/src/Simd/src/Simd/SimdParallel.hpp

Source
/*
* Simd Library (http://ermig1979.github.io/Simd).
*
* Copyright (c) 2011-2023 Yermalayeu Ihar.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#ifndef __SimdParallel_hpp__
#define __SimdParallel_hpp__

#include <vector>
#include <thread>
#ifndef SIMD_FUTURE_DISABLE
#include <future>
#endif

namespace Simd
{
    template<class Function> inline void Parallel(size_t begin, size_t end, const Function & function, size_t threadNumber, size_t blockAlign = 1)
    {
#ifdef SIMD_FUTURE_DISABLE
        function(0, begin, end);
#else
        static const size_t threadNumberMax = std::thread::hardware_concurrency();
        threadNumber = std::min<size_t>(threadNumber, threadNumberMax);
        if (threadNumber <= 1 || size_t(blockAlign*1.5) >= (end - begin))
            function(0, begin, end);
        else
        {
            std::vector<std::future<void>> futures;

            size_t blockSize = (end - begin + threadNumber - 1) / threadNumber;
            blockSize = (blockSize + blockAlign - 1) / blockAlign * blockAlign;
            size_t blockBegin = begin;
            size_t blockEnd = blockBegin + blockSize;

            for (size_t thread = 0; thread < threadNumber && blockBegin < end; ++thread)
            {
                futures.push_back(std::move(std::async(std::launch::async, [blockBegin, blockEnd, thread, &function] { function(thread, blockBegin, blockEnd); })));
                blockBegin += blockSize;
                blockEnd = std::min(blockBegin + blockSize, end);
            }

            for (size_t i = 0; i < futures.size(); ++i)
                futures[i].wait();
        }
#endif
    }
}

#endif//__SimdParallel_hpp__

Line	Count	Source
1		/*
2		* Simd Library (http://ermig1979.github.io/Simd).
3		*
4		* Copyright (c) 2011-2023 Yermalayeu Ihar.
5		*
6		* Permission is hereby granted, free of charge, to any person obtaining a copy
7		* of this software and associated documentation files (the "Software"), to deal
8		* in the Software without restriction, including without limitation the rights
9		* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
10		* copies of the Software, and to permit persons to whom the Software is
11		* furnished to do so, subject to the following conditions:
12		*
13		* The above copyright notice and this permission notice shall be included in
14		* all copies or substantial portions of the Software.
15		*
16		* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17		* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18		* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
19		* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20		* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21		* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22		* SOFTWARE.
23		*/
24		#ifndef __SimdParallel_hpp__
25		#define __SimdParallel_hpp__
26
27		#include <vector>
28		#include <thread>
29		#ifndef SIMD_FUTURE_DISABLE
30		#include <future>
31		#endif
32
33		namespace Simd
34		{
35		template<class Function> inline void Parallel(size_t begin, size_t end, const Function & function, size_t threadNumber, size_t blockAlign = 1)
36	0	{
37		#ifdef SIMD_FUTURE_DISABLE
38		function(0, begin, end);
39		#else
40	0	static const size_t threadNumberMax = std::thread::hardware_concurrency();
41	0	threadNumber = std::min<size_t>(threadNumber, threadNumberMax);
42	0	if (threadNumber <= 1 \|\| size_t(blockAlign*1.5) >= (end - begin))
43	0	function(0, begin, end);
44	0	else
45	0	{
46	0	std::vector<std::future<void>> futures;
47
48	0	size_t blockSize = (end - begin + threadNumber - 1) / threadNumber;
49	0	blockSize = (blockSize + blockAlign - 1) / blockAlign * blockAlign;
50	0	size_t blockBegin = begin;
51	0	size_t blockEnd = blockBegin + blockSize;
52
53	0	for (size_t thread = 0; thread < threadNumber && blockBegin < end; ++thread)
54	0	{
55	0	futures.push_back(std::move(std::async(std::launch::async, [blockBegin, blockEnd, thread, &function] { function(thread, blockBegin, blockEnd); }))); Unexecuted instantiation: SimdBaseResizerNearest.cpp:Simd::Parallel<Simd::Base::ResizerNearest::Run(unsigned char const, unsigned long, unsigned char, unsigned long)::$_0>(unsigned long, unsigned long, Simd::Base::ResizerNearest::Run(unsigned char const, unsigned long, unsigned char, unsigned long)::$_0 const&, unsigned long, unsigned long)::{lambda()#1}::operator()() const Unexecuted instantiation: SimdBaseWarpAffine.cpp:Simd::Parallel<Simd::Base::WarpAffineNearest::Run(unsigned char const, unsigned char)::$_0>(unsigned long, unsigned long, Simd::Base::WarpAffineNearest::Run(unsigned char const, unsigned char)::$_0 const&, unsigned long, unsigned long)::{lambda()#1}::operator()() const Unexecuted instantiation: SimdBaseWarpAffine.cpp:Simd::Parallel<Simd::Base::WarpAffineByteBilinear::Run(unsigned char const, unsigned char)::$_0>(unsigned long, unsigned long, Simd::Base::WarpAffineByteBilinear::Run(unsigned char const, unsigned char)::$_0 const&, unsigned long, unsigned long)::{lambda()#1}::operator()() const Unexecuted instantiation: Simd::Parallel<Simd::GemmNN<float, 4ul, unsigned long>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNN<float, 4ul, unsigned long>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long)::{lambda()#1}::operator()() const Unexecuted instantiation: Simd::Parallel<Simd::GemmNT<float, 4ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNT<float, 4ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long)::{lambda()#1}::operator()() const Unexecuted instantiation: Simd::Parallel<Simd::GemmNN<float, 8ul, unsigned long>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNN<float, 8ul, unsigned long>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long)::{lambda()#1}::operator()() const Unexecuted instantiation: Simd::Parallel<Simd::GemmNT<float, 8ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNT<float, 8ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long)::{lambda()#1}::operator()() const Unexecuted instantiation: Simd::Parallel<Simd::GemmNN<float, 16ul, unsigned short>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNN<float, 16ul, unsigned short>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long)::{lambda()#1}::operator()() const Unexecuted instantiation: Simd::Parallel<Simd::GemmNT<float, 16ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNT<float, 16ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long)::{lambda()#1}::operator()() const
56	0	blockBegin += blockSize;
57	0	blockEnd = std::min(blockBegin + blockSize, end);
58	0	}
59
60	0	for (size_t i = 0; i < futures.size(); ++i)
61	0	futures[i].wait();
62	0	}
63	0	#endif
64	0	} Unexecuted instantiation: SimdBaseResizerNearest.cpp:void Simd::Parallel<Simd::Base::ResizerNearest::Run(unsigned char const, unsigned long, unsigned char, unsigned long)::$_0>(unsigned long, unsigned long, Simd::Base::ResizerNearest::Run(unsigned char const, unsigned long, unsigned char, unsigned long)::$_0 const&, unsigned long, unsigned long) Unexecuted instantiation: SimdBaseWarpAffine.cpp:void Simd::Parallel<Simd::Base::WarpAffineNearest::Run(unsigned char const, unsigned char)::$_0>(unsigned long, unsigned long, Simd::Base::WarpAffineNearest::Run(unsigned char const, unsigned char)::$_0 const&, unsigned long, unsigned long) Unexecuted instantiation: SimdBaseWarpAffine.cpp:void Simd::Parallel<Simd::Base::WarpAffineByteBilinear::Run(unsigned char const, unsigned char)::$_0>(unsigned long, unsigned long, Simd::Base::WarpAffineByteBilinear::Run(unsigned char const, unsigned char)::$_0 const&, unsigned long, unsigned long) Unexecuted instantiation: void Simd::Parallel<Simd::GemmNN<float, 4ul, unsigned long>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNN<float, 4ul, unsigned long>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long) Unexecuted instantiation: void Simd::Parallel<Simd::GemmNT<float, 4ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNT<float, 4ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long) Unexecuted instantiation: void Simd::Parallel<Simd::GemmNN<float, 8ul, unsigned long>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNN<float, 8ul, unsigned long>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long) Unexecuted instantiation: void Simd::Parallel<Simd::GemmNT<float, 8ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNT<float, 8ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long) Unexecuted instantiation: void Simd::Parallel<Simd::GemmNN<float, 16ul, unsigned short>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNN<float, 16ul, unsigned short>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long) Unexecuted instantiation: void Simd::Parallel<Simd::GemmNT<float, 16ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1}>(unsigned long, unsigned long, Simd::GemmNT<float, 16ul>::Run(float const, float const, unsigned long, float const, unsigned long, float const, float, unsigned long)::{lambda(unsigned long, unsigned long, unsigned long)#1} const&, unsigned long, unsigned long)
65		}
66
67		#endif//__SimdParallel_hpp__

Coverage Report

Created: 2025-11-16 06:41