我对 opencl 有点陌生,正在尝试学习正确使用 boost::compute。考虑以下代码:
#include <iostream>
#include <vector>
#include <boost/compute.hpp>
const cl_int cell_U_size{ 4 };
#pragma pack (push,1)
struct Cell
{
cl_double U[cell_U_size];
};
#pragma pack (pop)
BOOST_COMPUTE_ADAPT_STRUCT(Cell, Cell, (U));
int main(int argc, char* argv[])
{
using namespace boost;
auto device = compute::system::default_device();
auto context = compute::context(device);
auto queue = compute::command_queue(context, device);
std::vector<Cell> host_Cells;
host_Cells.reserve(10);
for (auto j = 0; j < host_Cells.capacity(); ++j) {
host_Cells.emplace_back(Cell());
for (auto i = 0; i < cell_U_size; ++i) {
host_Cells.back().U[i] = static_cast<cl_double>(i+j);
}
}
std::cout << "Before:\n";
for (auto const& hc : host_Cells) {
for (auto const& u : hc.U)
std::cout << " " << u;
std::cout << "\n";
}
compute::vector<Cell> device_Cells(host_Cells.size(), context);
auto f = compute::copy_async(host_Cells.begin(), host_Cells.end(), device_Cells.begin(), queue);
try {
BOOST_COMPUTE_CLOSURE(Cell, Step1, (Cell cell), (cell_U_size), {
for (int i = 0; i < cell_U_size; ++i) {
cell.U[i] += 1.0;
}
return cell;
});
f.wait(); // Wait for data to finish being copied
compute::transform(device_Cells.begin(), device_Cells.end(), device_Cells.begin(), Step1, queue);
//BOOST_COMPUTE_CLOSURE(void, Step2, (Cell &cell), (cell_U_size), {
// for (int i = 0; i < cell_U_size; ++i) {
// cell.U[i] += 1.0;
// }
//});
//compute::for_each(device_Cells.begin(), device_Cells.end(), Step2, queue);
compute::copy(device_Cells.begin(), device_Cells.end(), host_Cells.begin(), queue);
}
catch (std::exception &e) {
std::cout << e.what() << std::endl;
throw;
}
std::cout << "After:\n";
for (auto const& hc : host_Cells) {
for (auto const& u : hc.U)
std::cout << " " << u;
std::cout << "\n";
}
}
我有一个要在 GPU 上处理的自定义结构向量(实际上比此处显示的要复杂得多)。在未注释的 BOOST_COMPUTE_CLOSURE 中,compute::transform
按值传递结构,处理它们,然后将它们复制回来。
我想通过引用来传递这些,如注释掉的 BOOST_COMPUTE_CLOSURE 所示compute::for_each
,但是当程序运行时内核无法编译(Build Program Failure
),我还没有找到任何文档提到如何实现这一点。
我知道我可以通过使用和传递指向整个结构向量的指针来实现按引用传递(实际上是指针,因为它是 C99)BOOST_COMPUTE_STRINGIZE_SOURCE
,但我想使用这些compute::...
函数,因为这些函数看起来更优雅。