GOSTCoin CUDA miner project, compatible with most nvidia cards, containing only gostd algo
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

94 lines
2.9 KiB

/*
* Copyright 2008-2012 NVIDIA Corporation
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include <thrust/detail/config.h>
#include <thrust/system/omp/detail/reduce_intervals.h>
#include <thrust/iterator/iterator_traits.h>
#include <thrust/detail/function.h>
#include <thrust/detail/cstdint.h>
namespace thrust
{
namespace system
{
namespace omp
{
namespace detail
{
template <typename DerivedPolicy,
typename InputIterator,
typename OutputIterator,
typename BinaryFunction,
typename Decomposition>
void reduce_intervals(execution_policy<DerivedPolicy> &,
InputIterator input,
OutputIterator output,
BinaryFunction binary_op,
Decomposition decomp)
{
// we're attempting to launch an omp kernel, assert we're compiling with omp support
// ========================================================================
// X Note to the user: If you've found this line due to a compiler error, X
// X you need to enable OpenMP support in your compiler. X
// ========================================================================
THRUST_STATIC_ASSERT( (thrust::detail::depend_on_instantiation<InputIterator,
(THRUST_DEVICE_COMPILER_IS_OMP_CAPABLE == THRUST_TRUE)>::value) );
#if (THRUST_DEVICE_COMPILER_IS_OMP_CAPABLE == THRUST_TRUE)
typedef typename thrust::iterator_value<OutputIterator>::type OutputType;
// wrap binary_op
thrust::detail::host_function<BinaryFunction,OutputType> wrapped_binary_op(binary_op);
typedef thrust::detail::intptr_t index_type;
index_type n = static_cast<index_type>(decomp.size());
#if (THRUST_DEVICE_COMPILER_IS_OMP_CAPABLE == THRUST_TRUE)
# pragma omp parallel for
#endif // THRUST_DEVICE_COMPILER_IS_OMP_CAPABLE
for(index_type i = 0; i < n; i++)
{
InputIterator begin = input + decomp[i].begin();
InputIterator end = input + decomp[i].end();
if (begin != end)
{
OutputType sum = thrust::raw_reference_cast(*begin);
++begin;
while (begin != end)
{
sum = wrapped_binary_op(sum, *begin);
++begin;
}
OutputIterator tmp = output + i;
*tmp = sum;
}
}
#endif // THRUST_DEVICE_COMPILER_IS_OMP_CAPABLE
}
} // end namespace detail
} // end namespace omp
} // end namespace system
} // end namespace thrust