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
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp %s -o - | FileCheck %s
define float @minf32(float* noalias nocapture readonly %s1, float* noalias nocapture readonly %s2, float* noalias nocapture %d, i32 %n) {
; CHECK-LABEL: minf32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: cmp r3, #1
; CHECK-NEXT: it lt
; CHECK-NEXT: poplt {r7, pc}
; CHECK-NEXT: .LBB0_1: @ %vector.ph
; CHECK-NEXT: dlstp.32 lr, r3
; CHECK-NEXT: .LBB0_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r0], #16
; CHECK-NEXT: vldrw.u32 q1, [r1], #16
; CHECK-NEXT: vabs.f32 q0, q0
; CHECK-NEXT: vminnm.f32 q0, q0, q1
; CHECK-NEXT: vstrw.32 q0, [r2], #16
; CHECK-NEXT: letp lr, .LBB0_2
; CHECK-NEXT: @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT: pop {r7, pc}
entry:
%cmp8 = icmp sgt i32 %n, 0
br i1 %cmp8, label %vector.ph, label %for.cond.cleanup
vector.ph: ; preds = %entry
%n.rnd.up = add i32 %n, 3
%n.vec = and i32 %n.rnd.up, -4
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
%0 = getelementptr inbounds float, float* %s1, i32 %index
%1 = bitcast float* %0 to <4 x float>*
%wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %1, i32 4, <4 x i1> %active.lane.mask, <4 x float> poison)
%2 = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> %wide.masked.load)
%3 = getelementptr inbounds float, float* %s2, i32 %index
%4 = bitcast float* %3 to <4 x float>*
%wide.masked.load10 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x float> poison)
%5 = call fast <4 x float> @llvm.minnum.v4f32(<4 x float> %2, <4 x float> %wide.masked.load10)
%6 = getelementptr inbounds float, float* %d, i32 %index
%7 = bitcast float* %6 to <4 x float>*
call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> %5, <4 x float>* %7, i32 4, <4 x i1> %active.lane.mask)
%index.next = add i32 %index, 4
%8 = icmp eq i32 %index.next, %n.vec
br i1 %8, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body, %entry
ret float undef
}
define float @maxaf32(float* noalias nocapture readonly %s1, float* noalias nocapture readonly %s2, float* noalias nocapture %d, i32 %n) {
; CHECK-LABEL: maxaf32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: cmp r3, #1
; CHECK-NEXT: it lt
; CHECK-NEXT: poplt {r7, pc}
; CHECK-NEXT: .LBB1_1: @ %vector.ph
; CHECK-NEXT: dlstp.32 lr, r3
; CHECK-NEXT: .LBB1_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrw.u32 q0, [r1], #16
; CHECK-NEXT: vldrw.u32 q1, [r0], #16
; CHECK-NEXT: vmaxnma.f32 q1, q0
; CHECK-NEXT: vstrw.32 q1, [r2], #16
; CHECK-NEXT: letp lr, .LBB1_2
; CHECK-NEXT: @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT: pop {r7, pc}
entry:
%cmp8 = icmp sgt i32 %n, 0
br i1 %cmp8, label %vector.ph, label %for.cond.cleanup
vector.ph: ; preds = %entry
%n.rnd.up = add i32 %n, 3
%n.vec = and i32 %n.rnd.up, -4
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
%0 = getelementptr inbounds float, float* %s1, i32 %index
%1 = bitcast float* %0 to <4 x float>*
%wide.masked.load = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %1, i32 4, <4 x i1> %active.lane.mask, <4 x float> poison)
%2 = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> %wide.masked.load)
%3 = getelementptr inbounds float, float* %s2, i32 %index
%4 = bitcast float* %3 to <4 x float>*
%wide.masked.load10 = call <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %4, i32 4, <4 x i1> %active.lane.mask, <4 x float> poison)
%5 = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> %wide.masked.load10)
%6 = call fast <4 x float> @llvm.maxnum.v4f32(<4 x float> %2, <4 x float> %5)
%7 = getelementptr inbounds float, float* %d, i32 %index
%8 = bitcast float* %7 to <4 x float>*
call void @llvm.masked.store.v4f32.p0v4f32(<4 x float> %6, <4 x float>* %8, i32 4, <4 x i1> %active.lane.mask)
%index.next = add i32 %index, 4
%9 = icmp eq i32 %index.next, %n.vec
br i1 %9, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body, %entry
ret float undef
}
define half @maxf16(half* noalias nocapture readonly %s1, half* noalias nocapture readonly %s2, half* noalias nocapture %d, i32 %n) {
; CHECK-LABEL: maxf16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: cmp r3, #1
; CHECK-NEXT: it lt
; CHECK-NEXT: poplt {r7, pc}
; CHECK-NEXT: .LBB2_1: @ %vector.ph
; CHECK-NEXT: dlstp.16 lr, r3
; CHECK-NEXT: .LBB2_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.u16 q0, [r0], #16
; CHECK-NEXT: vldrh.u16 q1, [r1], #16
; CHECK-NEXT: vabs.f16 q0, q0
; CHECK-NEXT: vmaxnm.f16 q0, q0, q1
; CHECK-NEXT: vstrh.16 q0, [r2], #16
; CHECK-NEXT: letp lr, .LBB2_2
; CHECK-NEXT: @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT: pop {r7, pc}
entry:
%cmp10 = icmp sgt i32 %n, 0
br i1 %cmp10, label %vector.ph, label %for.cond.cleanup
vector.ph: ; preds = %entry
%n.rnd.up = add i32 %n, 7
%n.vec = and i32 %n.rnd.up, -8
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %n)
%0 = getelementptr inbounds half, half* %s1, i32 %index
%1 = bitcast half* %0 to <8 x half>*
%wide.masked.load = call <8 x half> @llvm.masked.load.v8f16.p0v8f16(<8 x half>* %1, i32 2, <8 x i1> %active.lane.mask, <8 x half> poison)
%2 = call fast <8 x half> @llvm.fabs.v8f16(<8 x half> %wide.masked.load)
%3 = getelementptr inbounds half, half* %s2, i32 %index
%4 = bitcast half* %3 to <8 x half>*
%wide.masked.load12 = call <8 x half> @llvm.masked.load.v8f16.p0v8f16(<8 x half>* %4, i32 2, <8 x i1> %active.lane.mask, <8 x half> poison)
%5 = call fast <8 x half> @llvm.maxnum.v8f16(<8 x half> %2, <8 x half> %wide.masked.load12)
%6 = getelementptr inbounds half, half* %d, i32 %index
%7 = bitcast half* %6 to <8 x half>*
call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> %5, <8 x half>* %7, i32 2, <8 x i1> %active.lane.mask)
%index.next = add i32 %index, 8
%8 = icmp eq i32 %index.next, %n.vec
br i1 %8, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body, %entry
ret half undef
}
define half @minaf16(half* noalias nocapture readonly %s1, half* noalias nocapture readonly %s2, half* noalias nocapture %d, i32 %n) {
; CHECK-LABEL: minaf16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .save {r7, lr}
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: cmp r3, #1
; CHECK-NEXT: it lt
; CHECK-NEXT: poplt {r7, pc}
; CHECK-NEXT: .LBB3_1: @ %vector.ph
; CHECK-NEXT: dlstp.16 lr, r3
; CHECK-NEXT: .LBB3_2: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vldrh.u16 q0, [r1], #16
; CHECK-NEXT: vldrh.u16 q1, [r0], #16
; CHECK-NEXT: vminnma.f16 q1, q0
; CHECK-NEXT: vstrh.16 q1, [r2], #16
; CHECK-NEXT: letp lr, .LBB3_2
; CHECK-NEXT: @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT: pop {r7, pc}
entry:
%cmp10 = icmp sgt i32 %n, 0
br i1 %cmp10, label %vector.ph, label %for.cond.cleanup
vector.ph: ; preds = %entry
%n.rnd.up = add i32 %n, 7
%n.vec = and i32 %n.rnd.up, -8
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %n)
%0 = getelementptr inbounds half, half* %s1, i32 %index
%1 = bitcast half* %0 to <8 x half>*
%wide.masked.load = call <8 x half> @llvm.masked.load.v8f16.p0v8f16(<8 x half>* %1, i32 2, <8 x i1> %active.lane.mask, <8 x half> poison)
%2 = call fast <8 x half> @llvm.fabs.v8f16(<8 x half> %wide.masked.load)
%3 = getelementptr inbounds half, half* %s2, i32 %index
%4 = bitcast half* %3 to <8 x half>*
%wide.masked.load12 = call <8 x half> @llvm.masked.load.v8f16.p0v8f16(<8 x half>* %4, i32 2, <8 x i1> %active.lane.mask, <8 x half> poison)
%5 = call fast <8 x half> @llvm.fabs.v8f16(<8 x half> %wide.masked.load12)
%6 = call fast <8 x half> @llvm.minnum.v8f16(<8 x half> %2, <8 x half> %5)
%7 = getelementptr inbounds half, half* %d, i32 %index
%8 = bitcast half* %7 to <8 x half>*
call void @llvm.masked.store.v8f16.p0v8f16(<8 x half> %6, <8 x half>* %8, i32 2, <8 x i1> %active.lane.mask)
%index.next = add i32 %index, 8
%9 = icmp eq i32 %index.next, %n.vec
br i1 %9, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body, %entry
ret half undef
}
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32 immarg, <4 x i1>, <4 x float>)
declare <4 x float> @llvm.fabs.v4f32(<4 x float>)
declare <4 x float> @llvm.minnum.v4f32(<4 x float>, <4 x float>)
declare <4 x float> @llvm.maxnum.v4f32(<4 x float>, <4 x float>)
declare void @llvm.masked.store.v4f32.p0v4f32(<4 x float>, <4 x float>*, i32 immarg, <4 x i1>)
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32)
declare <8 x half> @llvm.masked.load.v8f16.p0v8f16(<8 x half>*, i32 immarg, <8 x i1>, <8 x half>)
declare <8 x half> @llvm.fabs.v8f16(<8 x half>)
declare <8 x half> @llvm.minnum.v8f16(<8 x half>, <8 x half>)
declare <8 x half> @llvm.maxnum.v8f16(<8 x half>, <8 x half>)
declare void @llvm.masked.store.v8f16.p0v8f16(<8 x half>, <8 x half>*, i32 immarg, <8 x i1>)
|
