test_vsriq_m_n_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vsri.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 1, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
int16x8_t
// CHECK-LABEL: @test_vsriq_m_n_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vsri.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 27, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
int32x4_t
// CHECK-LABEL: @test_vsriq_m_n_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <16 x i8> @llvm.arm.mve.vsri.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], i32 7, <16 x i1> [[TMP1]])
// CHECK-NEXT: ret <16 x i8> [[TMP2]]
//
uint8x16_t
// CHECK-LABEL: @test_vsriq_m_n_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <8 x i16> @llvm.arm.mve.vsri.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], i32 9, <8 x i1> [[TMP1]])
// CHECK-NEXT: ret <8 x i16> [[TMP2]]
//
uint16x8_t
// CHECK-LABEL: @test_vsriq_m_n_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP1:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP0]])
// CHECK-NEXT: [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vsri.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], i32 13, <4 x i1> [[TMP1]])
// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
uint32x4_t