File: parallel_for.h

package info (click to toggle)
swiftlang 6.0.3-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 2,519,992 kB
  • sloc: cpp: 9,107,863; ansic: 2,040,022; asm: 1,135,751; python: 296,500; objc: 82,456; f90: 60,502; lisp: 34,951; pascal: 19,946; sh: 18,133; perl: 7,482; ml: 4,937; javascript: 4,117; makefile: 3,840; awk: 3,535; xml: 914; fortran: 619; cs: 573; ruby: 573
file content (64 lines) | stat: -rw-r--r-- 2,134 bytes parent folder | download | duplicates (17)
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
// -*- C++ -*-
// -*-===----------------------------------------------------------------------===//
//
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
//
//===----------------------------------------------------------------------===//

#ifndef _PSTL_INTERNAL_OMP_PARALLEL_FOR_H
#define _PSTL_INTERNAL_OMP_PARALLEL_FOR_H

#include <cstddef>

#include "util.h"

namespace __pstl
{
namespace __omp_backend
{

template <class _Index, class _Fp>
void
__parallel_for_body(_Index __first, _Index __last, _Fp __f)
{
    // initial partition of the iteration space into chunks
    auto __policy = __omp_backend::__chunk_partitioner(__first, __last);

    // To avoid over-subscription we use taskloop for the nested parallelism
    _PSTL_PRAGMA(omp taskloop untied mergeable)
    for (std::size_t __chunk = 0; __chunk < __policy.__n_chunks; ++__chunk)
    {
        __pstl::__omp_backend::__process_chunk(__policy, __first, __chunk, __f);
    }
}

//------------------------------------------------------------------------
// Notation:
// Evaluation of brick f[i,j) for each subrange [i,j) of [first, last)
//------------------------------------------------------------------------

template <class _ExecutionPolicy, class _Index, class _Fp>
void
__parallel_for(__pstl::__internal::__openmp_backend_tag, _ExecutionPolicy&&, _Index __first, _Index __last, _Fp __f)
{
    if (omp_in_parallel())
    {
        // we don't create a nested parallel region in an existing parallel
        // region: just create tasks
        __pstl::__omp_backend::__parallel_for_body(__first, __last, __f);
    }
    else
    {
        // in any case (nested or non-nested) one parallel region is created and
        // only one thread creates a set of tasks
        _PSTL_PRAGMA(omp parallel)
        _PSTL_PRAGMA(omp single nowait) { __pstl::__omp_backend::__parallel_for_body(__first, __last, __f); }
    }
}

} // namespace __omp_backend
} // namespace __pstl
#endif // _PSTL_INTERNAL_OMP_PARALLEL_FOR_H