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
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve %s -o - | FileCheck %s
define dso_local i32 @test_500_504(ptr nocapture readonly %x) {
; CHECK-LABEL: test_500_504:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w lr, #126
; CHECK-NEXT: adr r2, .LCPI0_0
; CHECK-NEXT: vldrw.u32 q0, [r2]
; CHECK-NEXT: mov.w r2, #500
; CHECK-NEXT: vdup.32 q1, r2
; CHECK-NEXT: movs r1, #0
; CHECK-NEXT: movs r2, #0
; CHECK-NEXT: .LBB0_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vqadd.u32 q2, q0, r1
; CHECK-NEXT: adds r1, #4
; CHECK-NEXT: vptt.u32 hi, q1, q2
; CHECK-NEXT: vldrwt.u32 q2, [r0], #16
; CHECK-NEXT: vaddvat.u32 r2, q2
; CHECK-NEXT: le lr, .LBB0_1
; CHECK-NEXT: @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT: mov r0, r2
; CHECK-NEXT: pop {r7, pc}
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: @ %bb.3:
; CHECK-NEXT: .LCPI0_0:
; CHECK-NEXT: .long 0 @ 0x0
; CHECK-NEXT: .long 1 @ 0x1
; CHECK-NEXT: .long 2 @ 0x2
; CHECK-NEXT: .long 3 @ 0x3
entry:
br label %vector.body
vector.body: ; preds = %vector.body, %entry
%index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
%vec.phi = phi i32 [ 0, %entry ], [ %4, %vector.body ]
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 500)
%0 = getelementptr inbounds i32, ptr %x, i32 %index
%1 = bitcast ptr %0 to ptr
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
%2 = select <4 x i1> %active.lane.mask, <4 x i32> %wide.masked.load, <4 x i32> zeroinitializer
%3 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %2)
%4 = add i32 %3, %vec.phi
%index.next = add i32 %index, 4
%5 = icmp eq i32 %index.next, 504
br i1 %5, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body
ret i32 %4
}
define dso_local i32 @test_501_504(ptr nocapture readonly %x) {
; CHECK-LABEL: test_501_504:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: movw r1, #501
; CHECK-NEXT: movs r2, #0
; CHECK-NEXT: dlstp.32 lr, r1
; CHECK-NEXT: .LBB1_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16
; CHECK-NEXT: vaddva.u32 r2, q0
; CHECK-NEXT: letp lr, .LBB1_1
; CHECK-NEXT: @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT: mov r0, r2
; CHECK-NEXT: pop {r7, pc}
entry:
br label %vector.body
vector.body: ; preds = %vector.body, %entry
%index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
%vec.phi = phi i32 [ 0, %entry ], [ %4, %vector.body ]
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 501)
%0 = getelementptr inbounds i32, ptr %x, i32 %index
%1 = bitcast ptr %0 to ptr
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
%2 = select <4 x i1> %active.lane.mask, <4 x i32> %wide.masked.load, <4 x i32> zeroinitializer
%3 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %2)
%4 = add i32 %3, %vec.phi
%index.next = add i32 %index, 4
%5 = icmp eq i32 %index.next, 504
br i1 %5, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body
ret i32 %4
}
define dso_local i32 @test_502_504(ptr nocapture readonly %x) {
; CHECK-LABEL: test_502_504:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w r1, #502
; CHECK-NEXT: movs r2, #0
; CHECK-NEXT: dlstp.32 lr, r1
; CHECK-NEXT: .LBB2_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16
; CHECK-NEXT: vaddva.u32 r2, q0
; CHECK-NEXT: letp lr, .LBB2_1
; CHECK-NEXT: @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT: mov r0, r2
; CHECK-NEXT: pop {r7, pc}
entry:
br label %vector.body
vector.body: ; preds = %vector.body, %entry
%index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
%vec.phi = phi i32 [ 0, %entry ], [ %4, %vector.body ]
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 502)
%0 = getelementptr inbounds i32, ptr %x, i32 %index
%1 = bitcast ptr %0 to ptr
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
%2 = select <4 x i1> %active.lane.mask, <4 x i32> %wide.masked.load, <4 x i32> zeroinitializer
%3 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %2)
%4 = add i32 %3, %vec.phi
%index.next = add i32 %index, 4
%5 = icmp eq i32 %index.next, 504
br i1 %5, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body
ret i32 %4
}
define dso_local i32 @test_503_504(ptr nocapture readonly %x) {
; CHECK-LABEL: test_503_504:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: movw r1, #503
; CHECK-NEXT: movs r2, #0
; CHECK-NEXT: dlstp.32 lr, r1
; CHECK-NEXT: .LBB3_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16
; CHECK-NEXT: vaddva.u32 r2, q0
; CHECK-NEXT: letp lr, .LBB3_1
; CHECK-NEXT: @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT: mov r0, r2
; CHECK-NEXT: pop {r7, pc}
entry:
br label %vector.body
vector.body: ; preds = %vector.body, %entry
%index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
%vec.phi = phi i32 [ 0, %entry ], [ %4, %vector.body ]
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 503)
%0 = getelementptr inbounds i32, ptr %x, i32 %index
%1 = bitcast ptr %0 to ptr
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
%2 = select <4 x i1> %active.lane.mask, <4 x i32> %wide.masked.load, <4 x i32> zeroinitializer
%3 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %2)
%4 = add i32 %3, %vec.phi
%index.next = add i32 %index, 4
%5 = icmp eq i32 %index.next, 504
br i1 %5, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body
ret i32 %4
}
define dso_local i32 @test_504_504(ptr nocapture readonly %x) {
; CHECK-LABEL: test_504_504:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: mov.w r1, #504
; CHECK-NEXT: movs r2, #0
; CHECK-NEXT: dlstp.32 lr, r1
; CHECK-NEXT: .LBB4_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16
; CHECK-NEXT: vaddva.u32 r2, q0
; CHECK-NEXT: letp lr, .LBB4_1
; CHECK-NEXT: @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT: mov r0, r2
; CHECK-NEXT: pop {r7, pc}
entry:
br label %vector.body
vector.body: ; preds = %vector.body, %entry
%index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
%vec.phi = phi i32 [ 0, %entry ], [ %4, %vector.body ]
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 504)
%0 = getelementptr inbounds i32, ptr %x, i32 %index
%1 = bitcast ptr %0 to ptr
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr %1, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
%2 = select <4 x i1> %active.lane.mask, <4 x i32> %wide.masked.load, <4 x i32> zeroinitializer
%3 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %2)
%4 = add i32 %3, %vec.phi
%index.next = add i32 %index, 4
%5 = icmp eq i32 %index.next, 504
br i1 %5, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body
ret i32 %4
}
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
declare <4 x i32> @llvm.masked.load.v4i32.p0(ptr, i32 immarg, <4 x i1>, <4 x i32>)
declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32>)
|
