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
|
; RUN: opt -passes=loop-vectorize -scalable-vectorization=on -force-vector-width=4 -force-vector-interleave=1 -force-target-supports-scalable-vectors=true -S < %s | FileCheck %s --check-prefix=CHECK-VF4UF1
; RUN: opt -passes=loop-vectorize -scalable-vectorization=on -force-vector-width=4 -force-vector-interleave=2 -force-target-supports-scalable-vectors=true -S < %s | FileCheck %s --check-prefix=CHECK-VF4UF2
; void recurrence_1(int *a, int *b, int n) {
; for(int i = 0; i < n; i++)
; b[i] = a[i] + a[i - 1]
; }
;
define i32 @recurrence_1(ptr nocapture readonly %a, ptr nocapture %b, i32 %n) {
; CHECK-VF4UF1-LABEL: @recurrence_1
; CHECK-VF4UF1: for.preheader
; CHECK-VF4UF1: %[[SUB_1:.*]] = add i32 %n, -1
; CHECK-VF4UF1: %[[ZEXT:.*]] = zext i32 %[[SUB_1]] to i64
; CHECK-VF4UF1: %[[ADD:.*]] = add nuw nsw i64 %[[ZEXT]], 1
; CHECK-VF4UF1: vector.ph:
; CHECK-VF4UF1: %[[VSCALE1:.*]] = call i32 @llvm.vscale.i32()
; CHECK-VF4UF1: %[[MUL1:.*]] = mul i32 %[[VSCALE1]], 4
; CHECK-VF4UF1: %[[SUB1:.*]] = sub i32 %[[MUL1]], 1
; CHECK-VF4UF1: %[[VEC_RECUR_INIT:.*]] = insertelement <vscale x 4 x i32> poison, i32 %pre_load, i32 %[[SUB1]]
; CHECK-VF4UF1: vector.body:
; CHECK-VF4UF1: %[[INDEX:.*]] = phi i64 [ 0, %vector.ph ], [ %[[NEXT_IDX:.*]], %vector.body ]
; CHECK-VF4UF1: %[[VEC_RECUR:.*]] = phi <vscale x 4 x i32> [ %[[VEC_RECUR_INIT]], %vector.ph ], [ %[[LOAD:.*]], %vector.body ]
; CHECK-VF4UF1: %[[LOAD]] = load <vscale x 4 x i32>, ptr
; CHECK-VF4UF1: %[[SPLICE:.*]] = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> %[[VEC_RECUR]], <vscale x 4 x i32> %[[LOAD]], i32 -1)
; CHECK-VF4UF1: middle.block:
; CHECK-VF4UF1: %[[VSCALE3:.*]] = call i32 @llvm.vscale.i32()
; CHECK-VF4UF1: %[[MUL3:.*]] = mul i32 %[[VSCALE3]], 4
; CHECK-VF4UF1: %[[SUB3:.*]] = sub i32 %[[MUL3]], 1
; CHECK-VF4UF1: %[[VEC_RECUR_EXT:.*]] = extractelement <vscale x 4 x i32> %[[LOAD]], i32 %[[SUB3]]
; CHECK-VF4UF1: %[[VSCALE2:.*]] = call i32 @llvm.vscale.i32()
; CHECK-VF4UF1: %[[MUL2:.*]] = mul i32 %[[VSCALE2]], 4
; CHECK-VF4UF1: %[[SUB3:.*]] = sub i32 %[[MUL2]], 2
; CHECK-VF4UF1: %[[VEC_RECUR_FOR_PHI:.*]] = extractelement <vscale x 4 x i32> %[[LOAD]], i32 %[[SUB3]]
entry:
br label %for.preheader
for.preheader:
%pre_load = load i32, ptr %a
br label %scalar.body
scalar.body:
%0 = phi i32 [ %pre_load, %for.preheader ], [ %1, %scalar.body ]
%indvars.iv = phi i64 [ 0, %for.preheader ], [ %indvars.iv.next, %scalar.body ]
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%arrayidx32 = getelementptr inbounds i32, ptr %a, i64 %indvars.iv.next
%1 = load i32, ptr %arrayidx32
%arrayidx34 = getelementptr inbounds i32, ptr %b, i64 %indvars.iv
%add35 = add i32 %1, %0
store i32 %add35, ptr %arrayidx34
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.exit, label %scalar.body, !llvm.loop !0
for.exit:
ret i32 %0
}
; int recurrence_2(int *a, int n) {
; int minmax;
; for (int i = 0; i < n; ++i)
; minmax = min(minmax, max(a[i] - a[i-1], 0));
; return minmax;
; }
;
define i32 @recurrence_2(ptr nocapture readonly %a, i32 %n) {
; CHECK-VF4UF1-LABEL: @recurrence_2
; CHECK-VF4UF1: vector.ph:
; CHECK-VF4UF1: %[[VSCALE1:.*]] = call i32 @llvm.vscale.i32()
; CHECK-VF4UF1: %[[MUL1:.*]] = mul i32 %[[VSCALE1]], 4
; CHECK-VF4UF1: %[[SUB1:.*]] = sub i32 %[[MUL1]], 1
; CHECK-VF4UF1: %[[VEC_RECUR_INIT:.*]] = insertelement <vscale x 4 x i32> poison, i32 %.pre, i32 %[[SUB1]]
; CHECK-VF4UF1: vector.body:
; CHECK-VF4UF1: %[[VEC_RECUR:.*]] = phi <vscale x 4 x i32> [ %[[VEC_RECUR_INIT]], %vector.ph ], [ %[[LOAD:.*]], %vector.body ]
; CHECK-VF4UF1: %[[LOAD]] = load <vscale x 4 x i32>, ptr
; CHECK-VF4UF1: %[[REVERSE:.*]] = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> %[[VEC_RECUR]], <vscale x 4 x i32> %[[LOAD]], i32 -1)
; CHECK-VF4UF1: middle.block:
; CHECK-VF4UF1: %[[VSCALE2:.*]] = call i32 @llvm.vscale.i32()
; CHECK-VF4UF1: %[[MUL2:.*]] = mul i32 %[[VSCALE2]], 4
; CHECK-VF4UF1: %[[SUB2:.*]] = sub i32 %[[MUL2]], 1
; CHECK-VF4UF1: %[[VEC_RECUR_EXT:.*]] = extractelement <vscale x 4 x i32> %[[LOAD]], i32 %[[SUB2]]
entry:
%cmp27 = icmp sgt i32 %n, 0
br i1 %cmp27, label %for.preheader, label %for.cond.cleanup
for.preheader:
%arrayidx2.phi.trans.insert = getelementptr inbounds i32, ptr %a, i64 -1
%.pre = load i32, ptr %arrayidx2.phi.trans.insert, align 4
br label %scalar.body
for.cond.cleanup.loopexit:
%minmax.0.cond.lcssa = phi i32 [ %minmax.0.cond, %scalar.body ]
br label %for.cond.cleanup
for.cond.cleanup:
%minmax.0.lcssa = phi i32 [ undef, %entry ], [ %minmax.0.cond.lcssa, %for.cond.cleanup.loopexit ]
ret i32 %minmax.0.lcssa
scalar.body:
%0 = phi i32 [ %.pre, %for.preheader ], [ %1, %scalar.body ]
%indvars.iv = phi i64 [ 0, %for.preheader ], [ %indvars.iv.next, %scalar.body ]
%minmax.028 = phi i32 [ undef, %for.preheader ], [ %minmax.0.cond, %scalar.body ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
%1 = load i32, ptr %arrayidx, align 4
%sub3 = sub nsw i32 %1, %0
%cmp4 = icmp sgt i32 %sub3, 0
%cond = select i1 %cmp4, i32 %sub3, i32 0
%cmp5 = icmp slt i32 %minmax.028, %cond
%minmax.0.cond = select i1 %cmp5, i32 %minmax.028, i32 %cond
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %scalar.body, !llvm.loop !0
}
define void @recurrence_3(ptr nocapture readonly %a, ptr nocapture %b, i32 %n, float %f, i16 %p) {
; CHECK-VF4UF1: vector.ph:
; CHECK-VF4UF1: %[[VSCALE1:.*]] = call i32 @llvm.vscale.i32()
; CHECK-VF4UF1: %[[MUL1:.*]] = mul i32 %[[VSCALE1]], 4
; CHECK-VF4UF1: %[[SUB1:.*]] = sub i32 %[[MUL1]], 1
; CHECK-VF4UF1: %vector.recur.init = insertelement <vscale x 4 x i16> poison, i16 %0, i32 %[[SUB1]]
; CHECK-VF4UF1: vector.body:
; CHECK-VF4UF1: %vector.recur = phi <vscale x 4 x i16> [ %vector.recur.init, %vector.ph ], [ %[[L1:.*]], %vector.body ]
; CHECK-VF4UF1: %[[L1]] = load <vscale x 4 x i16>, ptr
; CHECK-VF4UF1: %[[SPLICE:.*]] = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> %vector.recur, <vscale x 4 x i16> %[[L1]], i32 -1)
; Check also that the casts were not moved needlessly.
; CHECK-VF4UF1: sitofp <vscale x 4 x i16> %[[L1]] to <vscale x 4 x double>
; CHECK-VF4UF1: sitofp <vscale x 4 x i16> %[[SPLICE]] to <vscale x 4 x double>
; CHECK-VF4UF1: middle.block:
; CHECK-VF4UF1: %[[VSCALE2:.*]] = call i32 @llvm.vscale.i32()
; CHECK-VF4UF1: %[[MUL2:.*]] = mul i32 %[[VSCALE2]], 4
; CHECK-VF4UF1: %[[SUB2:.*]] = sub i32 %[[MUL2]], 1
; CHECK-VF4UF1: %vector.recur.extract = extractelement <vscale x 4 x i16> %[[L1]], i32 %[[SUB2]]
entry:
%0 = load i16, ptr %a, align 2
%conv = sitofp i16 %0 to double
%conv1 = fpext float %f to double
%conv2 = sitofp i16 %p to double
%mul = fmul fast double %conv2, %conv1
%sub = fsub fast double %conv, %mul
store double %sub, ptr %b, align 8
%cmp25 = icmp sgt i32 %n, 1
br i1 %cmp25, label %for.preheader, label %for.end
for.preheader:
br label %scalar.body
scalar.body:
%1 = phi i16 [ %0, %for.preheader ], [ %2, %scalar.body ]
%iv = phi i64 [ %iv.next, %scalar.body ], [ 1, %for.preheader ]
%arrayidx5 = getelementptr inbounds i16, ptr %a, i64 %iv
%2 = load i16, ptr %arrayidx5, align 2
%conv6 = sitofp i16 %2 to double
%conv11 = sitofp i16 %1 to double
%mul12 = fmul fast double %conv11, %conv1
%sub13 = fsub fast double %conv6, %mul12
%arrayidx15 = getelementptr inbounds double, ptr %b, i64 %iv
store double %sub13, ptr %arrayidx15, align 8
%iv.next = add nuw nsw i64 %iv, 1
%lftr.wideiv = trunc i64 %iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end.loopexit, label %scalar.body, !llvm.loop !0
for.end.loopexit:
br label %for.end
for.end:
ret void
}
define i64 @constant_folded_previous_value() {
; CHECK-VF4UF2-LABEL: @constant_folded_previous_value
; CHECK-VF4UF2: vector.body
; CHECK-VF4UF2: %[[VECTOR_RECUR:.*]] = phi <vscale x 4 x i64> [ %vector.recur.init, %vector.ph ], [ shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer), %vector.body ]
; CHECK-VF4UF2: br i1 {{.*}}, label %middle.block, label %vector.body
entry:
br label %scalar.body
scalar.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %scalar.body ]
%tmp2 = phi i64 [ 0, %entry ], [ %tmp3, %scalar.body ]
%tmp3 = add i64 0, 1
%i.next = add nuw nsw i64 %i, 1
%cond = icmp eq i64 %i.next, undef
br i1 %cond, label %for.end, label %scalar.body, !llvm.loop !0
for.end:
ret i64 %tmp2
}
; We vectorize this first order recurrence, by generating two
; extracts for the phi `val.phi` - one at the last index and
; another at the second last index. We need these 2 extracts because
; the first order recurrence phi is used outside the loop, so we require the phi
; itself and not its update (addx).
define i32 @extract_second_last_iteration(ptr %cval, i32 %x) {
; CHECK-VF4UF2-LABEL: @extract_second_last_iteration
; CHECK-VF4UF2: vector.ph
; CHECK-VF4UF2: call i32 @llvm.vscale.i32()
; CHECK-VF4UF2: call i32 @llvm.vscale.i32()
; CHECK-VF4UF2: call i32 @llvm.vscale.i32()
; CHECK-VF4UF2: %[[VSCALE1:.*]] = call i32 @llvm.vscale.i32()
; CHECK-VF4UF2: %[[MUL1:.*]] = mul i32 %[[VSCALE1]], 4
; CHECK-VF4UF2: %[[SUB1:.*]] = sub i32 %[[MUL1]], 1
; CHECK-VF4UF2: %[[VEC_RECUR_INIT:.*]] = insertelement <vscale x 4 x i32> poison, i32 0, i32 %[[SUB1]]
; CHECK-VF4UF2: %[[SPLAT_INS1:.*]] = insertelement <vscale x 4 x i32> poison, i32 %x, i64 0
; CHECK-VF4UF2: %[[SPLAT1:.*]] = shufflevector <vscale x 4 x i32> %[[SPLAT_INS1]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
; ; CHECK-VF4UF2: vector.body
; CHECK-VF4UF2: %[[VEC_RECUR:.*]] = phi <vscale x 4 x i32> [ %[[VEC_RECUR_INIT]], %vector.ph ], [ %[[ADD2:.*]], %vector.body ]
; CHECK-VF4UF2: %[[ADD1:.*]] = add <vscale x 4 x i32> %{{.*}}, %[[SPLAT1]]
; CHECK-VF4UF2: %[[ADD2]] = add <vscale x 4 x i32> %{{.*}}, %[[SPLAT1]]
; CHECK-VF4UF2: middle.block
; CHECK-VF4UF2: %[[VSCALE3:.*]] = call i32 @llvm.vscale.i32()
; CHECK-VF4UF2: %[[MUL3:.*]] = mul i32 %[[VSCALE3]], 4
; CHECK-VF4UF2: %[[SUB2:.*]] = sub i32 %[[MUL3]], 1
; CHECK-VF4UF2: %vector.recur.extract = extractelement <vscale x 4 x i32> %[[ADD2]], i32 %[[SUB2]]
; CHECK-VF4UF2: %[[VSCALE2:.*]] = call i32 @llvm.vscale.i32()
; CHECK-VF4UF2: %[[MUL2:.*]] = mul i32 %[[VSCALE2]], 4
; CHECK-VF4UF2: %[[SUB3:.*]] = sub i32 %[[MUL2]], 2
; CHECK-VF4UF2: %vector.recur.extract.for.phi = extractelement <vscale x 4 x i32> %[[ADD2]], i32 %[[SUB3]]
entry:
br label %for.body
for.body:
%inc.phi = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%val.phi = phi i32 [ 0, %entry ], [ %addx, %for.body ]
%inc = add i32 %inc.phi, 1
%bc = zext i32 %inc.phi to i64
%addx = add i32 %inc.phi, %x
%cmp = icmp eq i32 %inc.phi, 95
br i1 %cmp, label %for.end, label %for.body, !llvm.loop !0
for.end:
ret i32 %val.phi
}
; void sink_after(short *a, int n, int *b) {
; for(int i = 0; i < n; i++)
; b[i] = (aptr a[i + 1]);
; }
; Check that the sext sank after the load in the vector loop.
define void @sink_after(ptr %a, ptr %b, i64 %n) {
; CHECK-VF4UF1-LABEL: @sink_after
; CHECK-VF4UF1: vector.body
; CHECK-VF4UF1: %[[VEC_RECUR:.*]] = phi <vscale x 4 x i16> [ %vector.recur.init, %vector.ph ], [ %[[LOAD:.*]], %vector.body ]
; CHECK-VF4UF1: %[[LOAD]] = load <vscale x 4 x i16>, ptr
; CHECK-VF4UF1-NEXT: %[[SPLICE:.*]] = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> %[[VEC_RECUR]], <vscale x 4 x i16> %[[LOAD]], i32 -1)
; CHECK-VF4UF1-NEXT: sext <vscale x 4 x i16> %[[SPLICE]] to <vscale x 4 x i32>
; CHECK-VF4UF1-NEXT: sext <vscale x 4 x i16> %[[LOAD]] to <vscale x 4 x i32>
entry:
%.pre = load i16, ptr %a
br label %for.body
for.body:
%0 = phi i16 [ %.pre, %entry ], [ %1, %for.body ]
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%conv = sext i16 %0 to i32
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%arrayidx2 = getelementptr inbounds i16, ptr %a, i64 %indvars.iv.next
%1 = load i16, ptr %arrayidx2
%conv3 = sext i16 %1 to i32
%mul = mul nsw i32 %conv3, %conv
%arrayidx5 = getelementptr inbounds i32, ptr %b, i64 %indvars.iv
store i32 %mul, ptr %arrayidx5
%exitcond = icmp eq i64 %indvars.iv.next, %n
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
for.end:
ret void
}
!0 = distinct !{!0, !1}
!1 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
|
