// 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 -sroa | 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 -sroa | FileCheck %s
// REQUIRES: aarch64-registered-target || arm-registered-target
// CHECK-LABEL: @test_vabavq_s8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.vabav.v16i8(i32 0, i32 [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]])
// CHECK-NEXT: ret i32 [[TMP0]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_s16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.vabav.v8i16(i32 0, i32 [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i16> [[C:%.*]])
// CHECK-NEXT: ret i32 [[TMP0]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_s32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.vabav.v4i32(i32 0, i32 [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i32> [[C:%.*]])
// CHECK-NEXT: ret i32 [[TMP0]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_u8(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.vabav.v16i8(i32 1, i32 [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]])
// CHECK-NEXT: ret i32 [[TMP0]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_u16(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.vabav.v8i16(i32 1, i32 [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i16> [[C:%.*]])
// CHECK-NEXT: ret i32 [[TMP0]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_u32(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.arm.mve.vabav.v4i32(i32 1, i32 [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i32> [[C:%.*]])
// CHECK-NEXT: ret i32 [[TMP0]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_p_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 i32 @llvm.arm.mve.vabav.predicated.v16i8.v16i1(i32 0, i32 [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i1> [[TMP1]])
// CHECK-NEXT: ret i32 [[TMP2]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_p_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 i32 @llvm.arm.mve.vabav.predicated.v8i16.v8i1(i32 0, i32 [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i16> [[C:%.*]], <8 x i1> [[TMP1]])
// CHECK-NEXT: ret i32 [[TMP2]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_p_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 i32 @llvm.arm.mve.vabav.predicated.v4i32.v4i1(i32 0, i32 [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i32> [[C:%.*]], <4 x i1> [[TMP1]])
// CHECK-NEXT: ret i32 [[TMP2]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_p_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 i32 @llvm.arm.mve.vabav.predicated.v16i8.v16i1(i32 1, i32 [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i8> [[C:%.*]], <16 x i1> [[TMP1]])
// CHECK-NEXT: ret i32 [[TMP2]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_p_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 i32 @llvm.arm.mve.vabav.predicated.v8i16.v8i1(i32 1, i32 [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i16> [[C:%.*]], <8 x i1> [[TMP1]])
// CHECK-NEXT: ret i32 [[TMP2]]
//
uint32_t
// CHECK-LABEL: @test_vabavq_p_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 i32 @llvm.arm.mve.vabav.predicated.v4i32.v4i1(i32 1, i32 [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i32> [[C:%.*]], <4 x i1> [[TMP1]])
// CHECK-NEXT: ret i32 [[TMP2]]
//
uint32_t