I'm somewhat new to opencl and am trying to learn to use boost::compute properly. Consider the following code:
#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";
}
}
I have a vector of custom structs (actually much more complicated than shown here) that I want to process on the GPU. In the uncommented BOOST_COMPUTE_CLOSURE the compute::transform
passes the structs by value, processes them and then copies them back.
I would like to pass these by reference as shown in the commented out BOOST_COMPUTE_CLOSURE with compute::for_each
, but the kernel fails to compile (Build Program Failure
) when the program is run and I have not found any documentation mentioning how this should be achieved.
I know I can achieve passing by reference (pointers actually, since it's C99) by using BOOST_COMPUTE_STRINGIZE_SOURCE
and passing a pointer to the entire vector of structs, but I'd like to use the compute::...
functions as these seem more elegant.