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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=armv8.1m.main -mattr=+mve -enable-arm-maskedldst=true -disable-mve-tail-predication=false --verify-machineinstrs %s -o - | FileCheck %s
define dso_local i32 @mul_reduce_add(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32 %N) {
; CHECK-LABEL: mul_reduce_add:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: cmp r2, #0
; CHECK-NEXT: itt eq
; CHECK-NEXT: moveq r0, #0
; CHECK-NEXT: bxeq lr
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: adds r3, r2, #3
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: bic r3, r3, #3
; CHECK-NEXT: sub.w r12, r3, #4
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: add.w lr, r3, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB0_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vmov q1, q0
; CHECK-NEXT: vctp.32 r2
; CHECK-NEXT: vpstt
; CHECK-NEXT: vldrwt.u32 q0, [r0]
; CHECK-NEXT: vldrwt.u32 q2, [r1]
; CHECK-NEXT: mov r3, r2
; CHECK-NEXT: vmul.i32 q0, q2, q0
; CHECK-NEXT: adds r0, #16
; CHECK-NEXT: adds r1, #16
; CHECK-NEXT: subs r2, #4
; CHECK-NEXT: vadd.i32 q0, q0, q1
; CHECK-NEXT: le lr, .LBB0_1
; CHECK-NEXT: @ %bb.2: @ %middle.block
; CHECK-NEXT: vctp.32 r3
; CHECK-NEXT: vpsel q0, q0, q1
; CHECK-NEXT: vaddv.u32 r0, q0
; CHECK-NEXT: pop {r7, pc}
entry:
%cmp8 = icmp eq i32 %N, 0
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%n.rnd.up = add i32 %N, 3
%n.vec = and i32 %n.rnd.up, -4
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert11 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat12 = shufflevector <4 x i32> %broadcast.splatinsert11, <4 x i32> undef, <4 x i32> zeroinitializer
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %6, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%0 = getelementptr inbounds i32, i32* %a, i32 %index
%1 = icmp ule <4 x i32> %induction, %broadcast.splat12
%2 = bitcast i32* %0 to <4 x i32>*
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %2, i32 4, <4 x i1> %1, <4 x i32> undef)
%3 = getelementptr inbounds i32, i32* %b, i32 %index
%4 = bitcast i32* %3 to <4 x i32>*
%wide.masked.load13 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %4, i32 4, <4 x i1> %1, <4 x i32> undef)
%5 = mul nsw <4 x i32> %wide.masked.load13, %wide.masked.load
%6 = add nsw <4 x i32> %5, %vec.phi
%index.next = add i32 %index, 4
%7 = icmp eq i32 %index.next, %n.vec
br i1 %7, label %middle.block, label %vector.body
middle.block: ; preds = %vector.body
%8 = select <4 x i1> %1, <4 x i32> %6, <4 x i32> %vec.phi
%9 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %8)
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %middle.block, %entry
%res.0.lcssa = phi i32 [ 0, %entry ], [ %9, %middle.block ]
ret i32 %res.0.lcssa
}
define dso_local i32 @mul_reduce_add_const(i32* noalias nocapture readonly %a, i32 %b, i32 %N) {
; CHECK-LABEL: mul_reduce_add_const:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: cmp r2, #0
; CHECK-NEXT: itt eq
; CHECK-NEXT: moveq r0, #0
; CHECK-NEXT: bxeq lr
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: adds r1, r2, #3
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: bic r1, r1, #3
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: subs r1, #4
; CHECK-NEXT: add.w lr, r3, r1, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB1_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: mov r1, r2
; CHECK-NEXT: vctp.32 r2
; CHECK-NEXT: vmov q1, q0
; CHECK-NEXT: vpst
; CHECK-NEXT: vldrwt.u32 q0, [r0]
; CHECK-NEXT: adds r0, #16
; CHECK-NEXT: subs r2, #4
; CHECK-NEXT: vadd.i32 q0, q0, q1
; CHECK-NEXT: le lr, .LBB1_1
; CHECK-NEXT: @ %bb.2: @ %middle.block
; CHECK-NEXT: vctp.32 r1
; CHECK-NEXT: vpsel q0, q0, q1
; CHECK-NEXT: vaddv.u32 r0, q0
; CHECK-NEXT: pop {r7, pc}
entry:
%cmp6 = icmp eq i32 %N, 0
br i1 %cmp6, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%n.rnd.up = add i32 %N, 3
%n.vec = and i32 %n.rnd.up, -4
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert9 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat10 = shufflevector <4 x i32> %broadcast.splatinsert9, <4 x i32> undef, <4 x i32> zeroinitializer
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %3, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%0 = getelementptr inbounds i32, i32* %a, i32 %index
%1 = icmp ule <4 x i32> %induction, %broadcast.splat10
%2 = bitcast i32* %0 to <4 x i32>*
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %2, i32 4, <4 x i1> %1, <4 x i32> undef)
%3 = add nsw <4 x i32> %wide.masked.load, %vec.phi
%index.next = add i32 %index, 4
%4 = icmp eq i32 %index.next, %n.vec
br i1 %4, label %middle.block, label %vector.body
middle.block: ; preds = %vector.body
%5 = select <4 x i1> %1, <4 x i32> %3, <4 x i32> %vec.phi
%6 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %5)
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %middle.block, %entry
%res.0.lcssa = phi i32 [ 0, %entry ], [ %6, %middle.block ]
ret i32 %res.0.lcssa
}
define dso_local i32 @add_reduce_add_const(i32* noalias nocapture readonly %a, i32 %b, i32 %N) {
; CHECK-LABEL: add_reduce_add_const:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: cmp r2, #0
; CHECK-NEXT: itt eq
; CHECK-NEXT: moveq r0, #0
; CHECK-NEXT: bxeq lr
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: adds r1, r2, #3
; CHECK-NEXT: movs r3, #1
; CHECK-NEXT: bic r1, r1, #3
; CHECK-NEXT: vmov.i32 q0, #0x0
; CHECK-NEXT: subs r1, #4
; CHECK-NEXT: add.w lr, r3, r1, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB2_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: mov r1, r2
; CHECK-NEXT: vctp.32 r2
; CHECK-NEXT: vmov q1, q0
; CHECK-NEXT: vpst
; CHECK-NEXT: vldrwt.u32 q0, [r0]
; CHECK-NEXT: adds r0, #16
; CHECK-NEXT: subs r2, #4
; CHECK-NEXT: vadd.i32 q0, q0, q1
; CHECK-NEXT: le lr, .LBB2_1
; CHECK-NEXT: @ %bb.2: @ %middle.block
; CHECK-NEXT: vctp.32 r1
; CHECK-NEXT: vpsel q0, q0, q1
; CHECK-NEXT: vaddv.u32 r0, q0
; CHECK-NEXT: pop {r7, pc}
entry:
%cmp6 = icmp eq i32 %N, 0
br i1 %cmp6, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%n.rnd.up = add i32 %N, 3
%n.vec = and i32 %n.rnd.up, -4
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert9 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat10 = shufflevector <4 x i32> %broadcast.splatinsert9, <4 x i32> undef, <4 x i32> zeroinitializer
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %3, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%0 = getelementptr inbounds i32, i32* %a, i32 %index
%1 = icmp ule <4 x i32> %induction, %broadcast.splat10
%2 = bitcast i32* %0 to <4 x i32>*
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %2, i32 4, <4 x i1> %1, <4 x i32> undef)
%3 = add nsw <4 x i32> %wide.masked.load, %vec.phi
%index.next = add i32 %index, 4
%4 = icmp eq i32 %index.next, %n.vec
br i1 %4, label %middle.block, label %vector.body
middle.block: ; preds = %vector.body
%5 = select <4 x i1> %1, <4 x i32> %3, <4 x i32> %vec.phi
%6 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %5)
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %middle.block, %entry
%res.0.lcssa = phi i32 [ 0, %entry ], [ %6, %middle.block ]
ret i32 %res.0.lcssa
}
define dso_local void @vector_mul_const(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32 %c, i32 %N) {
; CHECK-LABEL: vector_mul_const:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: cmp r3, #0
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r7, pc}
; CHECK-NEXT: add.w r12, r3, #3
; CHECK-NEXT: mov.w lr, #1
; CHECK-NEXT: bic r12, r12, #3
; CHECK-NEXT: sub.w r12, r12, #4
; CHECK-NEXT: add.w lr, lr, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB3_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r3
; CHECK-NEXT: vpst
; CHECK-NEXT: vldrwt.u32 q0, [r1]
; CHECK-NEXT: vmul.i32 q0, q0, r2
; CHECK-NEXT: vpst
; CHECK-NEXT: vstrwt.32 q0, [r0]
; CHECK-NEXT: adds r1, #16
; CHECK-NEXT: adds r0, #16
; CHECK-NEXT: subs r3, #4
; CHECK-NEXT: le lr, .LBB3_1
; CHECK-NEXT: @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT: pop {r7, pc}
entry:
%cmp6 = icmp eq i32 %N, 0
br i1 %cmp6, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%n.rnd.up = add i32 %N, 3
%n.vec = and i32 %n.rnd.up, -4
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert8 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat9 = shufflevector <4 x i32> %broadcast.splatinsert8, <4 x i32> undef, <4 x i32> zeroinitializer
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %c, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%0 = getelementptr inbounds i32, i32* %b, i32 %index
%1 = icmp ule <4 x i32> %induction, %broadcast.splat9
%2 = bitcast i32* %0 to <4 x i32>*
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %2, i32 4, <4 x i1> %1, <4 x i32> undef)
%3 = mul nsw <4 x i32> %wide.masked.load, %broadcast.splat11
%4 = getelementptr inbounds i32, i32* %a, i32 %index
%5 = bitcast i32* %4 to <4 x i32>*
call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %3, <4 x i32>* %5, i32 4, <4 x i1> %1)
%index.next = add i32 %index, 4
%6 = icmp eq i32 %index.next, %n.vec
br i1 %6, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
define dso_local void @vector_add_const(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32 %c, i32 %N) {
; CHECK-LABEL: vector_add_const:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: push {r7, lr}
; CHECK-NEXT: cmp r3, #0
; CHECK-NEXT: it eq
; CHECK-NEXT: popeq {r7, pc}
; CHECK-NEXT: add.w r12, r3, #3
; CHECK-NEXT: mov.w lr, #1
; CHECK-NEXT: bic r12, r12, #3
; CHECK-NEXT: sub.w r12, r12, #4
; CHECK-NEXT: add.w lr, lr, r12, lsr #2
; CHECK-NEXT: dls lr, lr
; CHECK-NEXT: .LBB4_1: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vctp.32 r3
; CHECK-NEXT: vpst
; CHECK-NEXT: vldrwt.u32 q0, [r1]
; CHECK-NEXT: vadd.i32 q0, q0, r2
; CHECK-NEXT: vpst
; CHECK-NEXT: vstrwt.32 q0, [r0]
; CHECK-NEXT: adds r1, #16
; CHECK-NEXT: adds r0, #16
; CHECK-NEXT: subs r3, #4
; CHECK-NEXT: le lr, .LBB4_1
; CHECK-NEXT: @ %bb.2: @ %for.cond.cleanup
; CHECK-NEXT: pop {r7, pc}
entry:
%cmp6 = icmp eq i32 %N, 0
br i1 %cmp6, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%n.rnd.up = add i32 %N, 3
%n.vec = and i32 %n.rnd.up, -4
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert8 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat9 = shufflevector <4 x i32> %broadcast.splatinsert8, <4 x i32> undef, <4 x i32> zeroinitializer
%broadcast.splatinsert10 = insertelement <4 x i32> undef, i32 %c, i32 0
%broadcast.splat11 = shufflevector <4 x i32> %broadcast.splatinsert10, <4 x i32> undef, <4 x i32> zeroinitializer
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%0 = getelementptr inbounds i32, i32* %b, i32 %index
%1 = icmp ule <4 x i32> %induction, %broadcast.splat9
%2 = bitcast i32* %0 to <4 x i32>*
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %2, i32 4, <4 x i1> %1, <4 x i32> undef)
%3 = add nsw <4 x i32> %wide.masked.load, %broadcast.splat11
%4 = getelementptr inbounds i32, i32* %a, i32 %index
%5 = bitcast i32* %4 to <4 x i32>*
call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %3, <4 x i32>* %5, i32 4, <4 x i1> %1)
%index.next = add i32 %index, 4
%6 = icmp eq i32 %index.next, %n.vec
br i1 %6, label %for.cond.cleanup, label %vector.body
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>) #4
declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>)
|