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
|
; RUN: opt -S -passes=openmpopt -pass-remarks=openmp-opt -openmp-print-gpu-kernels < %s | FileCheck %s
; RUN: opt -S -openmpopt -pass-remarks=openmp-opt -openmp-print-gpu-kernels < %s | FileCheck %s
; C input used for this test:
; void bar(void) {
; #pragma omp parallel
; { }
; }
; void foo(void) {
; #pragma omp target teams
; {
; #pragma omp parallel
; {}
; bar();
; #pragma omp parallel
; {}
; }
; }
; Verify we replace the function pointer uses for the first and last outlined
; region (1 and 3) but not for the middle one (2) because it could be called from
; another kernel.
; CHECK-DAG: @__omp_outlined__1_wrapper.ID = private constant i8 undef
; CHECK-DAG: @__omp_outlined__3_wrapper.ID = private constant i8 undef
; CHECK-DAG: icmp eq i8* %5, @__omp_outlined__1_wrapper.ID
; CHECK-DAG: icmp eq i8* %7, @__omp_outlined__3_wrapper.ID
; CHECK-DAG: call void @__kmpc_kernel_prepare_parallel(i8* @__omp_outlined__1_wrapper.ID)
; CHECK-DAG: call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void ()* @__omp_outlined__2_wrapper to i8*))
; CHECK-DAG: call void @__kmpc_kernel_prepare_parallel(i8* @__omp_outlined__3_wrapper.ID)
%struct.ident_t = type { i32, i32, i32, i32, i8* }
define internal void @__omp_offloading_35_a1e179_foo_l7_worker() {
entry:
%work_fn = alloca i8*, align 8
%exec_status = alloca i8, align 1
store i8* null, i8** %work_fn, align 8
store i8 0, i8* %exec_status, align 1
br label %.await.work
.await.work: ; preds = %.barrier.parallel, %entry
call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
%0 = call i1 @__kmpc_kernel_parallel(i8** %work_fn)
%1 = zext i1 %0 to i8
store i8 %1, i8* %exec_status, align 1
%2 = load i8*, i8** %work_fn, align 8
%should_terminate = icmp eq i8* %2, null
br i1 %should_terminate, label %.exit, label %.select.workers
.select.workers: ; preds = %.await.work
%3 = load i8, i8* %exec_status, align 1
%is_active = icmp ne i8 %3, 0
br i1 %is_active, label %.execute.parallel, label %.barrier.parallel
.execute.parallel: ; preds = %.select.workers
%4 = call i32 @__kmpc_global_thread_num(%struct.ident_t* null)
%5 = load i8*, i8** %work_fn, align 8
%work_match = icmp eq i8* %5, bitcast (void ()* @__omp_outlined__1_wrapper to i8*)
br i1 %work_match, label %.execute.fn, label %.check.next
.execute.fn: ; preds = %.execute.parallel
call void @__omp_outlined__1_wrapper()
br label %.terminate.parallel
.check.next: ; preds = %.execute.parallel
%6 = load i8*, i8** %work_fn, align 8
%work_match1 = icmp eq i8* %6, bitcast (void ()* @__omp_outlined__2_wrapper to i8*)
br i1 %work_match1, label %.execute.fn2, label %.check.next3
.execute.fn2: ; preds = %.check.next
call void @__omp_outlined__2_wrapper()
br label %.terminate.parallel
.check.next3: ; preds = %.check.next
%7 = load i8*, i8** %work_fn, align 8
%work_match4 = icmp eq i8* %7, bitcast (void ()* @__omp_outlined__3_wrapper to i8*)
br i1 %work_match4, label %.execute.fn5, label %.check.next6
.execute.fn5: ; preds = %.check.next3
call void @__omp_outlined__3_wrapper()
br label %.terminate.parallel
.check.next6: ; preds = %.check.next3
%8 = bitcast i8* %2 to void ()*
call void %8()
br label %.terminate.parallel
.terminate.parallel: ; preds = %.check.next6, %.execute.fn5, %.execute.fn2, %.execute.fn
call void @__kmpc_kernel_end_parallel()
br label %.barrier.parallel
.barrier.parallel: ; preds = %.terminate.parallel, %.select.workers
call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
br label %.await.work
.exit: ; preds = %.await.work
ret void
}
define weak void @__omp_offloading_35_a1e179_foo_l7() {
call void @__omp_offloading_35_a1e179_foo_l7_worker()
call void @__omp_outlined__()
ret void
}
define internal void @__omp_outlined__() {
call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void ()* @__omp_outlined__1_wrapper to i8*))
call void @bar()
call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void ()* @__omp_outlined__3_wrapper to i8*))
ret void
}
define internal void @__omp_outlined__1() {
ret void
}
define internal void @__omp_outlined__1_wrapper() {
call void @__omp_outlined__1()
ret void
}
define hidden void @bar() {
call void @__kmpc_kernel_prepare_parallel(i8* bitcast (void ()* @__omp_outlined__2_wrapper to i8*))
ret void
}
define internal void @__omp_outlined__2_wrapper() {
ret void
}
define internal void @__omp_outlined__3_wrapper() {
ret void
}
declare void @__kmpc_kernel_prepare_parallel(i8* %WorkFn)
declare zeroext i1 @__kmpc_kernel_parallel(i8** nocapture %WorkFn)
declare void @__kmpc_kernel_end_parallel()
declare void @__kmpc_barrier_simple_spmd(%struct.ident_t* nocapture readnone %loc_ref, i32 %tid)
declare i32 @__kmpc_global_thread_num(%struct.ident_t* nocapture readnone)
!nvvm.annotations = !{!0}
!0 = !{void ()* @__omp_offloading_35_a1e179_foo_l7, !"kernel", i32 1}
|
