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
| // RUN: %clang_cc1 -fopenmp -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86
// RUN: %clang_cc1 -fopenmp -triple x86_64-unknown-unknown -target-feature +avx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX
// RUN: %clang_cc1 -fopenmp -triple x86_64-unknown-unknown -target-feature +avx512f -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX512
// RUN: %clang_cc1 -fopenmp -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86
// RUN: %clang_cc1 -fopenmp -triple i386-unknown-unknown -target-feature +avx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX
// RUN: %clang_cc1 -fopenmp -triple i386-unknown-unknown -target-feature +avx512f -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX512
// RUN: %clang_cc1 -fopenmp -triple powerpc64-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=PPC
// RUN: %clang_cc1 -fopenmp -triple powerpc64-unknown-unknown -target-abi elfv1-qpx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=PPC-QPX
// RUN: %clang_cc1 -fopenmp-simd -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86
// RUN: %clang_cc1 -fopenmp-simd -triple x86_64-unknown-unknown -target-feature +avx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX
// RUN: %clang_cc1 -fopenmp-simd -triple x86_64-unknown-unknown -target-feature +avx512f -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX512
// RUN: %clang_cc1 -fopenmp-simd -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86
// RUN: %clang_cc1 -fopenmp-simd -triple i386-unknown-unknown -target-feature +avx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX
// RUN: %clang_cc1 -fopenmp-simd -triple i386-unknown-unknown -target-feature +avx512f -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=X86-AVX512
// RUN: %clang_cc1 -fopenmp-simd -triple powerpc64-unknown-unknown -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=PPC
// RUN: %clang_cc1 -fopenmp-simd -triple powerpc64-unknown-unknown -target-abi elfv1-qpx -emit-llvm %s -o - | FileCheck %s -check-prefix=CHECK -check-prefix=PPC-QPX
void h1(float *c, float *a, double b[], int size)
{
// CHECK-LABEL: define void @h1
int t = 0;
#pragma omp simd safelen(16) linear(t) aligned(c:32) aligned(a,b)
// CHECK: [[C_PTRINT:%.+]] = ptrtoint
// CHECK-NEXT: [[C_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[C_PTRINT]], 31
// CHECK-NEXT: [[C_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[C_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[C_MASKCOND]])
// CHECK: [[A_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// X86-AVX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 31
// X86-AVX512-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 63
// PPC-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// PPC-QPX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// CHECK-NEXT: [[A_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[A_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[A_MASKCOND]])
// CHECK: [[B_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// X86-AVX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// X86-AVX512-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 63
// PPC-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// PPC-QPX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// CHECK-NEXT: [[B_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[B_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[B_MASKCOND]])
for (int i = 0; i < size; ++i) {
c[i] = a[i] * a[i] + b[i] * b[t];
++t;
}
// do not emit llvm.access.group metadata due to usage of safelen clause.
// CHECK-NOT: store float {{.+}}, float* {{.+}}, align {{.+}}, !llvm.access.group {{![0-9]+}}
#pragma omp simd safelen(16) linear(t) aligned(c:32) aligned(a,b) simdlen(8)
// CHECK: [[C_PTRINT:%.+]] = ptrtoint
// CHECK-NEXT: [[C_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[C_PTRINT]], 31
// CHECK-NEXT: [[C_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[C_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[C_MASKCOND]])
// CHECK: [[A_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// X86-AVX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 31
// X86-AVX512-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 63
// PPC-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// PPC-QPX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// CHECK-NEXT: [[A_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[A_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[A_MASKCOND]])
// CHECK: [[B_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// X86-AVX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// X86-AVX512-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 63
// PPC-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// PPC-QPX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// CHECK-NEXT: [[B_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[B_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[B_MASKCOND]])
for (int i = 0; i < size; ++i) {
c[i] = a[i] * a[i] + b[i] * b[t];
++t;
}
// do not emit llvm.access.group metadata due to usage of safelen clause.
// CHECK-NOT: store float {{.+}}, float* {{.+}}, align {{.+}}, !llvm.access.group {{![0-9]+}}
#pragma omp simd linear(t) aligned(c:32) aligned(a,b) simdlen(8)
// CHECK: [[C_PTRINT:%.+]] = ptrtoint
// CHECK-NEXT: [[C_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[C_PTRINT]], 31
// CHECK-NEXT: [[C_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[C_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[C_MASKCOND]])
// CHECK: [[A_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// X86-AVX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 31
// X86-AVX512-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 63
// PPC-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// PPC-QPX-NEXT: [[A_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[A_PTRINT]], 15
// CHECK-NEXT: [[A_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[A_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[A_MASKCOND]])
// CHECK: [[B_PTRINT:%.+]] = ptrtoint
// X86-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// X86-AVX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// X86-AVX512-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 63
// PPC-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 15
// PPC-QPX-NEXT: [[B_MASKEDPTR:%.+]] = and i{{[0-9]+}} [[B_PTRINT]], 31
// CHECK-NEXT: [[B_MASKCOND:%.+]] = icmp eq i{{[0-9]+}} [[B_MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[B_MASKCOND]])
for (int i = 0; i < size; ++i) {
c[i] = a[i] * a[i] + b[i] * b[t];
++t;
// CHECK: store float {{.+}}, float* {{.+}}, align {{.+}}, !llvm.access.group ![[ACCESS_GROUP_7:[0-9]+]]
}
}
void h2(float *c, float *a, float *b, int size)
{
// CHECK-LABEL: define void @h2
int t = 0;
#pragma omp simd linear(t)
for (int i = 0; i < size; ++i) {
c[i] = a[i] * a[i] + b[i] * b[t];
++t;
// CHECK: store float {{.+}}, float* {{.+}}, align {{.+}}, !llvm.access.group ![[ACCESS_GROUP_10:[0-9]+]]
}
// CHECK: br label %{{.+}}, !llvm.loop [[LOOP_H2_HEADER:![0-9]+]]
}
void h3(float *c, float *a, float *b, int size)
{
// CHECK-LABEL: define void @h3
#pragma omp simd
for (int i = 0; i < size; ++i) {
for (int j = 0; j < size; ++j) {
c[j*i] = a[i] * b[j];
}
// CHECK: store float {{.+}}, float* {{.+}}, align {{.+}}, !llvm.access.group ![[ACCESS_GROUP_13:[0-9]+]]
}
// CHECK: br label %{{.+}}, !llvm.loop [[LOOP_H3_HEADER:![0-9]+]]
}
// Metadata for h1:
// CHECK: [[LOOP_H1_HEADER:![0-9]+]] = distinct !{[[LOOP_H1_HEADER]], [[LOOP_WIDTH_16:![0-9]+]], [[LOOP_VEC_ENABLE:![0-9]+]]}
// CHECK: [[LOOP_WIDTH_16]] = !{!"llvm.loop.vectorize.width", i32 16}
// CHECK: [[LOOP_VEC_ENABLE]] = !{!"llvm.loop.vectorize.enable", i1 true}
// CHECK: [[LOOP_H1_HEADER:![0-9]+]] = distinct !{[[LOOP_H1_HEADER]], [[LOOP_WIDTH_8:![0-9]+]], [[LOOP_VEC_ENABLE]]}
// CHECK: [[LOOP_WIDTH_8]] = !{!"llvm.loop.vectorize.width", i32 8}
// CHECK: ![[ACCESS_GROUP_7]] = distinct !{}
// CHECK: [[LOOP_H1_HEADER:![0-9]+]] = distinct !{[[LOOP_H1_HEADER]], ![[PARALLEL_ACCESSES_9:[0-9]+]], [[LOOP_WIDTH_8]], [[LOOP_VEC_ENABLE]]}
// CHECK: ![[PARALLEL_ACCESSES_9]] = !{!"llvm.loop.parallel_accesses", ![[ACCESS_GROUP_7]]}
//
// Metadata for h2:
// CHECK: ![[ACCESS_GROUP_10]] = distinct !{}
// CHECK: [[LOOP_H2_HEADER]] = distinct !{[[LOOP_H2_HEADER]], ![[PARALLEL_ACCESSES_12:[0-9]+]], [[LOOP_VEC_ENABLE]]}
// CHECK: ![[PARALLEL_ACCESSES_12]] = !{!"llvm.loop.parallel_accesses", ![[ACCESS_GROUP_10]]}
//
// Metadata for h3:
// CHECK: ![[ACCESS_GROUP_13]] = distinct !{}
// CHECK: [[LOOP_H3_HEADER]] = distinct !{[[LOOP_H3_HEADER]], ![[PARALLEL_ACCESSES_15:[0-9]+]], [[LOOP_VEC_ENABLE]]}
// CHECK: ![[PARALLEL_ACCESSES_15]] = !{!"llvm.loop.parallel_accesses", ![[ACCESS_GROUP_13]]}
//
|