1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -verify-machineinstrs -mattr=+mve.fp %s -o - | FileCheck %s
define arm_aapcs_vfpcc <4 x i32> @vaddqr_v4i32(<4 x i32> %src, i32 %src2, <4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: vaddqr_v4i32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vadd.i32 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%i = insertelement <4 x i32> undef, i32 %src2, i32 0
%sp = shufflevector <4 x i32> %i, <4 x i32> undef, <4 x i32> zeroinitializer
%c = add <4 x i32> %src, %sp
ret <4 x i32> %c
}
define arm_aapcs_vfpcc <8 x i16> @vaddqr_v8i16(<8 x i16> %src, i16 %src2, <8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: vaddqr_v8i16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vadd.i16 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%i = insertelement <8 x i16> undef, i16 %src2, i32 0
%sp = shufflevector <8 x i16> %i, <8 x i16> undef, <8 x i32> zeroinitializer
%c = add <8 x i16> %src, %sp
ret <8 x i16> %c
}
define arm_aapcs_vfpcc <16 x i8> @vaddqr_v16i8(<16 x i8> %src, i8 %src2, <16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: vaddqr_v16i8:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vadd.i8 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%i = insertelement <16 x i8> undef, i8 %src2, i32 0
%sp = shufflevector <16 x i8> %i, <16 x i8> undef, <16 x i32> zeroinitializer
%c = add <16 x i8> %src, %sp
ret <16 x i8> %c
}
define arm_aapcs_vfpcc <4 x i32> @vaddqr_v4i32_2(<4 x i32> %src, i32 %src2, <4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: vaddqr_v4i32_2:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vadd.i32 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%i = insertelement <4 x i32> undef, i32 %src2, i32 0
%sp = shufflevector <4 x i32> %i, <4 x i32> undef, <4 x i32> zeroinitializer
%c = add <4 x i32> %sp, %src
ret <4 x i32> %c
}
define arm_aapcs_vfpcc <8 x i16> @vaddqr_v8i16_2(<8 x i16> %src, i16 %src2, <8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: vaddqr_v8i16_2:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vadd.i16 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%i = insertelement <8 x i16> undef, i16 %src2, i32 0
%sp = shufflevector <8 x i16> %i, <8 x i16> undef, <8 x i32> zeroinitializer
%c = add <8 x i16> %sp, %src
ret <8 x i16> %c
}
define arm_aapcs_vfpcc <16 x i8> @vaddqr_v16i8_2(<16 x i8> %src, i8 %src2, <16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: vaddqr_v16i8_2:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vadd.i8 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%i = insertelement <16 x i8> undef, i8 %src2, i32 0
%sp = shufflevector <16 x i8> %i, <16 x i8> undef, <16 x i32> zeroinitializer
%c = add <16 x i8> %sp, %src
ret <16 x i8> %c
}
define arm_aapcs_vfpcc <4 x float> @vaddqr_v4f32(<4 x float> %src, float %src2, <4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: vaddqr_v4f32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov r0, s4
; CHECK-NEXT: vadd.f32 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%i = insertelement <4 x float> undef, float %src2, i32 0
%sp = shufflevector <4 x float> %i, <4 x float> undef, <4 x i32> zeroinitializer
%c = fadd <4 x float> %src, %sp
ret <4 x float> %c
}
define arm_aapcs_vfpcc <8 x half> @vaddqr_v8f16(<8 x half> %src, half %src2, <8 x half> %a, <8 x half> %b) {
; CHECK-LABEL: vaddqr_v8f16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.f16 r0, s4
; CHECK-NEXT: vadd.f16 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%i = insertelement <8 x half> undef, half %src2, i32 0
%sp = shufflevector <8 x half> %i, <8 x half> undef, <8 x i32> zeroinitializer
%c = fadd <8 x half> %src, %sp
ret <8 x half> %c
}
define arm_aapcs_vfpcc <4 x float> @vaddqr_v4f32_2(<4 x float> %src, float %src2, <4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: vaddqr_v4f32_2:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov r0, s4
; CHECK-NEXT: vadd.f32 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%i = insertelement <4 x float> undef, float %src2, i32 0
%sp = shufflevector <4 x float> %i, <4 x float> undef, <4 x i32> zeroinitializer
%c = fadd <4 x float> %sp, %src
ret <4 x float> %c
}
define arm_aapcs_vfpcc <8 x half> @vaddqr_v8f16_2(<8 x half> %src, half %src2, <8 x half> %a, <8 x half> %b) {
; CHECK-LABEL: vaddqr_v8f16_2:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.f16 r0, s4
; CHECK-NEXT: vadd.f16 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%i = insertelement <8 x half> undef, half %src2, i32 0
%sp = shufflevector <8 x half> %i, <8 x half> undef, <8 x i32> zeroinitializer
%c = fadd <8 x half> %sp, %src
ret <8 x half> %c
}
define arm_aapcs_vfpcc <4 x float> @vaddqr_v4f32_3(<4 x float> %src, float %src2, <4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: vaddqr_v4f32_3:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov r0, s4
; CHECK-NEXT: vadd.f32 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%src2bc = bitcast float %src2 to i32
%i = insertelement <4 x i32> undef, i32 %src2bc, i32 0
%spbc = shufflevector <4 x i32> %i, <4 x i32> undef, <4 x i32> zeroinitializer
%sp = bitcast <4 x i32> %spbc to <4 x float>
%c = fadd <4 x float> %src, %sp
ret <4 x float> %c
}
define arm_aapcs_vfpcc <8 x half> @vaddqr_v8f16_3(<8 x half> %src, half %src2, <8 x half> %a, <8 x half> %b) {
; CHECK-LABEL: vaddqr_v8f16_3:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.f16 r0, s4
; CHECK-NEXT: vadd.f16 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%src2bc = bitcast half %src2 to i16
%i = insertelement <8 x i16> undef, i16 %src2bc, i32 0
%spbc = shufflevector <8 x i16> %i, <8 x i16> undef, <8 x i32> zeroinitializer
%sp = bitcast <8 x i16> %spbc to <8 x half>
%c = fadd <8 x half> %src, %sp
ret <8 x half> %c
}
define arm_aapcs_vfpcc <4 x float> @vaddqr_v4f32_4(<4 x float> %src, float %src2, <4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: vaddqr_v4f32_4:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov r0, s4
; CHECK-NEXT: vadd.f32 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%src2bc = bitcast float %src2 to i32
%i = insertelement <4 x i32> undef, i32 %src2bc, i32 0
%spbc = shufflevector <4 x i32> %i, <4 x i32> undef, <4 x i32> zeroinitializer
%sp = bitcast <4 x i32> %spbc to <4 x float>
%c = fadd <4 x float> %sp, %src
ret <4 x float> %c
}
define arm_aapcs_vfpcc <8 x half> @vaddqr_v8f16_4(<8 x half> %src, half %src2, <8 x half> %a, <8 x half> %b) {
; CHECK-LABEL: vaddqr_v8f16_4:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.f16 r0, s4
; CHECK-NEXT: vadd.f16 q0, q0, r0
; CHECK-NEXT: bx lr
entry:
%src2bc = bitcast half %src2 to i16
%i = insertelement <8 x i16> undef, i16 %src2bc, i32 0
%spbc = shufflevector <8 x i16> %i, <8 x i16> undef, <8 x i32> zeroinitializer
%sp = bitcast <8 x i16> %spbc to <8 x half>
%c = fadd <8 x half> %sp, %src
ret <8 x half> %c
}
|
