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
|
/*
* Copyright 2008-2009 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.
*/
#pragma once
#include <cusp/detail/config.h>
#include <thrust/extrema.h>
#if THRUST_VERSION >= 100700
#include <thrust/system/cuda/detail/detail/launch_calculator.h>
#elif THRUST_VERSION >= 100600
#include <thrust/system/cuda/detail/arch.h>
#else
#include <thrust/detail/backend/cuda/arch.h>
#endif
namespace cusp
{
namespace detail
{
namespace device
{
namespace arch
{
template <typename KernelFunction>
size_t max_active_blocks(KernelFunction kernel, const size_t CTA_SIZE, const size_t dynamic_smem_bytes)
{
#if THRUST_VERSION >= 100700
using namespace thrust::system::cuda::detail;
function_attributes_t attributes = function_attributes(kernel);
device_properties_t properties = device_properties();
return properties.multiProcessorCount * cuda_launch_config_detail::max_active_blocks_per_multiprocessor(properties, attributes, CTA_SIZE, dynamic_smem_bytes);
#elif THRUST_VERSION >= 100600
return thrust::system::cuda::detail::arch::max_active_blocks(kernel, CTA_SIZE, dynamic_smem_bytes);
#else
return thrust::detail::backend::cuda::arch::max_active_blocks(kernel, CTA_SIZE, dynamic_smem_bytes);
#endif
}
} // end namespace arch
} // end namespace device
} // end namespace detail
} // end namespace cusp
|
