kernelfunc_1(sycl::queue&Q, int *ptr1,int*ptr2) {
image im3(ptr1, image_channel_order::rgba, image_channel_type::unsigned_int32, range{ M,N,L });
try
{
auto ev3 = Q.submit([&](handler &h) {
auto out = sycl::stream(1024, 1024, h);
accessor<int4, 2, access::mode::write, access::target::image_array> acs3_w(im3, h);
im3.set_final_data(ptr1);
h.parallel_for(nd_range{ range{ M ,N,L}, range{ 1,1,1 } }, [=](nd_item<3> it) {
int idx = it.get_global_linear_id();
if (idx == 0) {
for (int k = 0; k < L; k++) {
out << "layer:" << k << ":" << sycl::endl;
for (int i = 0; i < M; i++) {
for (int j = 0; j < N; j++)
{
if (i == 0 && j == 0 && k == 0) continue;
acs3_w[k].write(int2(i, j), int4(1, 2, 3, 4));
}
out << sycl::endl;
}
}
}
});
}
);
return ev3;
}
catch (const std::exception& e)
{
std::cout << "An exception is caught for vector add.\n" << e.what();
std::terminate();
}
}
auto kernelfunc_2(sycl::queue&Q, int *ptr1, int*ptr2) {
Q.wait();
buffer ptr(ptr1, range{ N*M*L*C });
ptr.set_final_data(ptr2);
try
{
auto ev2 = Q.submit([&](handler &h) {
ptr.set_final_data(ptr2);
accessor acs(ptr, h);
auto out = sycl::stream(1024, 1024, h);
h.parallel_for(nd_range{ range{ M ,N,L}, range{ 1,1,1 } }, [=](nd_item<3> it) {
int idx = it.get_global_linear_id();
if (idx == 0) {
for (int k = 0; k < L; k++) {
acs[0] = 999;
}
}
});
}
);
return ev2;
}
catch (const std::exception& e)
{
std::cout << "An exception is caught for vector add.\n" << e.what();
std::terminate();
}
}
int main(){
kernelfunc_1(Q, host_array3_2,host_array3_2);
kernelfunc_2(Q, shared_array3_2, shared_array3_2);
---------------------v1---------------------------------------------
kernelfunc_1(Q, host_array3_2,shared_array3_2);
kernelfunc_2(Q, shared_array3_2, shared_array3_2);
----------------------v2--------------------------------------------
The V1 can produce the correct result. Obviously, there is no relationship between the two functions.
However, the V2 REALLY confuses me a lot, as you can see in the kernelfunc_1, I didn't use the shared_array3_2, why the v2 will get stuck like this:
my programming environment :
VS2017
one API DPC++ Compiler (2021.3.0)
windows 10.
can anybody tell me why?
}
Link Copied
