1 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
2 ; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
4 define arm_aapcs_vfpcc <16 x i8> @test_vmaxaq_s8(<16 x i8> %a, <16 x i8> %b) local_unnamed_addr #0 {
5 ; CHECK-LABEL: test_vmaxaq_s8:
6 ; CHECK: @ %bb.0: @ %entry
7 ; CHECK-NEXT: vmaxa.s8 q0, q1
10 %0 = icmp slt <16 x i8> %b, zeroinitializer
11 %1 = sub <16 x i8> zeroinitializer, %b
12 %2 = select <16 x i1> %0, <16 x i8> %1, <16 x i8> %b
13 %3 = icmp ugt <16 x i8> %2, %a
14 %4 = select <16 x i1> %3, <16 x i8> %2, <16 x i8> %a
18 define arm_aapcs_vfpcc <8 x i16> @test_vmaxaq_s16(<8 x i16> %a, <8 x i16> %b) local_unnamed_addr #0 {
19 ; CHECK-LABEL: test_vmaxaq_s16:
20 ; CHECK: @ %bb.0: @ %entry
21 ; CHECK-NEXT: vmaxa.s16 q0, q1
24 %0 = icmp slt <8 x i16> %b, zeroinitializer
25 %1 = sub <8 x i16> zeroinitializer, %b
26 %2 = select <8 x i1> %0, <8 x i16> %1, <8 x i16> %b
27 %3 = icmp ugt <8 x i16> %2, %a
28 %4 = select <8 x i1> %3, <8 x i16> %2, <8 x i16> %a
32 define arm_aapcs_vfpcc <4 x i32> @test_vmaxaq_s32(<4 x i32> %a, <4 x i32> %b) local_unnamed_addr #0 {
33 ; CHECK-LABEL: test_vmaxaq_s32:
34 ; CHECK: @ %bb.0: @ %entry
35 ; CHECK-NEXT: vmaxa.s32 q0, q1
38 %0 = icmp slt <4 x i32> %b, zeroinitializer
39 %1 = sub <4 x i32> zeroinitializer, %b
40 %2 = select <4 x i1> %0, <4 x i32> %1, <4 x i32> %b
41 %3 = icmp ugt <4 x i32> %2, %a
42 %4 = select <4 x i1> %3, <4 x i32> %2, <4 x i32> %a
46 define arm_aapcs_vfpcc <16 x i8> @test_vmaxaq_m_s8(<16 x i8> %a, <16 x i8> %b, i16 zeroext %p) local_unnamed_addr #1 {
47 ; CHECK-LABEL: test_vmaxaq_m_s8:
48 ; CHECK: @ %bb.0: @ %entry
49 ; CHECK-NEXT: vmsr p0, r0
51 ; CHECK-NEXT: vmaxat.s8 q0, q1
54 %0 = zext i16 %p to i32
55 %1 = tail call <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32 %0)
56 %2 = tail call <16 x i8> @llvm.arm.mve.vmaxa.predicated.v16i8.v16i1(<16 x i8> %a, <16 x i8> %b, <16 x i1> %1)
60 declare <16 x i1> @llvm.arm.mve.pred.i2v.v16i1(i32) #2
62 declare <16 x i8> @llvm.arm.mve.vmaxa.predicated.v16i8.v16i1(<16 x i8>, <16 x i8>, <16 x i1>) #2
64 define arm_aapcs_vfpcc <8 x i16> @test_vmaxaq_m_s16(<8 x i16> %a, <8 x i16> %b, i16 zeroext %p) local_unnamed_addr #1 {
65 ; CHECK-LABEL: test_vmaxaq_m_s16:
66 ; CHECK: @ %bb.0: @ %entry
67 ; CHECK-NEXT: vmsr p0, r0
69 ; CHECK-NEXT: vmaxat.s16 q0, q1
72 %0 = zext i16 %p to i32
73 %1 = tail call <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32 %0)
74 %2 = tail call <8 x i16> @llvm.arm.mve.vmaxa.predicated.v8i16.v8i1(<8 x i16> %a, <8 x i16> %b, <8 x i1> %1)
78 declare <8 x i1> @llvm.arm.mve.pred.i2v.v8i1(i32) #2
80 declare <8 x i16> @llvm.arm.mve.vmaxa.predicated.v8i16.v8i1(<8 x i16>, <8 x i16>, <8 x i1>) #2
82 define arm_aapcs_vfpcc <4 x i32> @test_vmaxaq_m_s32(<4 x i32> %a, <4 x i32> %b, i16 zeroext %p) local_unnamed_addr #1 {
83 ; CHECK-LABEL: test_vmaxaq_m_s32:
84 ; CHECK: @ %bb.0: @ %entry
85 ; CHECK-NEXT: vmsr p0, r0
87 ; CHECK-NEXT: vmaxat.s32 q0, q1
90 %0 = zext i16 %p to i32
91 %1 = tail call <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32 %0)
92 %2 = tail call <4 x i32> @llvm.arm.mve.vmaxa.predicated.v4i32.v4i1(<4 x i32> %a, <4 x i32> %b, <4 x i1> %1)
96 declare <4 x i1> @llvm.arm.mve.pred.i2v.v4i1(i32) #2
98 declare <4 x i32> @llvm.arm.mve.vmaxa.predicated.v4i32.v4i1(<4 x i32>, <4 x i32>, <4 x i1>) #2