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
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs
// RUN: %clang_cc1 -no-opaque-pointers -fopenmp-enable-irbuilder -verify -fopenmp -fopenmp-version=51 -x c -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
// CHECK-LABEL: define {{.*}}@unroll_unroll_partial_heuristic(
// CHECK-NEXT: [[ENTRY:.*]]:
// CHECK-NEXT: %[[A_ADDR:.+]] = alloca float*, align 8
// CHECK-NEXT: %[[B_ADDR:.+]] = alloca float*, align 8
// CHECK-NEXT: %[[C_ADDR:.+]] = alloca float*, align 8
// CHECK-NEXT: %[[D_ADDR:.+]] = alloca float*, align 8
// CHECK-NEXT: %[[I:.+]] = alloca i32, align 4
// CHECK-NEXT: %[[AGG_CAPTURED:.+]] = alloca %struct.anon, align 8
// CHECK-NEXT: %[[AGG_CAPTURED1:.+]] = alloca %struct.anon.0, align 4
// CHECK-NEXT: %[[DOTCOUNT_ADDR:.+]] = alloca i32, align 4
// CHECK-NEXT: store float* %[[A:.+]], float** %[[A_ADDR]], align 8
// CHECK-NEXT: store float* %[[B:.+]], float** %[[B_ADDR]], align 8
// CHECK-NEXT: store float* %[[C:.+]], float** %[[C_ADDR]], align 8
// CHECK-NEXT: store float* %[[D:.+]], float** %[[D_ADDR]], align 8
// CHECK-NEXT: store i32 0, i32* %[[I]], align 4
// CHECK-NEXT: %[[TMP0:.+]] = getelementptr inbounds %struct.anon, %struct.anon* %[[AGG_CAPTURED]], i32 0, i32 0
// CHECK-NEXT: store i32* %[[I]], i32** %[[TMP0]], align 8
// CHECK-NEXT: %[[TMP1:.+]] = getelementptr inbounds %struct.anon.0, %struct.anon.0* %[[AGG_CAPTURED1]], i32 0, i32 0
// CHECK-NEXT: %[[TMP2:.+]] = load i32, i32* %[[I]], align 4
// CHECK-NEXT: store i32 %[[TMP2]], i32* %[[TMP1]], align 4
// CHECK-NEXT: call void @__captured_stmt(i32* %[[DOTCOUNT_ADDR]], %struct.anon* %[[AGG_CAPTURED]])
// CHECK-NEXT: %[[DOTCOUNT:.+]] = load i32, i32* %[[DOTCOUNT_ADDR]], align 4
// CHECK-NEXT: br label %[[OMP_LOOP_PREHEADER:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_LOOP_PREHEADER]]:
// CHECK-NEXT: %[[TMP3:.+]] = udiv i32 %[[DOTCOUNT]], 8
// CHECK-NEXT: %[[TMP4:.+]] = urem i32 %[[DOTCOUNT]], 8
// CHECK-NEXT: %[[TMP5:.+]] = icmp ne i32 %[[TMP4]], 0
// CHECK-NEXT: %[[TMP6:.+]] = zext i1 %[[TMP5]] to i32
// CHECK-NEXT: %[[OMP_FLOOR0_TRIPCOUNT:.+]] = add nuw i32 %[[TMP3]], %[[TMP6]]
// CHECK-NEXT: br label %[[OMP_FLOOR0_PREHEADER:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_FLOOR0_PREHEADER]]:
// CHECK-NEXT: br label %[[OMP_FLOOR0_HEADER:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_FLOOR0_HEADER]]:
// CHECK-NEXT: %[[OMP_FLOOR0_IV:.+]] = phi i32 [ 0, %[[OMP_FLOOR0_PREHEADER]] ], [ %[[OMP_FLOOR0_NEXT:.+]], %[[OMP_FLOOR0_INC:.+]] ]
// CHECK-NEXT: br label %[[OMP_FLOOR0_COND:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_FLOOR0_COND]]:
// CHECK-NEXT: %[[OMP_FLOOR0_CMP:.+]] = icmp ult i32 %[[OMP_FLOOR0_IV]], %[[OMP_FLOOR0_TRIPCOUNT]]
// CHECK-NEXT: br i1 %[[OMP_FLOOR0_CMP]], label %[[OMP_FLOOR0_BODY:.+]], label %[[OMP_FLOOR0_EXIT:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_FLOOR0_BODY]]:
// CHECK-NEXT: %[[TMP7:.+]] = icmp eq i32 %[[OMP_FLOOR0_IV]], %[[OMP_FLOOR0_TRIPCOUNT]]
// CHECK-NEXT: %[[TMP8:.+]] = select i1 %[[TMP7]], i32 %[[TMP4]], i32 8
// CHECK-NEXT: br label %[[OMP_TILE0_PREHEADER:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_TILE0_PREHEADER]]:
// CHECK-NEXT: br label %[[OMP_TILE0_HEADER:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_TILE0_HEADER]]:
// CHECK-NEXT: %[[OMP_TILE0_IV:.+]] = phi i32 [ 0, %[[OMP_TILE0_PREHEADER]] ], [ %[[OMP_TILE0_NEXT:.+]], %[[OMP_TILE0_INC:.+]] ]
// CHECK-NEXT: br label %[[OMP_TILE0_COND:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_TILE0_COND]]:
// CHECK-NEXT: %[[OMP_TILE0_CMP:.+]] = icmp ult i32 %[[OMP_TILE0_IV]], %[[TMP8]]
// CHECK-NEXT: br i1 %[[OMP_TILE0_CMP]], label %[[OMP_TILE0_BODY:.+]], label %[[OMP_TILE0_EXIT:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_TILE0_BODY]]:
// CHECK-NEXT: %[[TMP9:.+]] = mul nuw i32 8, %[[OMP_FLOOR0_IV]]
// CHECK-NEXT: %[[TMP10:.+]] = add nuw i32 %[[TMP9]], %[[OMP_TILE0_IV]]
// CHECK-NEXT: br label %[[OMP_LOOP_BODY:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_LOOP_BODY]]:
// CHECK-NEXT: call void @__captured_stmt.1(i32* %[[I]], i32 %[[TMP10]], %struct.anon.0* %[[AGG_CAPTURED1]])
// CHECK-NEXT: %[[TMP11:.+]] = load float*, float** %[[B_ADDR]], align 8
// CHECK-NEXT: %[[TMP12:.+]] = load i32, i32* %[[I]], align 4
// CHECK-NEXT: %[[IDXPROM:.+]] = sext i32 %[[TMP12]] to i64
// CHECK-NEXT: %[[ARRAYIDX:.+]] = getelementptr inbounds float, float* %[[TMP11]], i64 %[[IDXPROM]]
// CHECK-NEXT: %[[TMP13:.+]] = load float, float* %[[ARRAYIDX]], align 4
// CHECK-NEXT: %[[TMP14:.+]] = load float*, float** %[[C_ADDR]], align 8
// CHECK-NEXT: %[[TMP15:.+]] = load i32, i32* %[[I]], align 4
// CHECK-NEXT: %[[IDXPROM2:.+]] = sext i32 %[[TMP15]] to i64
// CHECK-NEXT: %[[ARRAYIDX3:.+]] = getelementptr inbounds float, float* %[[TMP14]], i64 %[[IDXPROM2]]
// CHECK-NEXT: %[[TMP16:.+]] = load float, float* %[[ARRAYIDX3]], align 4
// CHECK-NEXT: %[[MUL:.+]] = fmul float %[[TMP13]], %[[TMP16]]
// CHECK-NEXT: %[[TMP17:.+]] = load float*, float** %[[D_ADDR]], align 8
// CHECK-NEXT: %[[TMP18:.+]] = load i32, i32* %[[I]], align 4
// CHECK-NEXT: %[[IDXPROM4:.+]] = sext i32 %[[TMP18]] to i64
// CHECK-NEXT: %[[ARRAYIDX5:.+]] = getelementptr inbounds float, float* %[[TMP17]], i64 %[[IDXPROM4]]
// CHECK-NEXT: %[[TMP19:.+]] = load float, float* %[[ARRAYIDX5]], align 4
// CHECK-NEXT: %[[MUL6:.+]] = fmul float %[[MUL]], %[[TMP19]]
// CHECK-NEXT: %[[TMP20:.+]] = load float*, float** %[[A_ADDR]], align 8
// CHECK-NEXT: %[[TMP21:.+]] = load i32, i32* %[[I]], align 4
// CHECK-NEXT: %[[IDXPROM7:.+]] = sext i32 %[[TMP21]] to i64
// CHECK-NEXT: %[[ARRAYIDX8:.+]] = getelementptr inbounds float, float* %[[TMP20]], i64 %[[IDXPROM7]]
// CHECK-NEXT: store float %[[MUL6]], float* %[[ARRAYIDX8]], align 4
// CHECK-NEXT: br label %[[OMP_TILE0_INC]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_TILE0_INC]]:
// CHECK-NEXT: %[[OMP_TILE0_NEXT]] = add nuw i32 %[[OMP_TILE0_IV]], 1
// CHECK-NEXT: br label %[[OMP_TILE0_HEADER]], !llvm.loop ![[LOOP3:[0-9]+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_TILE0_EXIT]]:
// CHECK-NEXT: br label %[[OMP_TILE0_AFTER:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_TILE0_AFTER]]:
// CHECK-NEXT: br label %[[OMP_FLOOR0_INC]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_FLOOR0_INC]]:
// CHECK-NEXT: %[[OMP_FLOOR0_NEXT]] = add nuw i32 %[[OMP_FLOOR0_IV]], 1
// CHECK-NEXT: br label %[[OMP_FLOOR0_HEADER]], !llvm.loop ![[LOOP6:[0-9]+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_FLOOR0_EXIT]]:
// CHECK-NEXT: br label %[[OMP_FLOOR0_AFTER:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_FLOOR0_AFTER]]:
// CHECK-NEXT: br label %[[OMP_LOOP_AFTER:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[OMP_LOOP_AFTER]]:
// CHECK-NEXT: ret void
// CHECK-NEXT: }
void unroll_unroll_partial_heuristic(float *a, float *b, float *c, float *d) {
#pragma omp unroll partial
#pragma omp unroll partial
for (int i = 0; i < 2; i++) {
a[i] = b[i] * c[i] * d[i];
}
}
#endif // HEADER
// CHECK-LABEL: define {{.*}}@__captured_stmt(
// CHECK-NEXT: [[ENTRY:.*]]:
// CHECK-NEXT: %[[DISTANCE_ADDR:.+]] = alloca i32*, align 8
// CHECK-NEXT: %[[__CONTEXT_ADDR:.+]] = alloca %struct.anon*, align 8
// CHECK-NEXT: %[[DOTSTART:.+]] = alloca i32, align 4
// CHECK-NEXT: %[[DOTSTOP:.+]] = alloca i32, align 4
// CHECK-NEXT: %[[DOTSTEP:.+]] = alloca i32, align 4
// CHECK-NEXT: store i32* %[[DISTANCE:.+]], i32** %[[DISTANCE_ADDR]], align 8
// CHECK-NEXT: store %struct.anon* %[[__CONTEXT:.+]], %struct.anon** %[[__CONTEXT_ADDR]], align 8
// CHECK-NEXT: %[[TMP0:.+]] = load %struct.anon*, %struct.anon** %[[__CONTEXT_ADDR]], align 8
// CHECK-NEXT: %[[TMP1:.+]] = getelementptr inbounds %struct.anon, %struct.anon* %[[TMP0]], i32 0, i32 0
// CHECK-NEXT: %[[TMP2:.+]] = load i32*, i32** %[[TMP1]], align 8
// CHECK-NEXT: %[[TMP3:.+]] = load i32, i32* %[[TMP2]], align 4
// CHECK-NEXT: store i32 %[[TMP3]], i32* %[[DOTSTART]], align 4
// CHECK-NEXT: store i32 2, i32* %[[DOTSTOP]], align 4
// CHECK-NEXT: store i32 1, i32* %[[DOTSTEP]], align 4
// CHECK-NEXT: %[[TMP4:.+]] = load i32, i32* %[[DOTSTART]], align 4
// CHECK-NEXT: %[[TMP5:.+]] = load i32, i32* %[[DOTSTOP]], align 4
// CHECK-NEXT: %[[CMP:.+]] = icmp slt i32 %[[TMP4]], %[[TMP5]]
// CHECK-NEXT: br i1 %[[CMP]], label %[[COND_TRUE:.+]], label %[[COND_FALSE:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[COND_TRUE]]:
// CHECK-NEXT: %[[TMP6:.+]] = load i32, i32* %[[DOTSTOP]], align 4
// CHECK-NEXT: %[[TMP7:.+]] = load i32, i32* %[[DOTSTART]], align 4
// CHECK-NEXT: %[[SUB:.+]] = sub nsw i32 %[[TMP6]], %[[TMP7]]
// CHECK-NEXT: %[[TMP8:.+]] = load i32, i32* %[[DOTSTEP]], align 4
// CHECK-NEXT: %[[SUB1:.+]] = sub i32 %[[TMP8]], 1
// CHECK-NEXT: %[[ADD:.+]] = add i32 %[[SUB]], %[[SUB1]]
// CHECK-NEXT: %[[TMP9:.+]] = load i32, i32* %[[DOTSTEP]], align 4
// CHECK-NEXT: %[[DIV:.+]] = udiv i32 %[[ADD]], %[[TMP9]]
// CHECK-NEXT: br label %[[COND_END:.+]]
// CHECK-EMPTY:
// CHECK-NEXT: [[COND_FALSE]]:
// CHECK-NEXT: br label %[[COND_END]]
// CHECK-EMPTY:
// CHECK-NEXT: [[COND_END]]:
// CHECK-NEXT: %[[COND:.+]] = phi i32 [ %[[DIV]], %[[COND_TRUE]] ], [ 0, %[[COND_FALSE]] ]
// CHECK-NEXT: %[[TMP10:.+]] = load i32*, i32** %[[DISTANCE_ADDR]], align 8
// CHECK-NEXT: store i32 %[[COND]], i32* %[[TMP10]], align 4
// CHECK-NEXT: ret void
// CHECK-NEXT: }
// CHECK-LABEL: define {{.*}}@__captured_stmt.1(
// CHECK-NEXT: [[ENTRY:.*]]:
// CHECK-NEXT: %[[LOOPVAR_ADDR:.+]] = alloca i32*, align 8
// CHECK-NEXT: %[[LOGICAL_ADDR:.+]] = alloca i32, align 4
// CHECK-NEXT: %[[__CONTEXT_ADDR:.+]] = alloca %struct.anon.0*, align 8
// CHECK-NEXT: store i32* %[[LOOPVAR:.+]], i32** %[[LOOPVAR_ADDR]], align 8
// CHECK-NEXT: store i32 %[[LOGICAL:.+]], i32* %[[LOGICAL_ADDR]], align 4
// CHECK-NEXT: store %struct.anon.0* %[[__CONTEXT:.+]], %struct.anon.0** %[[__CONTEXT_ADDR]], align 8
// CHECK-NEXT: %[[TMP0:.+]] = load %struct.anon.0*, %struct.anon.0** %[[__CONTEXT_ADDR]], align 8
// CHECK-NEXT: %[[TMP1:.+]] = getelementptr inbounds %struct.anon.0, %struct.anon.0* %[[TMP0]], i32 0, i32 0
// CHECK-NEXT: %[[TMP2:.+]] = load i32, i32* %[[TMP1]], align 4
// CHECK-NEXT: %[[TMP3:.+]] = load i32, i32* %[[LOGICAL_ADDR]], align 4
// CHECK-NEXT: %[[MUL:.+]] = mul i32 1, %[[TMP3]]
// CHECK-NEXT: %[[ADD:.+]] = add i32 %[[TMP2]], %[[MUL]]
// CHECK-NEXT: %[[TMP4:.+]] = load i32*, i32** %[[LOOPVAR_ADDR]], align 8
// CHECK-NEXT: store i32 %[[ADD]], i32* %[[TMP4]], align 4
// CHECK-NEXT: ret void
// CHECK-NEXT: }
// CHECK: ![[META0:[0-9]+]] = !{i32 1, !"wchar_size", i32 4}
// CHECK: ![[META1:[0-9]+]] = !{i32 7, !"openmp", i32 51}
// CHECK: ![[META2:[0-9]+]] =
// CHECK: ![[LOOP3]] = distinct !{![[LOOP3]], ![[LOOPPROP4:[0-9]+]], ![[LOOPPROP5:[0-9]+]]}
// CHECK: ![[LOOPPROP4]] = !{!"llvm.loop.unroll.enable"}
// CHECK: ![[LOOPPROP5]] = !{!"llvm.loop.unroll.count", i32 8}
// CHECK: ![[LOOP6]] = distinct !{![[LOOP6]], ![[LOOPPROP4]]}
|
