File: target_num_teams_num_threads_attributes.cpp

package info (click to toggle)
llvm-toolchain-19 1%3A19.1.7-3
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 1,998,520 kB
  • sloc: cpp: 6,951,680; ansic: 1,486,157; asm: 913,598; python: 232,024; f90: 80,126; objc: 75,281; lisp: 37,276; pascal: 16,990; sh: 10,009; ml: 5,058; perl: 4,724; awk: 3,523; makefile: 3,167; javascript: 2,504; xml: 892; fortran: 664; cs: 573
file content (91 lines) | stat: -rw-r--r-- 2,860 bytes parent folder | download | duplicates (6)
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
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s 
// RUN: %clang_cc1 -target-cpu gfx900 -fopenmp -x c++ -std=c++11 -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fopenmp-targets=nvptx64 -emit-llvm-bc %s -o %t-ppc-host.bc
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple nvptx64 -fopenmp-targets=nvptx64 -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s 
// RUN: %clang_cc1 -target-cpu sm_80 -fopenmp -x c++ -std=c++11 -triple nvptx64 -fopenmp-targets=nvptx64 -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s

// expected-no-diagnostics


#ifndef HEADER
#define HEADER


void default_val_num_teams() {
    #pragma omp target simd
    for (int i = 0; i < 22; i++)
        int a_var;
}

void foo1() {
    #pragma omp target teams num_teams(22)
    { int a_var; }
}

void foo2() {
    #pragma omp target teams distribute num_teams(22)
    for (int i = 0; i < 22; i++)
        int a_var;
}

void foo3() {
    #pragma omp target teams distribute parallel for num_teams(22)
    for (int i = 0; i < 22; i++)
        int a_var;
}

void bar1() {
    #pragma omp target teams num_teams(22)
    { int a_var; }
}

void bar2() {
    #pragma omp target teams distribute num_teams(33)
    for (int i = 0; i < 22; i++)
        int a_var;
}

void bar3() {
    #pragma omp target teams distribute parallel for num_teams(44)
    for (int i = 0; i < 22; i++)
        int a_var;
}

void const_int() {
    const int NT = 22;
    #pragma omp target teams num_teams(NT)
    { int a_var; }
}

void thread_limit() {
    #pragma omp target teams thread_limit(22)
    { int a_var; }
}

void num_threads() {
    #pragma omp target teams distribute parallel for thread_limit(22) num_threads(11)
    for (int i = 0; i < 22; i++)
        int a_var;
}

void threads_and_teams() {
    #pragma omp target teams distribute parallel for thread_limit(22) num_teams(33)
    for (int i = 0; i < 22; i++)
        int a_var;
}

#endif


// CHECK:      "omp_target_num_teams"="1"
// CHECK:      "omp_target_num_teams"="22"
// CHECK:      "omp_target_num_teams"="33"
// CHECK:      "omp_target_num_teams"="44"

// CHECK:      "omp_target_thread_limit"="22"

// CHECK:      "omp_target_thread_limit"="11"

// CHECK:      "omp_target_num_teams"="33"
// CHECK-SAME: "omp_target_thread_limit"="22"