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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-vectorize -mcpu=corei7-avx -S -vectorizer-min-trip-count=21 | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux"
;
; The source code for the test:
;
; void foo(ptr restrict A, ptr restrict B)
; {
; for (int i = 0; i < 20; ++i) A[i] += B[i];
; }
;
;
; This loop will be vectorized, although the trip count is below the threshold, but
; vectorization is explicitly forced in metadata. The trip count of 4 is chosen as
; it more nicely divides the loop count of 20, produce a lower total cost.
;
define void @vectorized(ptr noalias nocapture %A, ptr noalias nocapture readonly %B) {
; CHECK-LABEL: @vectorized(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP3:%.*]] = add i64 [[INDEX]], 12
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds float, ptr [[B:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP2]]
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[TMP3]]
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds float, ptr [[TMP4]], i32 0
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds float, ptr [[TMP4]], i32 4
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds float, ptr [[TMP4]], i32 8
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds float, ptr [[TMP4]], i32 12
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP8]], align 4, !llvm.access.group [[ACC_GRP0:![0-9]+]]
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x float>, ptr [[TMP9]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <4 x float>, ptr [[TMP10]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[WIDE_LOAD3:%.*]] = load <4 x float>, ptr [[TMP11]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds float, ptr [[A:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP2]]
; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[TMP3]]
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds float, ptr [[TMP12]], i32 0
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds float, ptr [[TMP12]], i32 4
; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds float, ptr [[TMP12]], i32 8
; CHECK-NEXT: [[TMP19:%.*]] = getelementptr inbounds float, ptr [[TMP12]], i32 12
; CHECK-NEXT: [[WIDE_LOAD4:%.*]] = load <4 x float>, ptr [[TMP16]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[WIDE_LOAD5:%.*]] = load <4 x float>, ptr [[TMP17]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[WIDE_LOAD6:%.*]] = load <4 x float>, ptr [[TMP18]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[WIDE_LOAD7:%.*]] = load <4 x float>, ptr [[TMP19]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[TMP20:%.*]] = fadd fast <4 x float> [[WIDE_LOAD]], [[WIDE_LOAD4]]
; CHECK-NEXT: [[TMP21:%.*]] = fadd fast <4 x float> [[WIDE_LOAD1]], [[WIDE_LOAD5]]
; CHECK-NEXT: [[TMP22:%.*]] = fadd fast <4 x float> [[WIDE_LOAD2]], [[WIDE_LOAD6]]
; CHECK-NEXT: [[TMP23:%.*]] = fadd fast <4 x float> [[WIDE_LOAD3]], [[WIDE_LOAD7]]
; CHECK-NEXT: store <4 x float> [[TMP20]], ptr [[TMP16]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: store <4 x float> [[TMP21]], ptr [[TMP17]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: store <4 x float> [[TMP22]], ptr [[TMP18]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: store <4 x float> [[TMP23]], ptr [[TMP19]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-NEXT: [[TMP24:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
; CHECK-NEXT: br i1 [[TMP24]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP1:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 false, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP25:%.*]] = load float, ptr [[ARRAYIDX]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP26:%.*]] = load float, ptr [[ARRAYIDX2]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[ADD:%.*]] = fadd fast float [[TMP25]], [[TMP26]]
; CHECK-NEXT: store float [[ADD]], ptr [[ARRAYIDX2]], align 4, !llvm.access.group [[ACC_GRP0]]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 20
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds float, ptr %B, i64 %indvars.iv
%0 = load float, ptr %arrayidx, align 4, !llvm.access.group !11
%arrayidx2 = getelementptr inbounds float, ptr %A, i64 %indvars.iv
%1 = load float, ptr %arrayidx2, align 4, !llvm.access.group !11
%add = fadd fast float %0, %1
store float %add, ptr %arrayidx2, align 4, !llvm.access.group !11
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 20
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !1
for.end:
ret void
}
!1 = !{!1, !2, !{!"llvm.loop.parallel_accesses", !11}}
!2 = !{!"llvm.loop.vectorize.enable", i1 true}
!11 = distinct !{}
;
; This loop will be vectorized as the trip count is below the threshold but no
; scalar iterations are needed thanks to folding its tail.
;
define void @vectorized1(ptr noalias nocapture %A, ptr noalias nocapture readonly %B) {
; CHECK-LABEL: @vectorized1(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <8 x i64> poison, i64 [[INDEX]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <8 x i64> [[BROADCAST_SPLATINSERT]], <8 x i64> poison, <8 x i32> zeroinitializer
; CHECK-NEXT: [[VEC_IV:%.*]] = add <8 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>
; CHECK-NEXT: [[TMP1:%.*]] = icmp ule <8 x i64> [[VEC_IV]], <i64 19, i64 19, i64 19, i64 19, i64 19, i64 19, i64 19, i64 19>
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, ptr [[B:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds float, ptr [[TMP2]], i32 0
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0(ptr [[TMP3]], i32 4, <8 x i1> [[TMP1]], <8 x float> poison), !llvm.access.group [[ACC_GRP6:![0-9]+]]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds float, ptr [[A:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds float, ptr [[TMP4]], i32 0
; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <8 x float> @llvm.masked.load.v8f32.p0(ptr [[TMP5]], i32 4, <8 x i1> [[TMP1]], <8 x float> poison), !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[TMP6:%.*]] = fadd fast <8 x float> [[WIDE_MASKED_LOAD]], [[WIDE_MASKED_LOAD1]]
; CHECK-NEXT: call void @llvm.masked.store.v8f32.p0(<8 x float> [[TMP6]], ptr [[TMP5]], i32 4, <8 x i1> [[TMP1]]), !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 24
; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 24, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP8:%.*]] = load float, ptr [[ARRAYIDX]], align 4, !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP9:%.*]] = load float, ptr [[ARRAYIDX2]], align 4, !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[ADD:%.*]] = fadd fast float [[TMP8]], [[TMP9]]
; CHECK-NEXT: store float [[ADD]], ptr [[ARRAYIDX2]], align 4, !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 20
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds float, ptr %B, i64 %indvars.iv
%0 = load float, ptr %arrayidx, align 4, !llvm.access.group !13
%arrayidx2 = getelementptr inbounds float, ptr %A, i64 %indvars.iv
%1 = load float, ptr %arrayidx2, align 4, !llvm.access.group !13
%add = fadd fast float %0, %1
store float %add, ptr %arrayidx2, align 4, !llvm.access.group !13
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 20
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !3
for.end:
ret void
}
!3 = !{!3, !{!"llvm.loop.parallel_accesses", !13}}
!13 = distinct !{}
;
; This loop will be vectorized as the trip count is below the threshold but no
; scalar iterations are needed.
;
define void @vectorized2(ptr noalias nocapture %A, ptr noalias nocapture readonly %B) {
; CHECK-LABEL: @vectorized2(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds float, ptr [[B:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds float, ptr [[TMP1]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x float>, ptr [[TMP2]], align 4, !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds float, ptr [[A:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds float, ptr [[TMP3]], i32 0
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <8 x float>, ptr [[TMP4]], align 4, !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[TMP5:%.*]] = fadd fast <8 x float> [[WIDE_LOAD]], [[WIDE_LOAD1]]
; CHECK-NEXT: store <8 x float> [[TMP5]], ptr [[TMP4]], align 4, !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
; CHECK-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[B]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP7:%.*]] = load float, ptr [[ARRAYIDX]], align 4, !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds float, ptr [[A]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP8:%.*]] = load float, ptr [[ARRAYIDX2]], align 4, !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[ADD:%.*]] = fadd fast float [[TMP7]], [[TMP8]]
; CHECK-NEXT: store float [[ADD]], ptr [[ARRAYIDX2]], align 4, !llvm.access.group [[ACC_GRP6]]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 16
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds float, ptr %B, i64 %indvars.iv
%0 = load float, ptr %arrayidx, align 4, !llvm.access.group !13
%arrayidx2 = getelementptr inbounds float, ptr %A, i64 %indvars.iv
%1 = load float, ptr %arrayidx2, align 4, !llvm.access.group !13
%add = fadd fast float %0, %1
store float %add, ptr %arrayidx2, align 4, !llvm.access.group !13
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 16
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !4
for.end:
ret void
}
!4 = !{!4}
|
