1 ; RUN: llc -march=aarch64 -aarch64-neon-syntax=generic < %s | FileCheck %s
3 define i8 @add_B(<16 x i8>* %arr) {
5 ; CHECK: addv {{b[0-9]+}}, {{v[0-9]+}}.16b
6 %bin.rdx = load <16 x i8>, <16 x i8>* %arr
7 %rdx.shuf0 = shufflevector <16 x i8> %bin.rdx, <16 x i8> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef,i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
8 %bin.rdx0 = add <16 x i8> %bin.rdx, %rdx.shuf0
9 %rdx.shuf = shufflevector <16 x i8> %bin.rdx0, <16 x i8> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef,i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef >
10 %bin.rdx11 = add <16 x i8> %bin.rdx0, %rdx.shuf
11 %rdx.shuf12 = shufflevector <16 x i8> %bin.rdx11, <16 x i8> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef>
12 %bin.rdx13 = add <16 x i8> %bin.rdx11, %rdx.shuf12
13 %rdx.shuf13 = shufflevector <16 x i8> %bin.rdx13, <16 x i8> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef>
14 %bin.rdx14 = add <16 x i8> %bin.rdx13, %rdx.shuf13
15 %r = extractelement <16 x i8> %bin.rdx14, i32 0
19 define i16 @add_H(<8 x i16>* %arr) {
21 ; CHECK: addv {{h[0-9]+}}, {{v[0-9]+}}.8h
22 %bin.rdx = load <8 x i16>, <8 x i16>* %arr
23 %rdx.shuf = shufflevector <8 x i16> %bin.rdx, <8 x i16> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef,i32 undef, i32 undef>
24 %bin.rdx11 = add <8 x i16> %bin.rdx, %rdx.shuf
25 %rdx.shuf12 = shufflevector <8 x i16> %bin.rdx11, <8 x i16> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
26 %bin.rdx13 = add <8 x i16> %bin.rdx11, %rdx.shuf12
27 %rdx.shuf13 = shufflevector <8 x i16> %bin.rdx13, <8 x i16> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
28 %bin.rdx14 = add <8 x i16> %bin.rdx13, %rdx.shuf13
29 %r = extractelement <8 x i16> %bin.rdx14, i32 0
33 define i32 @add_S( <4 x i32>* %arr) {
35 ; CHECK: addv {{s[0-9]+}}, {{v[0-9]+}}.4s
36 %bin.rdx = load <4 x i32>, <4 x i32>* %arr
37 %rdx.shuf = shufflevector <4 x i32> %bin.rdx, <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
38 %bin.rdx11 = add <4 x i32> %bin.rdx, %rdx.shuf
39 %rdx.shuf12 = shufflevector <4 x i32> %bin.rdx11, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
40 %bin.rdx13 = add <4 x i32> %bin.rdx11, %rdx.shuf12
41 %r = extractelement <4 x i32> %bin.rdx13, i32 0
45 define i64 @add_D(<2 x i64>* %arr) {
48 %bin.rdx = load <2 x i64>, <2 x i64>* %arr
49 %rdx.shuf0 = shufflevector <2 x i64> %bin.rdx, <2 x i64> undef, <2 x i32> <i32 1, i32 undef>
50 %bin.rdx0 = add <2 x i64> %bin.rdx, %rdx.shuf0
51 %r = extractelement <2 x i64> %bin.rdx0, i32 0
55 define i32 @oversized_ADDV_256(i8* noalias nocapture readonly %arg1, i8* noalias nocapture readonly %arg2) {
56 ; CHECK-LABEL: oversized_ADDV_256
57 ; CHECK: addv {{s[0-9]+}}, {{v[0-9]+}}.4s
59 %0 = bitcast i8* %arg1 to <8 x i8>*
60 %1 = load <8 x i8>, <8 x i8>* %0, align 1
61 %2 = zext <8 x i8> %1 to <8 x i32>
62 %3 = bitcast i8* %arg2 to <8 x i8>*
63 %4 = load <8 x i8>, <8 x i8>* %3, align 1
64 %5 = zext <8 x i8> %4 to <8 x i32>
65 %6 = sub nsw <8 x i32> %2, %5
66 %7 = icmp slt <8 x i32> %6, zeroinitializer
67 %8 = sub nsw <8 x i32> zeroinitializer, %6
68 %9 = select <8 x i1> %7, <8 x i32> %8, <8 x i32> %6
69 %rdx.shuf = shufflevector <8 x i32> %9, <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
70 %bin.rdx = add <8 x i32> %9, %rdx.shuf
71 %rdx.shuf1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
72 %bin.rdx2 = add <8 x i32> %bin.rdx, %rdx.shuf1
73 %rdx.shuf3 = shufflevector <8 x i32> %bin.rdx2, <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
74 %bin.rdx4 = add <8 x i32> %bin.rdx2, %rdx.shuf3
75 %10 = extractelement <8 x i32> %bin.rdx4, i32 0
79 define i32 @oversized_ADDV_512(<16 x i32>* %arr) {
80 ; CHECK-LABEL: oversized_ADDV_512
81 ; CHECK: addv {{s[0-9]+}}, {{v[0-9]+}}.4s
82 %bin.rdx = load <16 x i32>, <16 x i32>* %arr
84 %rdx.shuf0 = shufflevector <16 x i32> %bin.rdx, <16 x i32> undef, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef,i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
85 %bin.rdx0 = add <16 x i32> %bin.rdx, %rdx.shuf0
87 %rdx.shuf = shufflevector <16 x i32> %bin.rdx0, <16 x i32> undef, <16 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef,i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef >
88 %bin.rdx11 = add <16 x i32> %bin.rdx0, %rdx.shuf
90 %rdx.shuf12 = shufflevector <16 x i32> %bin.rdx11, <16 x i32> undef, <16 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef>
91 %bin.rdx13 = add <16 x i32> %bin.rdx11, %rdx.shuf12
93 %rdx.shuf13 = shufflevector <16 x i32> %bin.rdx13, <16 x i32> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef, i32 undef, i32 undef,i32 undef, i32 undef>
94 %bin.rdx14 = add <16 x i32> %bin.rdx13, %rdx.shuf13
96 %r = extractelement <16 x i32> %bin.rdx14, i32 0