// 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.and.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i1> [[TMP1]], <16 x i8> [[INACTIVE:%.*]])
// 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.and.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i1> [[TMP1]], <8 x i16> [[INACTIVE:%.*]])
// 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.and.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i1> [[TMP1]], <4 x i32> [[INACTIVE:%.*]])
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <8 x half> [[A:%.*]] to <8 x i16>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <8 x half> [[B:%.*]] to <8 x i16>
// CHECK-NEXT: [[TMP2:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 [[TMP2]])
// CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x half> [[INACTIVE:%.*]] to <8 x i16>
// CHECK-NEXT: [[TMP5:%.*]] = call <8 x i16> @llvm.arm.mve.and.predicated.v8i16.v8i1(<8 x i16> [[TMP0]], <8 x i16> [[TMP1]], <8 x i1> [[TMP3]], <8 x i16> [[TMP4]])
// CHECK-NEXT: [[TMP6:%.*]] = bitcast <8 x i16> [[TMP5]] to <8 x half>
// 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.and.predicated.v16i8.v16i1(<16 x i8> [[A:%.*]], <16 x i8> [[B:%.*]], <16 x i1> [[TMP1]], <16 x i8> undef)
// 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.and.predicated.v8i16.v8i1(<8 x i16> [[A:%.*]], <8 x i16> [[B:%.*]], <8 x i1> [[TMP1]], <8 x i16> undef)
// 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.and.predicated.v4i32.v4i1(<4 x i32> [[A:%.*]], <4 x i32> [[B:%.*]], <4 x i1> [[TMP1]], <4 x i32> undef)
// CHECK-NEXT: [[TMP0:%.*]] = bitcast <4 x float> [[A:%.*]] to <4 x i32>
// CHECK-NEXT: [[TMP1:%.*]] = bitcast <4 x float> [[B:%.*]] to <4 x i32>
// CHECK-NEXT: [[TMP2:%.*]] = zext i16 [[P:%.*]] to i32
// CHECK-NEXT: [[TMP3:%.*]] = call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 [[TMP2]])
// CHECK-NEXT: [[TMP4:%.*]] = call <4 x i32> @llvm.arm.mve.and.predicated.v4i32.v4i1(<4 x i32> [[TMP0]], <4 x i32> [[TMP1]], <4 x i1> [[TMP3]], <4 x i32> undef)
// CHECK-NEXT: [[TMP5:%.*]] = bitcast <4 x i32> [[TMP4]] to <4 x float>