remarks_parallel_in_multiple_target_state_machines.c
9.05 KB
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
// RUN: %clang_cc1 -verify=host -Rpass=openmp -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -verify=all,safe -Rpass=openmp -fopenmp -O2 -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t.out
// RUN: %clang_cc1 -fexperimental-new-pass-manager -verify=all,safe -Rpass=openmp -fopenmp -O2 -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o %t.out
// host-no-diagnostics
void bar1(void) {
#pragma omp parallel // #0
// all-remark@#0 {{Found a parallel region that is called in a target region but not part of a combined target construct nor nesed inside a target construct without intermediate code. This can lead to excessive register usage for unrelated target regions in the same translation unit due to spurious call edges assumed by ptxas.}}
// safe-remark@#0 {{Parallel region is not known to be called from a unique single target region, maybe the surrounding function has external linkage?; will not attempt to rewrite the state machine use.}}
// force-remark@#0 {{[UNSAFE] Parallel region is not known to be called from a unique single target region, maybe the surrounding function has external linkage?; will rewrite the state machine use due to command line flag, this can lead to undefined behavior if the parallel region is called from a target region outside this translation unit.}}
// force-remark@#0 {{Specialize parallel region that is only reached from a single target region to avoid spurious call edges and excessive register usage in other target regions. (parallel region ID: __omp_outlined__2_wrapper, kernel ID: <NONE>}}
{
}
}
void bar2(void) {
#pragma omp parallel // #1
// all-remark@#1 {{Found a parallel region that is called in a target region but not part of a combined target construct nor nesed inside a target construct without intermediate code. This can lead to excessive register usage for unrelated target regions in the same translation unit due to spurious call edges assumed by ptxas.}}
// safe-remark@#1 {{Parallel region is not known to be called from a unique single target region, maybe the surrounding function has external linkage?; will not attempt to rewrite the state machine use.}}
// force-remark@#1 {{[UNSAFE] Parallel region is not known to be called from a unique single target region, maybe the surrounding function has external linkage?; will rewrite the state machine use due to command line flag, this can lead to undefined behavior if the parallel region is called from a target region outside this translation unit.}}
// force-remark@#1 {{Specialize parallel region that is only reached from a single target region to avoid spurious call edges and excessive register usage in other target regions. (parallel region ID: __omp_outlined__6_wrapper, kernel ID: <NONE>}}
{
}
}
void foo1(void) {
#pragma omp target teams // #2
// all-remark@#2 {{Target region containing the parallel region that is specialized. (parallel region ID: __omp_outlined__1_wrapper, kernel ID: __omp_offloading}}
// all-remark@#2 {{Target region containing the parallel region that is specialized. (parallel region ID: __omp_outlined__3_wrapper, kernel ID: __omp_offloading}}
{
#pragma omp parallel // #3
// all-remark@#3 {{Found a parallel region that is called in a target region but not part of a combined target construct nor nesed inside a target construct without intermediate code. This can lead to excessive register usage for unrelated target regions in the same translation unit due to spurious call edges assumed by ptxas.}}
// all-remark@#3 {{Specialize parallel region that is only reached from a single target region to avoid spurious call edges and excessive register usage in other target regions. (parallel region ID: __omp_outlined__1_wrapper, kernel ID: __omp_offloading}}
{
}
bar1();
#pragma omp parallel // #4
// all-remark@#4 {{Found a parallel region that is called in a target region but not part of a combined target construct nor nesed inside a target construct without intermediate code. This can lead to excessive register usage for unrelated target regions in the same translation unit due to spurious call edges assumed by ptxas.}}
// all-remark@#4 {{Specialize parallel region that is only reached from a single target region to avoid spurious call edges and excessive register usage in other target regions. (parallel region ID: __omp_outlined__3_wrapper, kernel ID: __omp_offloading}}
{
}
}
}
void foo2(void) {
#pragma omp target teams // #5
// all-remark@#5 {{Target region containing the parallel region that is specialized. (parallel region ID: __omp_outlined__5_wrapper, kernel ID: __omp_offloading}}
// all-remark@#5 {{Target region containing the parallel region that is specialized. (parallel region ID: __omp_outlined__7_wrapper, kernel ID: __omp_offloading}}
{
#pragma omp parallel // #6
// all-remark@#6 {{Found a parallel region that is called in a target region but not part of a combined target construct nor nesed inside a target construct without intermediate code. This can lead to excessive register usage for unrelated target regions in the same translation unit due to spurious call edges assumed by ptxas.}}
// all-remark@#6 {{Specialize parallel region that is only reached from a single target region to avoid spurious call edges and excessive register usage in other target regions. (parallel region ID: __omp_outlined__5_wrapper, kernel ID: __omp_offloading}}
{
}
bar1();
bar2();
#pragma omp parallel // #7
// all-remark@#7 {{Found a parallel region that is called in a target region but not part of a combined target construct nor nesed inside a target construct without intermediate code. This can lead to excessive register usage for unrelated target regions in the same translation unit due to spurious call edges assumed by ptxas.}}
// all-remark@#7 {{Specialize parallel region that is only reached from a single target region to avoid spurious call edges and excessive register usage in other target regions. (parallel region ID: __omp_outlined__7_wrapper, kernel ID: __omp_offloading}}
{
}
bar1();
bar2();
}
}
void foo3(void) {
#pragma omp target teams // #8
// all-remark@#8 {{Target region containing the parallel region that is specialized. (parallel region ID: __omp_outlined__9_wrapper, kernel ID: __omp_offloading}}
// all-remark@#8 {{Target region containing the parallel region that is specialized. (parallel region ID: __omp_outlined__10_wrapper, kernel ID: __omp_offloading}}
{
#pragma omp parallel // #9
// all-remark@#9 {{Found a parallel region that is called in a target region but not part of a combined target construct nor nesed inside a target construct without intermediate code. This can lead to excessive register usage for unrelated target regions in the same translation unit due to spurious call edges assumed by ptxas.}}
// all-remark@#9 {{Specialize parallel region that is only reached from a single target region to avoid spurious call edges and excessive register usage in other target regions. (parallel region ID: __omp_outlined__9_wrapper, kernel ID: __omp_offloading}}
{
}
bar1();
bar2();
#pragma omp parallel // #10
// all-remark@#10 {{Found a parallel region that is called in a target region but not part of a combined target construct nor nesed inside a target construct without intermediate code. This can lead to excessive register usage for unrelated target regions in the same translation unit due to spurious call edges assumed by ptxas.}}
// all-remark@#10 {{Specialize parallel region that is only reached from a single target region to avoid spurious call edges and excessive register usage in other target regions. (parallel region ID: __omp_outlined__10_wrapper, kernel ID: __omp_offloading}}
{
}
bar1();
bar2();
}
}
void spmd(void) {
// Verify we do not emit the remarks above for "SPMD" regions.
#pragma omp target teams
#pragma omp parallel
{
}
#pragma omp target teams distribute parallel for
for (int i = 0; i < 100; ++i) {
}
}
// all-remark@* 3 {{OpenMP runtime call __kmpc_global_thread_num moved to}}
// all-remark@* 3 {{OpenMP runtime call __kmpc_global_thread_num deduplicated}}