|
|
|
@ -7,66 +7,18 @@ |
|
|
|
|
#endif |
|
|
|
|
|
|
|
|
|
#include <iostream> |
|
|
|
|
#include "cvconfig.h" |
|
|
|
|
#include "opencv2/core/core.hpp" |
|
|
|
|
#include "opencv2/gpu/gpu.hpp" |
|
|
|
|
|
|
|
|
|
#if !defined(HAVE_CUDA) || !defined(HAVE_TBB) |
|
|
|
|
|
|
|
|
|
int main() |
|
|
|
|
{ |
|
|
|
|
#if !defined(HAVE_CUDA) |
|
|
|
|
std::cout << "CUDA support is required (CMake key 'WITH_CUDA' must be true).\n"; |
|
|
|
|
#endif |
|
|
|
|
|
|
|
|
|
#if !defined(HAVE_TBB) |
|
|
|
|
std::cout << "TBB support is required (CMake key 'WITH_TBB' must be true).\n"; |
|
|
|
|
#endif |
|
|
|
|
|
|
|
|
|
return 0; |
|
|
|
|
} |
|
|
|
|
|
|
|
|
|
#else |
|
|
|
|
|
|
|
|
|
#include "opencv2/core/internal.hpp" // For TBB wrappers |
|
|
|
|
|
|
|
|
|
using namespace std; |
|
|
|
|
using namespace cv; |
|
|
|
|
using namespace cv::gpu; |
|
|
|
|
|
|
|
|
|
struct Worker { void operator()(int device_id) const; }; |
|
|
|
|
|
|
|
|
|
int main() |
|
|
|
|
struct Worker: public ParallelLoopBody |
|
|
|
|
{ |
|
|
|
|
int num_devices = getCudaEnabledDeviceCount(); |
|
|
|
|
if (num_devices < 2) |
|
|
|
|
virtual void operator() (const Range& range) const |
|
|
|
|
{ |
|
|
|
|
std::cout << "Two or more GPUs are required\n"; |
|
|
|
|
return -1; |
|
|
|
|
} |
|
|
|
|
for (int i = 0; i < num_devices; ++i) |
|
|
|
|
{ |
|
|
|
|
cv::gpu::printShortCudaDeviceInfo(i); |
|
|
|
|
|
|
|
|
|
DeviceInfo dev_info(i); |
|
|
|
|
if (!dev_info.isCompatible()) |
|
|
|
|
{ |
|
|
|
|
std::cout << "GPU module isn't built for GPU #" << i << " (" |
|
|
|
|
<< dev_info.name() << ", CC " << dev_info.majorVersion() |
|
|
|
|
<< dev_info.minorVersion() << "\n"; |
|
|
|
|
return -1; |
|
|
|
|
} |
|
|
|
|
} |
|
|
|
|
|
|
|
|
|
// Execute calculation in two threads using two GPUs
|
|
|
|
|
int devices[] = {0, 1}; |
|
|
|
|
parallel_do(devices, devices + 2, Worker()); |
|
|
|
|
|
|
|
|
|
return 0; |
|
|
|
|
} |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
void Worker::operator()(int device_id) const |
|
|
|
|
for (int device_id = range.start; device_id != range.end; ++device_id) |
|
|
|
|
{ |
|
|
|
|
setDevice(device_id); |
|
|
|
|
|
|
|
|
@ -94,5 +46,33 @@ void Worker::operator()(int device_id) const |
|
|
|
|
d_src.release(); |
|
|
|
|
d_dst.release(); |
|
|
|
|
} |
|
|
|
|
} |
|
|
|
|
}; |
|
|
|
|
|
|
|
|
|
#endif |
|
|
|
|
int main() |
|
|
|
|
{ |
|
|
|
|
int num_devices = getCudaEnabledDeviceCount(); |
|
|
|
|
if (num_devices < 2) |
|
|
|
|
{ |
|
|
|
|
std::cout << "Two or more GPUs are required\n"; |
|
|
|
|
return -1; |
|
|
|
|
} |
|
|
|
|
for (int i = 0; i < num_devices; ++i) |
|
|
|
|
{ |
|
|
|
|
cv::gpu::printShortCudaDeviceInfo(i); |
|
|
|
|
|
|
|
|
|
DeviceInfo dev_info(i); |
|
|
|
|
if (!dev_info.isCompatible()) |
|
|
|
|
{ |
|
|
|
|
std::cout << "GPU module isn't built for GPU #" << i << " (" |
|
|
|
|
<< dev_info.name() << ", CC " << dev_info.majorVersion() |
|
|
|
|
<< dev_info.minorVersion() << "\n"; |
|
|
|
|
return -1; |
|
|
|
|
} |
|
|
|
|
} |
|
|
|
|
|
|
|
|
|
// Execute calculation in several threads, 1 GPU per thread
|
|
|
|
|
parallel_for_(cv::Range(0, num_devices, Worker()); |
|
|
|
|
|
|
|
|
|
return 0; |
|
|
|
|
} |
|
|
|
|